breeze5428

CVPR 2014 论文

转载网址：http://www.cvpapers.com/cvpr2014.html

BING: Binarized Normed Gradients for Objectness Estimation at 300fps这篇会带来大量引用。

通过筛选出可能的候选窗口作为detection的bounding box输入，避免检测时滑块在image上做穷尽滑动。

Accepted Orals

Reconstructing Storyline Graphs for Image Recommendation from Web Community Photos ( project, PDF): Gunhee Kim* (Disney Research), Eric Xing (Carnegie Mellon University)
Unsupervised One-Class Learning for Automatic Outlier Removal: Wei Liu* (IBM Thomas J. Watson Research), Gang Hua (Stevens Institute of Technology), John Smith (IBM T. J. Watson Research Center)
Critical Configurations For Radial Distortion Self-Calibration ( PDF): Changchang Wu* (Google)
Active Flattening of Curved Document Images via Two Structured Beams ( PDF): Gaofeng MENG ( NLPR, CASIA), Ying WANG, Shenquan QU, Shiming XIANG, Chunhong PAN
Segmentation-Free Dynamic Scene Deblurring: Tae Hyun Kim (Seoul National University), Kyoung Mu Lee* (Seoul National University)
Diffuse Mirrors: 3D Reconstruction from Diffuse Indirect Illumination Using Inexpensive Time-of-Flight Sensors: Felix Heide* (University of British Columbia), Lei Xiao (University of British Columbia), Wolfgang Heidrich (University of British Columbia), Matthias B. Hullin (University of Bonn)
A Primal-Dual Method for Higher-Order Multilabel Markov Random Fields ( PDF): Alexander Fix (Cornell), Chen Wang ([email protected]), Ramin Zabih*
Single Image Layer Separation using Relative Smoothness: YU LI* (NUS), Michael Brown (NUS)
L0 Regularized Stationary Time Estimation for Crowd Group Analysis ( PDF): SHUAI YI* (The Chinese University of HK), Xiaogang Wang (Chinese University of Hong Kong), Cewu Lu (The Hong Kong University of Sc), Jiaya Jia (CUHK)
Shape-Preserving Half-Projective Warps for Image Stitching: Che-Han Chang* (National Taiwan University), Yoichi Sato (Univ of Tokyo), Yung-Yu Chuang (NTU)
Parsing videos of actions with segmental grammars: Hamed Pirsiavash* (MIT), Deva Ramanan
Multiscale Centerline Detection by Learning a Scale-Space Distance Transform ( PDF,supplementary material): Amos Sironi* (EPFL), Vincent Lepetit (EPFL), Pascal Fua (EPFL)
Context Driven Scene Parsing with Attention to Rare Classes ( PDF): Jimei Yang* (UC Merced), Brian Price, Scott Cohen (Adobe Inc.), Ming-Hsuan Yang (UC Merced)
Multi-Object Tracking via Constrained Sequential Labeling ( PDF): Sheng Chen* (Oregon State University), Alan Fern (Oregon State University), Sinisa Todorovic (Oregon State University)
Unsupervised Spectral Dual Assignment Clustering of Human Actions in Context ( PDF, code): Simon Jones (The University of Sheffield), Ling Shao* (The University of Sheffield)
Bayesian View Synthesis and Image-Based Rendering Principles ( PDF, abstract): Sergi Pujades (INRIA), Frederic Devernay (INRIA), Bastian Goldluecke (HCI)
BING: Binarized Normed Gradients for Objectness Estimation at 300fps (project,PDF,code,slides): Ming-Ming Cheng ( University of Oxford), Ziming Zhang (Boston University), Wen-Yan Lin (Oxford Brookes University), Philip Torr ( University of Oxford)
Multivariate General Linear Models (MGLM) on Riemannian Manifolds with Applications to Statistical Analysis of Diffusion Weighted Images: Hyunwoo Kim* (University of Wisconsin-Madison), Nagesh Adluru (University of Wisconsin-Madiso), Maxwell Collins (University of Wisconsin-Madison), Moo Chung (University of Wisconsin-Madison), barbara Bendlin (University of Wisconsin-Madison), Sterling Johnson (University of Wisconsin-Madison), Richard Davidson (University of Wisconsin-Madison), Vikas Singh (University of Wisconsin-Madison)
Spectral Graph Reduction for Efficient Image and Streaming Video Segmentation ( PDF): Fabio Galasso* (Max Planck Institute), Margret Keuper (University of Freiburg), Thomas Brox (University of Freiburg), Bernt Schiele (Max Planck Institute)
Learning Scalable Discriminative Attributes with Sample Relatedness: Jiashi Feng* (NUS), Stefanie Jegelka , Trevor Darrell (University of California Berkeley), Huan Xu , Shuicheng Yan (National University of Singapore)
Object Non-detection: Hiding an Object from Many Viewpoints: Andrew Owens* (MIT), Connelly Barnes (University of Virginia), Alex Flint (Ogemento), hanumant Singh (Woods Hole Oceanographic Institution), Bill Freeman (MIT)
DeepPose: Human Pose Estimation via Deep Neural Networks ( PDF): Alexander Toshev* (Google), Christian Szegedy
Neural Decision Forests for Semantic Image Labelling ( PDF, supplementary material): Samuel Rota Bulo` (FBK-irst), Peter Kontschieder (Microsoft Research)
Learning Everything about Anything: Webly-Supervised Visual Concept Learning: Santosh Kumar Divvala* (University of Washington), Ali Farhadi (University of Washington), Carlos Guestrin (University of Washington)
Scene Labeling Using Beam Search Under Mutex Constraints ( PDF) - formely: Heuristic-Score Beam Search for Scene Labeling: Anirban Roy* (Oregon State University), Sinisa Todorovic (Oregon State University)
Parallax-tolerant Image Stitching: Fan Zhang (Portland State University), Feng Liu* (Portland State University)
Second-order Shape Optimization for Geometric Inverse Problems in Vision ( PDF): Jonathan Balzer* (UCLA), Stefano Soatto (University of California at Los Angeles)
Hierarchical Subquery Evaluation for Active Learning on a Graph ( project): Oisin Mac Aodha* (UCL), Neill D.F. Campbell (UCL), Jan Kautz (UCL), Gabriel J. Brostow (UCL)
PANDA: Pose Aligned Networks for Deep Attribute Modeling ( PDF): Ning Zhang (UC Berkeley), Manohar Paluri (Facebook), Marc'Aurelio Ranzato, Trevor Darrell (UC Berkeley), Lubomir Bourdev (Facebook)
Realtime and Robust Hand Tracking from Depth: Chen Qian (CUHK), Xiao Sun (Microsoft Research Asia), Yichen Wei* (Microsoft Research Asia), Xiaoou Tang (Chinese University of Hong Kong), Jian Sun
Energy based multi-model fitting & matching for 3D reconstruction: Hossam Isack* (Western Ontario), Yuri Boykov (University of Western Ontario)
Robust Subspace Segmentation with Block-diagonal Prior ( PDF, supplementary material): Jiashi Feng* (NUS), Zhouchen Lin (Peking University), Huan Xu, Shuicheng Yan (National University of Singapore)
Grassmann Averages for Scalable Robust PCA: Soren Hauberg* (Max Planck Institute), Aasa Feragen (University of Copenhagen), Michael Black (Max Planck)
Multiview Shape and Reflectance from Natural Illumination: Geoffrey Oxholm* (Drexel University), Ko Nishino
Adaptive Partial Differential Equation Learning for Visual Saliency Detection ( PDF, supplementary material): Risheng Liu* (Dalian University of Technolog), Zhouchen Lin (Peking University), Shiguang Shan (Chinese Academy of Sciences)
Local Regularity-driven City-scale Facade Detection from Aerial Images: Yanxi Liu* (Penn State University), Jingchen Liu (PSU)
L0 norm based dictionary learning method with global convergence: Chenglong Bao (nus.edu.sg), Hui Ji* (Natl Univ Singapore), Yuhui Quan (nus.edu.sg), Zuowei Shen (nus.edu.sg)
Optimal Decisions from Probabilistic Models: the Intersection-over-Union Case ( PDF, supplementary material, code): Sebastian Nowozin* ( Microsoft Research)
Rich feature hierarchies for accurate object detection and semantic segmentation ( code, PDF, supplementary material, technical report): Ross Girshick (UC Berkeley), Jeff Donahue (UC Berkeley and ICSI), Trevor Darrell (UC Berkeley and ICSI), Jitendra Malik (UC Berkeley)
Surface-from-Gradients: An Approach Based on Discrete Geometry Processing: Wuyuan Xie (Chinese Univ. of Hong Kong), Yunbo Zhang (University at Buffalo), Charlie C L Wang* (Chinese Univ. of Hong Kong)
Nearest Neighbor-based Label Transfer for Weakly Supervised Multiclass Video Segmentation ( PDF): Xiao Liu* (Zhejiang University), Dacheng Tao, Mingli Song (zju), Ying Ruan (zju), Chun Chen (zju), Jiajun Bu (zju)
Minimal Solvers for Relative Pose with a Single Unknown Radial Distortion: Yubin Kuang* (Centre for Mathematical Scienc), Jan Erik Solem (Centre for Mathematical Sciences, Lund University), Kalle Astroem (Lund University), Fredrik Kahl (Lund University)
Partial Optimality by Pruning for MAP-inference with General Graphical Models ( PDF): Paul Swoboda* (Heidelberg University), Bogdan Savchynskyy (Heidelberg University), Joerg Kappes (Heidelberg University), Christoph SchnÃ£rr
Learning to disambiguate indistinguishable objects over time: weakly supervised structured learning: Luca Fiaschi* (HCI/IWR University of Heidelberg), Ferran Diego (HCI/IWR University of Heidelberg), Konstantin Gregor (HCI/IWR University of Heidelberg), Ullrich Koethe (HCI/IWR University of Heidelberg), Marta Zlatic (HHMI Janelia Farm), Fred Hamprecht (HCI/IWR University of Heidelberg)
Filter Forests for Learning Data-Dependent Convolutional Kernels: Sean Ryan Fanello* (IIT), Cem Keskin (Microsoft Research), Pushmeet Kohli , Shahram Izadi (Microsoft Research), Jamie Shotton (Microsoft Research), Antonio Criminisi (Microsoft Research), Ugo Pattacini (IIT), Tim Paek (Microsoft)
Rate-Invariant Analysis of Trajectories on Riemannian Manifolds with Application in Visual Speech Recognition: Jingyong Su* (Texas Tech University), Anuj Srivastava , Fillipe Souza (University of South Florida), Sudeep Sarkar (University of South Florida)
Video Event Detection by Inferring Temporal Instance Labels ( PDF, project): Kuan-Ting Lai* (National Taiwan University), Felix Yu (Columbia University), Ming-Syan Chen, Shih-Fu Chang
Decorrelating Semantic Visual Attributes by Resisting the Urge to Share ( PDF): Dinesh Jayaraman* (UT Austin), Fei Sha (University of Southern California), Kristen Grauman (University of Texas at Austin)
Triangulation embedding and democratic aggregation for image search ( PDF): Herve Jegou* (INRIA), Andrew Zisserman (Oxford)
Image Fusion with Local Spectral Consistency and Dynamic Gradient Sparsity ( PDF): Chen Chen* (UT Arlington), Junzhou Huang, Wei Liu (IBM Thomas J. Watson Research)
Transparent Object Reconstruction via Coded Transport of Intensity: Chenguang Ma (Tsinghua University), Xing Lin (Tsinghua University), Jinli Suo (Tsinghua University), Qionghai Dai (Tsinghua University), Gordon Wetzstein* (MIT)
Scene-Independent Group Profiling in Crowd: Jing Shao* (The Chinese University of HK), Chen Change Loy, Xiaogang Wang (Chinese University of Hong Kong)
Learning Euclidean-to-Riemannian Metric for Point-to-Set Classification: Zhiwu Huang* (Chinese Academy of Sciences), Ruiping Wang (Institute of Computing Technology , Chinese Academy of Sciences), Shiguang Shan (Chinese Academy of Sciences), Xilin Chen
Pulling Things out of Perspective: Lubor Ladicky* , Jianbo Shi , Marc Pollefeys (ETH)
Adaptive Color Attributes for Real-Time Visual Tracking ( PDF, project): Martin Danelljan* (CVL, Linkoping University), Fahad Shahbaz Khan (CVL, Linkoping University), Michael Felsberg (CVL, Linkoping University), Joost van de Weijer (Computer Vision Center Barcelona)
Reconstructing PASCAL VOC ( project,videos,code,PDF,supplementary material): Sara Vicente (University College London), Joao Carreira* (ISR-Coimbra), Lourdes Agapito (University College London), Jorge Batista (ISR - University of Coimbra)
Trinocular Geometry Revisited: Jean Ponce* (Ecole Normale Superieure), Martial Hebert (Carnegie Mellon University)
3D Shape and Indirect Appearance by Structured Light Transport ( project, PDF, supplementary material): Matthew O\'Toole* (University of Toronto), John Mather (University of Toronto), Kiriakos N. Kutulakos (University of Toronto)
Shrinkage Fields for Effective Image Restoration ( PDF, supplementary material): Uwe Schmidt (TU Darmstadt), Stefan Roth (TU Darmstadt)
Temporal Sequence Modeling For Video Event Detection ( PDF): Yu Cheng* (IBM Research, Northwestern University), Quanfu Fan (IBM Research), Sharath Pankanti (IBM Research), Alok Choudhary (Northwestern University)
Reflectance and Fluorescent Spectra Recovery based on Fluorescent Chromaticity Invariance under Varying Illumination: Ying Fu* (The University of Tokyo), Antony Lam (National Institute of Informatics), Yasuyuki Kobashi (Ministry of Internal Affairs and Communications), Imari Sato (National Institute of Informatics), Takahiro Okabe (Kyushu Institute of Technology), Yoichi Sato (Univ of Tokyo)
Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group: Raviteja Vemulapalli* (University of Maryland), Felipe Arrate (University of Maryland , College Park), Rama Chellappa (University of Maryland)
Anytime Recognition of Objects and Scenes ( PDF, project): Sergey Karayev (UC Berkeley), Mario Fritz (MPI for Informatics), Trevor Darrell (UC Berkeley)
Preconditioning for Accelerated Iteratively Reweighted Least Squares in Structured Sparsity Reconstruction ( PDF): Chen Chen* (UT Arlington), Junzhou Huang, Lei He
Photometric Stereo using Constrained Bivariate Regression for General Isotropic Surfaces: Satoshi Ikehata* (University of Tokyo), Kiyoharu Aizawa
Scale-space Processing Using Polynomial Representations ( project): Gou Koutaki* (Kumamoto University), Keiichi Uchimura (Kumamoto University)
Optimizing Over Radial Kernels on Compact Manifolds ( PDF): Sadeep Jayasumana* (Australian National University), Richard Hartley (Australian National University), Mathieu Salzmann (NICTA), Hongdong Li, Mehrtash Harandi
Robust Separation of Reflection from Multiple Images ( PDF): Xiaojie Guo* (IIE, CAS, China), Xiaochun Cao (IIE, CAS, China), Yi Ma (ShanghaiTech University, China)
Face Alignment at 3000 FPS via Regressing Local Binary Features ( PDF): Shaoqing Ren (USTC), Xudong Cao* (Microsoft Research Asia), Yichen Wei (Microsoft Research Asia), Jian Sun (Microsoft Research Asia)
Image-based Synthesis and Re-Synthesis of Viewpoints Guided by 3D Models ( PDF, project, videos): Konstantinos Rematas* (KU Leuven), Tobias Ritschel (MPI for Informatics), Mario Fritz (MPI for Informatics), Tinne Tuytelaars (KU Leuven)
Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks: Maxime Oquab* (Microsoft Research), Ivan Laptev , Leon Bottou (Microsoft Research), Josef Sivic (INRIA)
Smooth Representation Clustering ( PDF, supplementary material): Han Hu* (Tsinghua University), Zhouchen Lin (Peking University), Jianjiang Feng (Tsinghua University), Jie Zhou (Tsinghua University)
Predicting Matchability ( PDF, supplementary material): Wilfried Hartmann* (ETH Zurich), Michal Havlena (ETH Zurich), Konrad Schindler (ETH Zurich)
Robust Orthonormal Subspace Learning: Efficient Recovery of Corrupted Low-rank Matrices: Xianbiao Shu* (University of Illinois), Fatih Porikli (Australian National University), Narendra Ahuja (University of Illinois at Urbana-Champaign)
Cut, Glue & Cut: A Fast, Approximate Solver for Multicut Partitioning ( PDF): Thorsten Beier (HCI , University of Heidelberg), Thorben Kroeger (HCI , University of Heidelberg), Joerg Kappes* (Heidelberg University), Ullrich Koethe (HCI/IWR University of Heidelberg), Fred Hamprecht (HCI/IWR University of Heidelberg)
Local Layering for Joint Motion Estimation and Occlusion Detection: Deqing Sun* , Ce Liu (Microsoft Research New England), Hanspeter Pfister (Harvard University)
What Camera Motion Reveals About Shape with Unknown BRDF: Manmohan Chandraker* (NEC Labs America)
Multi-Output Learning for Camera Relocalization: Abner Guzman-Rivera (University of Illinois), Pushmeet Kohli* , Ben Glocker (Imperial College London), Jamie Shotton (Microsoft Research), Shahram Izadi (Microsoft Research), Andrew Fitzgibbon (Microsoft Research), Toby Sharp (Microsoft)
3D Pictorial Structures: From Single to Multiple Human Pose Estimation: Vasileios Belagiannis* (Technische Universitat Munchen), Sikandar Amin (Technische Universitat Munchen), Mykhaylo Andriluka (Max Planck Institute), Bernt Schiele (Max Planck Institute), Nassir Navab (Technische Universitat Munchen), Slobodan Ilic
Novel methods for multilinear data completion and de-noising based on tensor-SVD: Zemin Zhang* (Tufts University), Gregory Ely , Shuchin Aeron (Tufts University), Ning Hao (Tufts University), Misha Kilmer (Tufts University)
Convolutional Neural Networks for No-Reference Image Quality Assessment: Le Kang* (University of Maryland), Peng Ye (University of Maryland), Yi Li (NICTA), David Doermann (University of Maryland)
Patch to the Future: Unsupervised Visual Prediction: Jacob Walker* (Carnegie Mellon University), Abhinav Gupta , Martial Hebert (Carnegie Mellon University)
Fast and Accurate Image Matching with Cascade Hashing for 3D Reconstruction ( PDF): Jian Cheng* (Chinese Academy of Sciences), Cong Leng (Chinese Academy of Science), Jiaxiang Wu (Chinese Academy of Sciences), Hainan Cui, Hanqing Lu (NLPR , IACAS)
FAUST: Dataset and evaluation for 3D mesh registration: Federica Bogo* (University of Padova), Javier Romero (Max Planck Institute), Matthew Loper (Max Planck Institute), Michael Black (Max Planck)
A Compact and Discriminative Face Track Descriptor ( PDF): Omkar Parkhi* (VGG), Karen Simonyan (VGG , Oxford), Andrea Vedaldi (Oxford University), Andrew Zisserman (Oxford)
Local Submodular Approximations for Binary Pairwise Energies: Lena Gorelick* , Yuri Boykov (University of Western Ontario), Olga Veksler (University of Western Ontario), Ismail BenAyed , Andrew Delong (University of Toronto)
Dirichlet-based Histogram Feature Transform for Image Classification: Takumi Kobayashi* (National Institute of AIST)
MAP Visibility Estimation for Large-Scale Dynamic 3D Reconstruction ( PDF, project) - formely: Optimal Visibility Estimation for Large-Scale Dynamic 3D Reconstruction: Hanbyul Joo* (Carnegie Mellon University), Hyun Soo Park (Carnegie Mellon University), Yaser Sheikh (Carnegie Mellon University)
Maximum Persistency in Energy Minimization ( PDF) - formely: Search Space Reduction in Discrete Optimization: Alexander Shekhovtsov* ( Graz University of Technology)
Iterated Second-Order Label Sensitive Pooling for 3D Human Pose Estimation: Catalin Ionescu* (University of Bonn), Joao Carreira (University of Coimbra), Cristian Sminchisescu (University of Lund)
Video Motion Segmentation Using New Adaptive Manifold Denoising Model: Dijun Luo (University of Texas at Arlington), Heng Huang* (University of Texas at Austin)
A Riemannian framework for matching point clouds represented by the Schr\"{o}dinger distance transform: Yan Deng* (University of Florida), Anand Rangarajan (University of Florida), Baba Vemuri (University of Florida)
Seeing 3D chairs: exemplar part-based 2D-3D alignment using a large dataset of CAD models ( PDF, project): Mathieu Aubry* (INRIA), Daniel Maturana (CMU), Alexei Efros (UC Berkeley), Bryan Russell (Intell), Josef Sivic (INRIA)
Fourier Analysis on Transient Imaging by Multifrequency Time-of-Flight Camera: Jingyu Lin* (Tsinghua University), Yebin Liu (Tsinghua University), Matthias Hullin , Qionghai Dai
DeepFace: Closing the Gap to Human-Level Performance in Face Verification ( PDF, project): Yaniv Taigman (Facebook), Ming Yang (Facebook), Marc\'Aurelio Ranzato (Facebook), Lior Wolf (Tel Aviv University)
Large-scale Video Classification using Convolutional Neural Networks: Andrej Karpathy* (Stanford), Sanketh Shetty (Google), George Toderici (Google), Rahul Sukthankar (Google), Thomas Leung (Google), Li Fei-Fei (Stanford University)
Joint Coupled-Feature Representation and Coupled Boosting for AD Diagnosis: Yinghuan Shi* (Nanjing University), Heung-Il Suk (UNC at Chapel Hill), Yang Gao (Nanjing University), Dinggang Shen (University of North Carolina)
Covariance Trees for 2D and 3D Processing ( PDF, supplementary material, videos): Thierry Guillemot (Telecom ParisTech), Andres Almansa (Telecom ParisTech), Tamy Boubekeur (Telecom ParisTech)
Latent Regression Forest: Structural Estimation of 3D Articulated Hand Posture: Danhang Tang* (Imperial College London), alykhan Tejani , Hyung Jin Chang (Imperial College London), Tae-Kyun Kim (Imperial College London)
A Mixture of Manhattan Frames: Beyond the Manhattan World: Julian Straub* (MIT CSAIL), Guy Rosman (MIT), Oren Freifeld (MIT), John Leonard (MIT CSAIL), John Fisher III (MIT)
Multi-View Super Vector for Action Recognition: Zhuowei Cai* (Chinese Academy of Sciences), Yu Qiao (SIAT)
Recognition of Complex Events exploiting Temporal Dynamics between Underlying Concepts: Subhabrata Bhattacharya* (Columbia University)
Socially-aware Large-scale Crowd Forecasting: Alexandre Alahi* (Stanford University), Vignesh Ramanathan (Stanford), Li Fei-Fei (Stanford University)
Deformable Registration of Feature-Endowed Point Sets Based on Tensor Fields: Demian Wassermann* (Harvard Medical School), James Ross , George Washko , Sandy Wells , Raul San Jose-Estepar

Accepted Orals

Reconstructing Storyline Graphs for Image Recommendation from Web Community Photos ( project, PDF): Gunhee Kim* (Disney Research), Eric Xing (Carnegie Mellon University)
Unsupervised One-Class Learning for Automatic Outlier Removal: Wei Liu* (IBM Thomas J. Watson Research), Gang Hua (Stevens Institute of Technology), John Smith (IBM T. J. Watson Research Center)
Critical Configurations For Radial Distortion Self-Calibration ( PDF): Changchang Wu* (Google)
Active Flattening of Curved Document Images via Two Structured Beams ( PDF): Gaofeng MENG ( NLPR, CASIA), Ying WANG, Shenquan QU, Shiming XIANG, Chunhong PAN
Segmentation-Free Dynamic Scene Deblurring: Tae Hyun Kim (Seoul National University), Kyoung Mu Lee* (Seoul National University)
Diffuse Mirrors: 3D Reconstruction from Diffuse Indirect Illumination Using Inexpensive Time-of-Flight Sensors: Felix Heide* (University of British Columbia), Lei Xiao (University of British Columbia), Wolfgang Heidrich (University of British Columbia), Matthias B. Hullin (University of Bonn)
A Primal-Dual Method for Higher-Order Multilabel Markov Random Fields ( PDF): Alexander Fix (Cornell), Chen Wang ([email protected]), Ramin Zabih*
Single Image Layer Separation using Relative Smoothness: YU LI* (NUS), Michael Brown (NUS)
L0 Regularized Stationary Time Estimation for Crowd Group Analysis ( PDF): SHUAI YI* (The Chinese University of HK), Xiaogang Wang (Chinese University of Hong Kong), Cewu Lu (The Hong Kong University of Sc), Jiaya Jia (CUHK)
Shape-Preserving Half-Projective Warps for Image Stitching: Che-Han Chang* (National Taiwan University), Yoichi Sato (Univ of Tokyo), Yung-Yu Chuang (NTU)
Parsing videos of actions with segmental grammars: Hamed Pirsiavash* (MIT), Deva Ramanan
Multiscale Centerline Detection by Learning a Scale-Space Distance Transform ( PDF,supplementary material): Amos Sironi* (EPFL), Vincent Lepetit (EPFL), Pascal Fua (EPFL)
Context Driven Scene Parsing with Attention to Rare Classes ( PDF): Jimei Yang* (UC Merced), Brian Price, Scott Cohen (Adobe Inc.), Ming-Hsuan Yang (UC Merced)
Multi-Object Tracking via Constrained Sequential Labeling ( PDF): Sheng Chen* (Oregon State University), Alan Fern (Oregon State University), Sinisa Todorovic (Oregon State University)
Unsupervised Spectral Dual Assignment Clustering of Human Actions in Context ( PDF, code): Simon Jones (The University of Sheffield), Ling Shao* (The University of Sheffield)
Bayesian View Synthesis and Image-Based Rendering Principles ( PDF, abstract): Sergi Pujades (INRIA), Frederic Devernay (INRIA), Bastian Goldluecke (HCI)
BING: Binarized Normed Gradients for Objectness Estimation at 300fps ( project,PDF,code,slides): Ming-Ming Cheng ( University of Oxford), Ziming Zhang (Boston University), Wen-Yan Lin (Oxford Brookes University), Philip Torr ( University of Oxford)
Multivariate General Linear Models (MGLM) on Riemannian Manifolds with Applications to Statistical Analysis of Diffusion Weighted Images: Hyunwoo Kim* (University of Wisconsin-Madison), Nagesh Adluru (University of Wisconsin-Madiso), Maxwell Collins (University of Wisconsin-Madison), Moo Chung (University of Wisconsin-Madison), barbara Bendlin (University of Wisconsin-Madison), Sterling Johnson (University of Wisconsin-Madison), Richard Davidson (University of Wisconsin-Madison), Vikas Singh (University of Wisconsin-Madison)
Spectral Graph Reduction for Efficient Image and Streaming Video Segmentation ( PDF): Fabio Galasso* (Max Planck Institute), Margret Keuper (University of Freiburg), Thomas Brox (University of Freiburg), Bernt Schiele (Max Planck Institute)
Learning Scalable Discriminative Attributes with Sample Relatedness: Jiashi Feng* (NUS), Stefanie Jegelka , Trevor Darrell (University of California Berkeley), Huan Xu , Shuicheng Yan (National University of Singapore)
Object Non-detection: Hiding an Object from Many Viewpoints: Andrew Owens* (MIT), Connelly Barnes (University of Virginia), Alex Flint (Ogemento), hanumant Singh (Woods Hole Oceanographic Institution), Bill Freeman (MIT)
DeepPose: Human Pose Estimation via Deep Neural Networks ( PDF): Alexander Toshev* (Google), Christian Szegedy
Neural Decision Forests for Semantic Image Labelling ( PDF, supplementary material): Samuel Rota Bulo` (FBK-irst), Peter Kontschieder (Microsoft Research)
Learning Everything about Anything: Webly-Supervised Visual Concept Learning: Santosh Kumar Divvala* (University of Washington), Ali Farhadi (University of Washington), Carlos Guestrin (University of Washington)
Scene Labeling Using Beam Search Under Mutex Constraints ( PDF) - formely: Heuristic-Score Beam Search for Scene Labeling: Anirban Roy* (Oregon State University), Sinisa Todorovic (Oregon State University)
Parallax-tolerant Image Stitching: Fan Zhang (Portland State University), Feng Liu* (Portland State University)
Second-order Shape Optimization for Geometric Inverse Problems in Vision ( PDF): Jonathan Balzer* (UCLA), Stefano Soatto (University of California at Los Angeles)
Hierarchical Subquery Evaluation for Active Learning on a Graph ( project): Oisin Mac Aodha* (UCL), Neill D.F. Campbell (UCL), Jan Kautz (UCL), Gabriel J. Brostow (UCL)
PANDA: Pose Aligned Networks for Deep Attribute Modeling ( PDF): Ning Zhang (UC Berkeley), Manohar Paluri (Facebook), Marc'Aurelio Ranzato, Trevor Darrell (UC Berkeley), Lubomir Bourdev (Facebook)
Realtime and Robust Hand Tracking from Depth: Chen Qian (CUHK), Xiao Sun (Microsoft Research Asia), Yichen Wei* (Microsoft Research Asia), Xiaoou Tang (Chinese University of Hong Kong), Jian Sun
Energy based multi-model fitting & matching for 3D reconstruction: Hossam Isack* (Western Ontario), Yuri Boykov (University of Western Ontario)
Robust Subspace Segmentation with Block-diagonal Prior ( PDF, supplementary material): Jiashi Feng* (NUS), Zhouchen Lin (Peking University), Huan Xu, Shuicheng Yan (National University of Singapore)
Grassmann Averages for Scalable Robust PCA: Soren Hauberg* (Max Planck Institute), Aasa Feragen (University of Copenhagen), Michael Black (Max Planck)
Multiview Shape and Reflectance from Natural Illumination: Geoffrey Oxholm* (Drexel University), Ko Nishino
Adaptive Partial Differential Equation Learning for Visual Saliency Detection ( PDF, supplementary material): Risheng Liu* (Dalian University of Technolog), Zhouchen Lin (Peking University), Shiguang Shan (Chinese Academy of Sciences)
Local Regularity-driven City-scale Facade Detection from Aerial Images: Yanxi Liu* (Penn State University), Jingchen Liu (PSU)
L0 norm based dictionary learning method with global convergence: Chenglong Bao (nus.edu.sg), Hui Ji* (Natl Univ Singapore), Yuhui Quan (nus.edu.sg), Zuowei Shen (nus.edu.sg)
Optimal Decisions from Probabilistic Models: the Intersection-over-Union Case ( PDF, supplementary material, code): Sebastian Nowozin* ( Microsoft Research)
Rich feature hierarchies for accurate object detection and semantic segmentation ( code, PDF, supplementary material, technical report): Ross Girshick (UC Berkeley), Jeff Donahue (UC Berkeley and ICSI), Trevor Darrell (UC Berkeley and ICSI), Jitendra Malik (UC Berkeley)
Surface-from-Gradients: An Approach Based on Discrete Geometry Processing: Wuyuan Xie (Chinese Univ. of Hong Kong), Yunbo Zhang (University at Buffalo), Charlie C L Wang* (Chinese Univ. of Hong Kong)
Nearest Neighbor-based Label Transfer for Weakly Supervised Multiclass Video Segmentation ( PDF): Xiao Liu* (Zhejiang University), Dacheng Tao, Mingli Song (zju), Ying Ruan (zju), Chun Chen (zju), Jiajun Bu (zju)
Minimal Solvers for Relative Pose with a Single Unknown Radial Distortion: Yubin Kuang* (Centre for Mathematical Scienc), Jan Erik Solem (Centre for Mathematical Sciences, Lund University), Kalle Astroem (Lund University), Fredrik Kahl (Lund University)
Partial Optimality by Pruning for MAP-inference with General Graphical Models ( PDF): Paul Swoboda* (Heidelberg University), Bogdan Savchynskyy (Heidelberg University), Joerg Kappes (Heidelberg University), Christoph SchnÃ£rr
Learning to disambiguate indistinguishable objects over time: weakly supervised structured learning: Luca Fiaschi* (HCI/IWR University of Heidelberg), Ferran Diego (HCI/IWR University of Heidelberg), Konstantin Gregor (HCI/IWR University of Heidelberg), Ullrich Koethe (HCI/IWR University of Heidelberg), Marta Zlatic (HHMI Janelia Farm), Fred Hamprecht (HCI/IWR University of Heidelberg)
Filter Forests for Learning Data-Dependent Convolutional Kernels: Sean Ryan Fanello* (IIT), Cem Keskin (Microsoft Research), Pushmeet Kohli , Shahram Izadi (Microsoft Research), Jamie Shotton (Microsoft Research), Antonio Criminisi (Microsoft Research), Ugo Pattacini (IIT), Tim Paek (Microsoft)
Rate-Invariant Analysis of Trajectories on Riemannian Manifolds with Application in Visual Speech Recognition: Jingyong Su* (Texas Tech University), Anuj Srivastava , Fillipe Souza (University of South Florida), Sudeep Sarkar (University of South Florida)
Video Event Detection by Inferring Temporal Instance Labels ( PDF, project): Kuan-Ting Lai* (National Taiwan University), Felix Yu (Columbia University), Ming-Syan Chen, Shih-Fu Chang
Decorrelating Semantic Visual Attributes by Resisting the Urge to Share ( PDF): Dinesh Jayaraman* (UT Austin), Fei Sha (University of Southern California), Kristen Grauman (University of Texas at Austin)
Triangulation embedding and democratic aggregation for image search ( PDF): Herve Jegou* (INRIA), Andrew Zisserman (Oxford)
Image Fusion with Local Spectral Consistency and Dynamic Gradient Sparsity ( PDF): Chen Chen* (UT Arlington), Junzhou Huang, Wei Liu (IBM Thomas J. Watson Research)
Transparent Object Reconstruction via Coded Transport of Intensity: Chenguang Ma (Tsinghua University), Xing Lin (Tsinghua University), Jinli Suo (Tsinghua University), Qionghai Dai (Tsinghua University), Gordon Wetzstein* (MIT)
Scene-Independent Group Profiling in Crowd: Jing Shao* (The Chinese University of HK), Chen Change Loy, Xiaogang Wang (Chinese University of Hong Kong)
Learning Euclidean-to-Riemannian Metric for Point-to-Set Classification: Zhiwu Huang* (Chinese Academy of Sciences), Ruiping Wang (Institute of Computing Technology , Chinese Academy of Sciences), Shiguang Shan (Chinese Academy of Sciences), Xilin Chen
Pulling Things out of Perspective: Lubor Ladicky* , Jianbo Shi , Marc Pollefeys (ETH)
Adaptive Color Attributes for Real-Time Visual Tracking ( PDF, project): Martin Danelljan* (CVL, Linkoping University), Fahad Shahbaz Khan (CVL, Linkoping University), Michael Felsberg (CVL, Linkoping University), Joost van de Weijer (Computer Vision Center Barcelona)
Reconstructing PASCAL VOC ( project,videos,code,PDF,supplementary material): Sara Vicente (University College London), Joao Carreira* (ISR-Coimbra), Lourdes Agapito (University College London), Jorge Batista (ISR - University of Coimbra)
Trinocular Geometry Revisited: Jean Ponce* (Ecole Normale Superieure), Martial Hebert (Carnegie Mellon University)
3D Shape and Indirect Appearance by Structured Light Transport ( project, PDF, supplementary material): Matthew O\'Toole* (University of Toronto), John Mather (University of Toronto), Kiriakos N. Kutulakos (University of Toronto)
Shrinkage Fields for Effective Image Restoration ( PDF, supplementary material): Uwe Schmidt (TU Darmstadt), Stefan Roth (TU Darmstadt)
Temporal Sequence Modeling For Video Event Detection ( PDF): Yu Cheng* (IBM Research, Northwestern University), Quanfu Fan (IBM Research), Sharath Pankanti (IBM Research), Alok Choudhary (Northwestern University)
Reflectance and Fluorescent Spectra Recovery based on Fluorescent Chromaticity Invariance under Varying Illumination: Ying Fu* (The University of Tokyo), Antony Lam (National Institute of Informatics), Yasuyuki Kobashi (Ministry of Internal Affairs and Communications), Imari Sato (National Institute of Informatics), Takahiro Okabe (Kyushu Institute of Technology), Yoichi Sato (Univ of Tokyo)
Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group: Raviteja Vemulapalli* (University of Maryland), Felipe Arrate (University of Maryland , College Park), Rama Chellappa (University of Maryland)
Anytime Recognition of Objects and Scenes ( PDF, project): Sergey Karayev (UC Berkeley), Mario Fritz (MPI for Informatics), Trevor Darrell (UC Berkeley)
Preconditioning for Accelerated Iteratively Reweighted Least Squares in Structured Sparsity Reconstruction ( PDF): Chen Chen* (UT Arlington), Junzhou Huang, Lei He
Photometric Stereo using Constrained Bivariate Regression for General Isotropic Surfaces: Satoshi Ikehata* (University of Tokyo), Kiyoharu Aizawa
Scale-space Processing Using Polynomial Representations ( project): Gou Koutaki* (Kumamoto University), Keiichi Uchimura (Kumamoto University)
Optimizing Over Radial Kernels on Compact Manifolds ( PDF): Sadeep Jayasumana* (Australian National University), Richard Hartley (Australian National University), Mathieu Salzmann (NICTA), Hongdong Li, Mehrtash Harandi
Robust Separation of Reflection from Multiple Images ( PDF): Xiaojie Guo* (IIE, CAS, China), Xiaochun Cao (IIE, CAS, China), Yi Ma (ShanghaiTech University, China)
Face Alignment at 3000 FPS via Regressing Local Binary Features ( PDF): Shaoqing Ren (USTC), Xudong Cao* (Microsoft Research Asia), Yichen Wei (Microsoft Research Asia), Jian Sun (Microsoft Research Asia)
Image-based Synthesis and Re-Synthesis of Viewpoints Guided by 3D Models ( PDF, project, videos): Konstantinos Rematas* (KU Leuven), Tobias Ritschel (MPI for Informatics), Mario Fritz (MPI for Informatics), Tinne Tuytelaars (KU Leuven)
Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks: Maxime Oquab* (Microsoft Research), Ivan Laptev , Leon Bottou (Microsoft Research), Josef Sivic (INRIA)
Smooth Representation Clustering ( PDF, supplementary material): Han Hu* (Tsinghua University), Zhouchen Lin (Peking University), Jianjiang Feng (Tsinghua University), Jie Zhou (Tsinghua University)
Predicting Matchability ( PDF, supplementary material): Wilfried Hartmann* (ETH Zurich), Michal Havlena (ETH Zurich), Konrad Schindler (ETH Zurich)
Robust Orthonormal Subspace Learning: Efficient Recovery of Corrupted Low-rank Matrices: Xianbiao Shu* (University of Illinois), Fatih Porikli (Australian National University), Narendra Ahuja (University of Illinois at Urbana-Champaign)
Cut, Glue & Cut: A Fast, Approximate Solver for Multicut Partitioning ( PDF): Thorsten Beier (HCI , University of Heidelberg), Thorben Kroeger (HCI , University of Heidelberg), Joerg Kappes* (Heidelberg University), Ullrich Koethe (HCI/IWR University of Heidelberg), Fred Hamprecht (HCI/IWR University of Heidelberg)
Local Layering for Joint Motion Estimation and Occlusion Detection: Deqing Sun* , Ce Liu (Microsoft Research New England), Hanspeter Pfister (Harvard University)
What Camera Motion Reveals About Shape with Unknown BRDF: Manmohan Chandraker* (NEC Labs America)
Multi-Output Learning for Camera Relocalization: Abner Guzman-Rivera (University of Illinois), Pushmeet Kohli* , Ben Glocker (Imperial College London), Jamie Shotton (Microsoft Research), Shahram Izadi (Microsoft Research), Andrew Fitzgibbon (Microsoft Research), Toby Sharp (Microsoft)
3D Pictorial Structures: From Single to Multiple Human Pose Estimation: Vasileios Belagiannis* (Technische Universitat Munchen), Sikandar Amin (Technische Universitat Munchen), Mykhaylo Andriluka (Max Planck Institute), Bernt Schiele (Max Planck Institute), Nassir Navab (Technische Universitat Munchen), Slobodan Ilic
Novel methods for multilinear data completion and de-noising based on tensor-SVD: Zemin Zhang* (Tufts University), Gregory Ely , Shuchin Aeron (Tufts University), Ning Hao (Tufts University), Misha Kilmer (Tufts University)
Convolutional Neural Networks for No-Reference Image Quality Assessment: Le Kang* (University of Maryland), Peng Ye (University of Maryland), Yi Li (NICTA), David Doermann (University of Maryland)
Patch to the Future: Unsupervised Visual Prediction: Jacob Walker* (Carnegie Mellon University), Abhinav Gupta , Martial Hebert (Carnegie Mellon University)
Fast and Accurate Image Matching with Cascade Hashing for 3D Reconstruction ( PDF): Jian Cheng* (Chinese Academy of Sciences), Cong Leng (Chinese Academy of Science), Jiaxiang Wu (Chinese Academy of Sciences), Hainan Cui, Hanqing Lu (NLPR , IACAS)
FAUST: Dataset and evaluation for 3D mesh registration: Federica Bogo* (University of Padova), Javier Romero (Max Planck Institute), Matthew Loper (Max Planck Institute), Michael Black (Max Planck)
A Compact and Discriminative Face Track Descriptor ( PDF): Omkar Parkhi* (VGG), Karen Simonyan (VGG , Oxford), Andrea Vedaldi (Oxford University), Andrew Zisserman (Oxford)
Local Submodular Approximations for Binary Pairwise Energies: Lena Gorelick* , Yuri Boykov (University of Western Ontario), Olga Veksler (University of Western Ontario), Ismail BenAyed , Andrew Delong (University of Toronto)
Dirichlet-based Histogram Feature Transform for Image Classification: Takumi Kobayashi* (National Institute of AIST)
MAP Visibility Estimation for Large-Scale Dynamic 3D Reconstruction ( PDF, project) - formely: Optimal Visibility Estimation for Large-Scale Dynamic 3D Reconstruction: Hanbyul Joo* (Carnegie Mellon University), Hyun Soo Park (Carnegie Mellon University), Yaser Sheikh (Carnegie Mellon University)
Maximum Persistency in Energy Minimization ( PDF) - formely: Search Space Reduction in Discrete Optimization: Alexander Shekhovtsov* ( Graz University of Technology)
Iterated Second-Order Label Sensitive Pooling for 3D Human Pose Estimation: Catalin Ionescu* (University of Bonn), Joao Carreira (University of Coimbra), Cristian Sminchisescu (University of Lund)
Video Motion Segmentation Using New Adaptive Manifold Denoising Model: Dijun Luo (University of Texas at Arlington), Heng Huang* (University of Texas at Austin)
A Riemannian framework for matching point clouds represented by the Schr\"{o}dinger distance transform: Yan Deng* (University of Florida), Anand Rangarajan (University of Florida), Baba Vemuri (University of Florida)
Seeing 3D chairs: exemplar part-based 2D-3D alignment using a large dataset of CAD models ( PDF, project): Mathieu Aubry* (INRIA), Daniel Maturana (CMU), Alexei Efros (UC Berkeley), Bryan Russell (Intell), Josef Sivic (INRIA)
Fourier Analysis on Transient Imaging by Multifrequency Time-of-Flight Camera: Jingyu Lin* (Tsinghua University), Yebin Liu (Tsinghua University), Matthias Hullin , Qionghai Dai
DeepFace: Closing the Gap to Human-Level Performance in Face Verification ( PDF, project): Yaniv Taigman (Facebook), Ming Yang (Facebook), Marc\'Aurelio Ranzato (Facebook), Lior Wolf (Tel Aviv University)
Large-scale Video Classification using Convolutional Neural Networks: Andrej Karpathy* (Stanford), Sanketh Shetty (Google), George Toderici (Google), Rahul Sukthankar (Google), Thomas Leung (Google), Li Fei-Fei (Stanford University)
Joint Coupled-Feature Representation and Coupled Boosting for AD Diagnosis: Yinghuan Shi* (Nanjing University), Heung-Il Suk (UNC at Chapel Hill), Yang Gao (Nanjing University), Dinggang Shen (University of North Carolina)
Covariance Trees for 2D and 3D Processing ( PDF, supplementary material, videos): Thierry Guillemot (Telecom ParisTech), Andres Almansa (Telecom ParisTech), Tamy Boubekeur (Telecom ParisTech)
Latent Regression Forest: Structural Estimation of 3D Articulated Hand Posture: Danhang Tang* (Imperial College London), alykhan Tejani , Hyung Jin Chang (Imperial College London), Tae-Kyun Kim (Imperial College London)
A Mixture of Manhattan Frames: Beyond the Manhattan World: Julian Straub* (MIT CSAIL), Guy Rosman (MIT), Oren Freifeld (MIT), John Leonard (MIT CSAIL), John Fisher III (MIT)
Multi-View Super Vector for Action Recognition: Zhuowei Cai* (Chinese Academy of Sciences), Yu Qiao (SIAT)
Recognition of Complex Events exploiting Temporal Dynamics between Underlying Concepts: Subhabrata Bhattacharya* (Columbia University)
Socially-aware Large-scale Crowd Forecasting: Alexandre Alahi* (Stanford University), Vignesh Ramanathan (Stanford), Li Fei-Fei (Stanford University)
Deformable Registration of Feature-Endowed Point Sets Based on Tensor Fields: Demian Wassermann* (Harvard Medical School), James Ross , George Washko , Sandy Wells , Raul San Jose-Estepar

Accepted Posters

Total Variation Blind Deconvolution: The Devil is in the Details ( project, PDF, code): Daniele Perrone* (University of Bern), Paolo Favaro (University of Bern)
Joint Summarization of Large-scale Collections of Web Images and Videos for Storyline Reconstruction ( project, PDF) - formely: Jointly Summarizing Large-Scale Web Images and Videos for the Storyline Reconstruction: Gunhee Kim* (Disney Research), Leonid Sigal (Disney Research), Eric Xing (Carnegie Mellon University)
Stable and Informative Spectral Signatures for Graph Matching: Nan Hu* (Stanford University), Raif Rustamov , Leonidas J. Guibas
Fantope Regularization in Metric Learning ( PDF): Marc Law* (LIP6 , UPMC), Nicolas Thome (LIP6 - UPMC Sorbonne University), Matthieu Cord (LIP6 - UPMC Sorbonne University)
One Millisecond Face Alignment with an Ensemble of Regression Trees ( PDF): Vahid Kazemi* ( KTH), Josephine Sullivan (KTH)
From Categories to Individuals in Real Time --- A Unified Boosting Approach: David Hall* (CalTech), Pietro Perona (California Institute of Technology)
Visual Persuasion: Inferring the Communicative Intents of Images ( project, PDF): Jungseock Joo* (UCLA), Weixin Li (UCLA), Francis Steen (UCLA), Song Chun Zhu (UCLA)
BirdMachine: Large-scale Fine-grained Visual Categorization of Birds: Thomas Berg* (Columbia University), Jiongxin Liu (Columbia University), Seung Woo Lee (Columbia University), Michelle Alexander (Columbia University), David Jacobs (UMD), Peter Belhumeur (Columbia University)
DISCOVER: Discovering Important Segments for Classification of Video Events and Recounting ( PDF): Chen Sun ( University of Southern California), Ram Nevatia (University of Southern California)
Transfer Joint Matching for Visual Domain Adaptation: Mingsheng Long* (Tsinghua University), Jianmin Wang (Tsinghua University), Guiguang Ding (Tsinghua University), Philip Yu (University of Illinois at Chicago)
Occluding Contours for Multi-View Stereo: Qi Shan* , Brian Curless , Yasutaka Furukawa (Washington University), Carlos Hernandez (Google), Steve Seitz (Washington/Google)
Raw-to-raw: Mapping between image sensor color responses: Rang Nguyen* (NUS , Singapore), Dilip Prasad (NUS), Michael Brown (NUS)
Sparse Representation for Edit Propagation of High-Resolution Images: Xiaowu Chen (Beihang University), Jianwei Li (Beihang University), Dongqing Zou* (Beihang University), Xiaochun Cao (Institute of information engineering , Chinese Academy of Sciences), Qinping Zhao (Beihang University), Hao (Richard) Zhang (Simon Fraser University)
The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities: Hilde Kuehne* (Fraunhofer FKIE), Ali Arslan (Brown University), Thomas Serre (Brown University)
Newton Greedy Pursuit: a Quadratic Approximation Method for Sparsity-Constrained Optimization: Xiao-Tong Yuan* (Rutgers University), Qingshan Liu (Nanjing University of Information Science and Technology)
Collaborative Hashing: Xianglong Liu* (Beihang University), Junfeng He (Facebook), Cheng Deng , Bo Lang
Timing-Based Local Descriptor for Dynamic Surfaces: Tony Tung* (Kyoto University), Takashi Matsuyama (Kyoto University)
Learning to Detect Ground Control Points for Improving the Accuracy of Stereo Matching: Aristotle Spyropoulos (Stevens Institute of Technology), Nikos Komodakis , Philippos Mordohai*
The Fastest Deformable Part Model for Object Detection ( PDF): Junjie Yan* (NLPR), Zhen Lei (ia.ac.cn), Longyin Wen ( ia.ac.cn), Stan Li (ia.ac.cn)
Packing and Padding: Coupled Multi-index for Accurate Image Retrieval ( PDF, code): Liang Zheng (Tsinghua University), Shengjin Wang* (Tsinghua University), Ziqiong Liu (Tsinghua University), Qi Tian (University of Texas at San Antonio)
From Stochastic Grammar to Bayes Network: Probabilistic Parsing of Complex Activity ( PDF,project,videos): Nam N. Vo* (Georgia Institute of Technolog), Aaron F. Bobick (Georgia Institute of Technology)
Simultaneous Localization and Calibration: Qian-Yi Zhou* (Stanford University), Vladlen Koltun (Adobe Research)
Global Optimization for Depth Reconstruction from Speckle Patterns: Qifeng Chen* (Stanford University), Vladlen Koltun (Adobe Research)
Kernel-PCA Analysis of Surface Normals: Patrick Snape* (Imperial College London), Stefanos Zafeiriou (Imperial College London)
The Shape-Time Random Field for Semantic Video Labeling: Andrew Kae* (UMass Amherst), Erik Learned-Miller (University of Massachusetts), Benjamin Marlin (UMass Amherst)
Bayes Merging of Multiple Vocabularies for Scalable Image Retrieval ( PDF, supplementary material, code): Liang Zheng (Tsinghua University), Shengjin Wang* (Tsinghua University), Wengang Zhou (University of Science and Technology of China), Qi Tian (University of Texas at San Antonio)
Joint Depth Estimation and Camera Shake Removal from Single Blurry Image ( PDF): Zhe Hu* (UC , Merced), Li Xu (Chinese University of Hong Kong), Ming-Hsuan Yang (UC Merced)
Attributed Graph Mining and Matching: An Attempt to Define and Extract Soft Attributed Patterns ( project, PDF) - formely: Unsupervised Learning for Graph Matching: An Attempt to Define and Extract Soft Attributed Patterns: Quanshi Zhang* (University of Tokyo), Xuan Song (University of Tokyo), Xiaowei Shao (University of Tokyo), Huijing Zhao, Ryosuke Shibasaki (University of Tokyo)
When 3D Reconstruction Meets Ubiquitous RGB-D Images ( PDF): Quanshi Zhang* (University of Tokyo), Xuan Song (University of Tokyo), Xiaowei Shao (University of Tokyo), Huijing Zhao, Ryosuke Shibasaki (University of Tokyo)
Scalable 3D Tracking of Multiple Interacting Objects ( videos, project): Nikolaos Kyriazis* (CSD, Univ. of Crete and Institute of Comp. Science, FORTH), Antonis Argyros (CSD, Univ. of Crete and Institute of Comp. Science, FORTH)
The Role of Context for Object Detection and Semantic Segmentation in the Wild: Roozbeh Mottaghi* (Stanford University), Xianjie Chen (UCLA), Xiaobai Liu (UCLA), Sanja Fidler (Toyota Technnological Institute), Raquel Urtasun (University of Toronto), Alan Yuille (University of California at Los Angeles)
Simplex-Based 3D Spatio-Temporal Feature Description for Action Recognition: Hao Zhang* (University of Tennessee), Wenjun Zhou (University of Tennessee), Christopher Reardon (University of Tennessee), Lynne Parker
Predicting Object Dynamics in Scenes ( PDF, supplementary material): David Fouhey* (Carnegie Mellon University), Larry Zitnick (Microsoft Research)
Interval Tracker: Tracking by Interval Analysis: Junseok Kwon (ETHZ), Kyoung Mu Lee* (Seoul National University)
Scanline Sampler without Detailed Balance: An Efficient MCMC for MRF Optimization: Wonsik Kim (Seoul National University), Kyoung Mu Lee* (Seoul National University)
Depth Enhancement via Low-rank Matrix Completion: Si Lu (Portland State University), Xiaofeng Ren (Amazon), Feng Liu* (Portland State University)
Describing Textures in the Wild ( PDF): Mircea Cimpoi (University of Oxford), Subhransu Maji* (Toyota Technnological Institute), Iasonas Kokkinos (Ecole Central de Paris), Andrea Vedaldi (Oxford University)
Parsing World\'s Skylines using Shape-Constrained MRFs ( PDF): Rashmi Tonge (IIIT Hyderabad), Subhransu Maji* (Toyota Technnological Institute), C.V. Jawahar (IIIT Hyderabad)
StoryGraphs: Narrative Charts for TV series: Makarand Tapaswi* (KIT), Martin BÃƒÂ¤uml (KIT), Rainer Stiefelhagen (Karlsruhe Institute of Technology)
Inferring Unseen Views of People ( PDF): Chao-Yeh Chen* (The Univ. of Texas at Austin), Kristen Grauman (University of Texas at Austin)
Orientational Pyramid Matching for Recognizing Indoor Scenes ( PDF): Lingxi Xie (Tsinghua University), Jingdong Wang (Microsoft Research), Baining Guo (Microsoft Research), Bo Zhang (Tsinghua University), Qi Tian (University of Texas at San Antonio)
Joint Unsupervised Multi-Class Image Segmentation: Fan Wang* (Stanford University), Qixing Huang (Stanford University), Maks Ovsjanikov (Ecole Polytechnique), Leonidas J. Guibas
Looking Beyond the Visible Scene: Joseph Lim* (MIT), Aditya Khosla , Antonio Torralba (MIT), Byoungkwon An An (CSAIL MIT)
Towards Multi-view and Partially-occluded Face Alignment: Junliang Xing* (NLPR , CASIA), Zhiheng Niu (National University of Singapo), Junshi Huang (National University of Singapore), Weiming Hu (NLPR , CASIA), Shuicheng Yan (National University of Singapore)
Learning Mid-level Filters for Person Re-identification: Rui Zhao* (The Chinese University of Hong Kong), Wanli Ouyang (The Chinese University of Hong Kong), Xiaogang Wang (The Chinese University of Hong Kong)
Automatic Face Reenactment: Pablo Garrido (MPI for Informatics), Levi Valgaerts* (Max Planck Institute), Ole Rehmsen , Thorsten Thormaehlen , Patrick Perez (technicolor), Christian Theobalt (MPI Informatik)
Illumination-Aware Age Progression ( project, PDF, videos, dataset): Ira Kemelmacher* (University of Washington), Supasorn Suwajanakorn (University of Washington), Steve Seitz (Washington/Google)
Hash-SVM: Scalable Kernel Machines for Large-Scale Visual Classification ( PDF): Yadong MU* (AT&T Labs - Research), Gang Hua (Stevens Institute of Technology), Wei Fan (Noah\'s Ark Lab, Huawei ), Shi-Fu Chang (Columbia University)
Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts: Xianjie Chen* (UCLA), Roozbeh Mottaghi (Stanford University), Xiaobai Liu (UCLA), Nam-Gyu Cho (Korea University), Sanja Fidler (Toyota Technnological Institute), Raquel Urtasun (University of Toronto), Alan Yuille (University of California at Los Angeles)
Quality-based Multimodal Classification Using Tree-Structured Sparsity: Soheil Bahrampour (Penn State University), Asok Ray* (Pennsylvania State University), nasser Nasrabadi , Kenneth Jenkins (Pennsylvania State University)
Diversity-Enhanced Condensation Algorithm and Its Application for Robust and Accurate Endoscope Electromagnetic Tracking: Ying Wan , Xiongbiao Luo* (Nagoya University), Sean He (University of Technology Sydney), Jie Yang , Terry Peters (Robarts Research Institute , Western University), kensaku Mori (Nagoya Unviversity)
Cross-Scale Cost Aggregation for Stereo Matching ( PDF, code): Kang Zhang* (Tsinghua University), Yuqiang Fang (National University of Defense Technology), Dongbo Min, Lifeng Sun (Tsinghua University), Shiqiang Yang (Tsinghua University), Shuicheng Yan ( National University of Singapore), Qi Tian
Learning an image-based motion context for multiple people tracking ( PDF): Laura Leal-Taixe (ETH Zurich), Michele Fenzi (Leibniz University Hannover), Alina Kuznetsova (Leibniz University Hannover), Bodo Rosenhahn (Leibniz University Hannover), Silvio Savarese (Stanford University)
Evaluation of Scan-Line Optimization for 3D Medical Image Registration: Simon Hermann* (Humboldt University of Berlin)
Deeply-Learned Slow Feature Analysis for Action Recognition: Lin SUN (NUS, HKUST, Lenovo,), Kui Jia (ADSC), Tsung-Han Chan (ADSC), Yuqiang Fang (NUS), Shuicheng Yan (NUS)
Subspace Clustering for Sequential Data: Stephen Tierney* (Charles Sturt University), Junbin Gao (Charles Sturt University), Yi Guo (CSIRO)
How to Evaluate Foreground Maps? ( PDF): Ran Margolin* (Technion), Lihi Zelnik-Manor (Israel Institute of Technology), Ayellet Tal (Technion)
An Automated Estimator of Image Visual Realism Based on Human Cognition ( PDF, project): Shaojing Fan* (Ningbo University, Institute for Infocomm Research), Tian-Tsong Ng (A*STAR, Singapore), Jonathan S. Herberg (Institute of High Performance Computing), Bryan L. Koenig (Lindenwood University), Cheston Y. -C. Tan (Institute for Infocomm Research), Rangding Wang (Ningbo University)
Robust Online Multi-Object Tracking based on Tracklet Confidence and Online Discriminative Appearance Learning ( PDF, supplementary material, videos): Seung-Hwan Bae* (GIST), Kuk-Jin Yoon (GIST)
Discrete-Continuous Gradient Orientation Estimation for Faster Image Segmentation ( PDF, project, code) - formely: Discrete-Continuous Gradient Orientation Estimation for Faster Unsupervised Segmentation: Michael Donoser* (Graz University of Technology), Dieter Schmalstieg (Graz University of Technology)
Good Vibrations: A Modal Analysis Approach for Sequential Non-Rigid Structure from Motion: Antonio Agudo* (Universidad de Zaragoza), Lourdes Agapito (University College London), BegoÃƒÂ±a Calvo (Universidad de Zaragoza), Jose M. Montiel (Universidad de Zaragoza)
Incremental Learning of NCM Forests for Large-Scale Image Classification ( PDF): Marko Ristin* (ETH Zurich), Matthieu Guillaumin (ETH Zurich), Juergen Gall (University of Bonn), Luc Van Gool (ETH Zurich)
Asymmetrical Gauss Mixture Models for Point Sets Matching: Wenbing Tao* (Huazhong Univ. of Sci. &), Tech., Kun Sun (Huazhong Univ. of Sci. &), Tech.
A Compositional Model for Low-Dimensional Image Set Representation ( PDF): Hossein Mobahi* (MIT), Ce Liu (Microsoft Research New England), Bill Freeman (MIT)
Associative embeddings for large-scale knowledge transfer with self-assessment: Alexander Vezhnevets* (University of Edinburgh), Vittorio Ferrari (University of Edinburgh)
Max-Margin Boltzmann Machines for Object Segmentation ( PDF): Jimei Yang* (UC Merced), Simon Safar (UC Merced), Ming-Hsuan Yang (UC Merced)
Parsing Occluded People ( PDF): Golnaz Ghiasi, Yi Yang (University of California , Irvine), Deva Ramanan, Charless Fowlkes* (UC Irvine)
Occlusion Coherence: Localizing Occluded Faces with a Hierarchical Deformable Part Model ( PDF): Golnaz Ghiasi, Charless Fowlkes* (UC Irvine)
Modeling long-tail distributions of object subcategories: Xiangxin Zhu* (UC Irvine), Dragomir Anguelov (Google), Deva Ramanan
A General and Simple Method for Camera Pose and Focal Length Determination: Yinqiang Zheng* (National Institute of Informat), Shigeki Sugimoto (Tokyo Institute of Technology), Imari Sato (National Institute of Informatics), Masatoshi Okutomi (Tokyo Institute of Technology)
Compuer vision vs. human vision: What can be learned?: Ali Borji* (University of Southern Califor), Laurent Itti
SteadyFlow: Spatially Smooth Optical Flow for Video Stabilization: Shuaicheng Liu (NUS), Lu Yuan (Microsoft Research Asia), Ping Tan* , Jian Sun
Nonparametric Context Modeling of Local Appearance for Pose- and Expression-Robust Facial Landmark Localization: Brandon Smith* (University of Wisconsin), Jonathan Brandt (Adobe Research), Zhe Lin (Adobe), Li Zhang
Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow ( project): Linchao Bao (City University of Hong Kong), Qingxiong Yang (City University of Hong Kong), Hailin Jin (Adobe Research)
COSTA: Co-Occurrence Statistics for Zero-Shot Classification ( PDF) - formely: Co-Occurrence Statistics for Zero-Shot Classification: Thomas Mensink* (University of Amsterdam), Efstratios Gavves (University of Amsterdam), Cees Snoek (University of Amsterdam)
Analysis by Synthesis: Object Recognition by Object Reconstruction: Mohsen Hejrati* (UC Irvine), Deva Ramanan
Object Classification with Adaptive Regions: Hakan Bilen* (KU Leuven), Marco Pedersoli , Vinay Namboodiri (Alcatel Lucent), Tinne Tuytelaars (KU Leuven), Luc Van Gool (KU Leuven)
100+ Times Faster Weighted Median Filter (WMF) ( project, PDF) - formely: Joint-Histogram Weighted Median Filter: Qi Zhang (CUHK), Li Xu (Chinese University of Hong Kong), Jiaya Jia* (CUHK)
Tracklet Association with Online Target-Specific Metric Learning - formely: Tracklet Association with Online Reidentification in Network Flow Optimaiztion for Long-term Multi-Person Tracking: BING WANG* (NTU), Gang Wang (NTU), Kap Luk Chan (NTU), LI WANG (NTU)
Piecewise Planar and Compact Floorplan Reconstruction from Images ( PDF, videos, supplementary material): Ricardo Cabral* ( Carnegie Mellon University), Yasutaka Furukawa (Washington University in St. Louis)
Persistent Tracking for Wide Area Aerial Surveillance: Jan Prokaj* (J Gradient), Gerard Medioni (USC)
Are Cars Just 3D Boxes? - Jointly Estimating the 3D Shape of Multiple Objects: Muhammad Zeeshan Zia* (ETH Zurich), Michael Stark (Stanford University), Konrad Schindler (ETH Zurich)
Graph Cut based Continuous Stereo Matching using Locally Shared Labels: Tatsunori Taniai* (University of Tokyo), Yasuyuki Matsushita (Microsoft Research Asia), Takeshi Naemura (University of Tokyo)
Two-View Camera Calibration for Multi-Layer Flat Refractive Interface: Xida Chen* (University of Alberta), Yee Hong Yang (University of Alberta)
Deblurring Low-light Images with Light Streaks ( PDF): Zhe Hu* (UC , Merced), Sunghyun Cho (Adobe), Jue Wang, Ming-Hsuan Yang (UC Merced)
Locally Optimized Product Quantization for Approximate Nearest Neighbor Search ( PDF) - formely: Locally Optimized Product Quantization: Yannis Kalantidis ( NTUA), Yannis Avrithis* ( NTUA)
Generalized Nonconvex Nonsmooth Low-Rank Minimization ( PDF): Canyi Lu (National University of Singapore), Jinhui Tang (Nanjing University of Science and Technology), Shuicheng Yan (National University of Singapore), Zhouchen Lin (Peking University)
Multiple Target Tracking Based on Undirected Hierarchical Relation Hypergraph ( PDF) - formely: Multiple Target Tracking Based on Hierarchical Relation Hypergraph: Longyin Wen* ( ia.ac.cn), Wenbo Li (tju.edu.cn), Junjie Yan (ia.ac.cn), Zhen Lei (ia.ac.cn), Dong Yi (ia.ac.cn), Stan Li (ia.ac.cn)
Discriminative Deep Metric Learning for Face Verification in the Wild: Junlin Hu* (NTU , Singapore), Jiwen Lu (ADSC , Singapore), Yap-Peng Tan
Ground Plane Estimation using a Hidden Markov Model: Ralf Dragon* (Eth Zurich), Luc Van Gool (ETH)
Human Body Shape Estimation Using a Multi-Resolution Manifold Forest: Frank Perbet (Toshiba Research Europe Ltd), Sam Johnson* (Toshiba Research Europe Ltd), Minh-Tri Pham (Toshiba Research Europe Ltd), Björn Stenger (Cambridge Research Laboratory , Toshiba Research Europe)
Separation of Line Drawings Based on Split Faces for 3D Object Reconstruction: Changqing ZOU* (SIAT)
Product Sparse Coding ( PDF): Tiezheng Ge, Kaiming He* (Microsoft Research Asia), Jian Sun
Robust and Efficient Full-Angle Quaternions for Matching Arrays of 3D Rotations: Stephan Liwicki* (Imperial College London), Stefanos Zafeiriou (Imperial College London), Maja Pantic , Björn Stenger (Cambridge Research Laboratory , Toshiba Research Europe), Minh-Tri Pham (Toshiba Research Europe Ltd)
Look at the Driver, Look at the Road: No Distraction! No Accident!: Mahdi Rezaei* (The University of Auckland), Reinhard Klette (The University of Auckland)
Efficient Boosted Exemplar-based Face Detection ( PDF): Haoxiang Li (Stevens Institute of Technology), Zhe Lin (Adobe), Jonathan Brandt (Adobe Research), Xiaohui Shen (Adobe Research), Gang Hua* (Stevens Institute of Technology)
Multiscale Combinatorial Grouping ( PDF): Pablo Arbelaez* (UC Berkeley), Jordi Pont-Tuset* (UPC BarcelonaTech), Jon Barron (UC Berkeley), Ferran Marques (UPC BarcelonaTech), Jitendra Malik (UC Berkeley)
Non-Parametric Bayesian Constrained Local Models ( PDF, videos): Pedro Martins* (ISR - University of Coimbra), Rui Caseiro (ISR - University of Coimbra), Jorge Batista (ISR - University of Coimbra)
Feature-Independent Action Spotting Without Human Localization, Segmentation or Frame-wise Tracking: Chuan Sun* (UCF), Hassan Foroosh (University of Central Florida)
A Multigraph Representation for Improved Unsupervised/Semi-supervised Learning of Human Actions ( PDF, code): Simon Jones (The University of Sheffield), Ling Shao* (The University of Sheffield)
Semi-supervised Relational Topic Model for Weakly Annotated Image Recognition in Social Media: Zhenxing Niu (Xidian University), Gang Hua* (Stevens Institute of Technology), Xinbo Gao , Qi Tian
Learning-Based Atlas Selection for Multiple-Atlas Segmentation: Gerard Sanroma* (UNC-Chapel Hill), Guorong Wu , Yaozong Gao (UNC-Chapel Hill), Dinggang Shen (University of North Carolina)
Modeling Image Patches with a Generic Dictionary of Mini-Epitomes ( PDF, supplementary material): George Papandreou (TTI Chicago), Liang-Chieh Chen (UC Los Angeles), Alan Yuille (UC Los Angeles)
Model Transport: Towards Scalable Transfer Learning on Manifolds: Oren Freifeld* (MIT), Soren Hauberg (Max Planck Institute), Michael Black (Max Planck)
Image Preconditioning: Balancing Contrast and Ringing: Yu Ji (University of Delaware), Jinwei Ye* (University of Delaware), Sing Bing Kang (Microsoft), Jingyi Yu
Complex Non-Rigid Motion 3D Reconstruction by Union of Subspaces ( PDF): Yingying Zhu* (University of queensland), Dong Huang (Carnegie Mellon University), Fernando de la Torre (CMU), Simon Lucey (CSIRO)
Recognizing RGB Images by Learning from RGB-D Data: Lin Chen* (NTU), Wen Li (NTU), Dong Xu
Cross-view Action Modeling, Learning and Recognition ( PDF): Jiang Wang* (Northwestern University), Xiaohan Nie (UCLA), Yin Xia (Northwestern University), Ying Wu (Northwestern University), Song Chun Zhu (UCLA)
Time-Mapping Using Space-Time Saliency ( project, PDF, supplementary material, slides, videos): Feng Zhou (Carnegie Mellon University), Sing Bing Kang (Microsoft Research), Michael F. Cohen (Microsoft Research)
Stereo under Sequential Optimal Sampling: A Statistical Analysis Framework for Search Space Reduction: Yilin Wang* (UNC), Jan-Michael Frahm , Enrique Dunn , Ke Wang (UNC Chapel Hill)
Empirical Minimum Bayes Risk Prediction: How to extract an extra 3% performance from vision models with just two more parameters: Vittal Premachandran (NanyangTechnologicalUniversity), Daniel Tarlow (Microsoft), Dhruv Batra* (Virginia Tech)
Matrix-Similarity Based Loss Function and Feature Selection for Alzheimer's Disease Diagnosis: Xiaofeng Zhu* (BRIC , UNC-Chapel Hill), Heung-Il Suk (UNC at Chapel Hill), Dinggang Shen
Active Frame, Location, and Detector Selection for Automated and Manual Video Annotation ( PDF): Vasiliy Karasev* (UCLA), Avinash Ravichandran (UCLA), Stefano Soatto (University of California at Los Angeles)
Saliency Optimization from Robust Background Detection: Wangjiang Zhu (Tsinghua University), Shuang Liang* (Tongji University), Yichen Wei (Microsoft Research Asia), Jian Sun
Robust Refinement of GPS-Tags Using RandomWalks with an Adaptive Damping Factor: Amir Roshan Zamir* (CRCV @ UCF)
Color Transfer using Probabilistic Moving Least Squares: Youngbae Hwang , Joon-Young Lee (KAIST), In So Kweon (KAIST), Seon Joo Kim* (Yonsei University)
Single-View 3D Scene Parsing by Attributed Grammar ( PDF): Xiaobai Liu (UCLA), Yibiao Zhao (UCLA), Song Chun Zhu (UCLA)
Calibrating a non-isotropic near point light source using a plane: Jaesik Park* (KAIST), Sudipta Sinha (Microsoft Research), Yasuyuki Matsushita (Microsoft Research Asia), Yu-Wing Tai (KAIST), In So Kweon
Exploiting Shading Cues in Kinect IR Images for Geometry Refinement: Gyeongmin Choe* (KAIST), Jaesik Park (KAIST), Yu-Wing Tai (KAIST), In So Kweon (KAIST)
Fine-Grained Visual Comparisons with Local Learning ( PDF): Aron Yu* (University of Texas at Austin), Kristen Grauman (University of Texas at Austin)
Compact Representation for Image Classification: To Choose or to Compress?: Yu Zhang* (NTU.sg), Jianxin Wu (Nanjing University), Jianfei Cai
Alert: Predicting Failures: Peng Zhang (Virginia Tech), Jiuling Wang (UT Austin), Ali Farhadi (University of Washington), Martial Hebert (Carnegie Mellon University), Devi Parikh* (Virginia Tech)
Surface Registration by Optimization in Constrained Diffeomorphism Space: Wei Zeng* (School of Computing and Information Sciences , Florida International University), Lok Ming Lui (The Chinese University of Hong Kong , Mathmatic department), Xianfeng Gu (Stony Brook University)
Low-Cost Compressive Sensing for Color Video and Depth ( PDF): Duke University), Lawrence Carin (Duke University)
Deformable Object Matching via Deformation Decomposition based 2D Label MRF: Kangwei Liu* (Institute of Automation , CAS), zhang Junge (Institute of Automation , CAS), Kaiqi Huang (National Laboratory of Pattern Recognition), Tieniu Tan (Chinese Academy of Sciences)
Similarity-Aware Patchwork Assembly for Depth Image Super-Resolution: Jing Li (Peking University), Zhichao Lu (Peking University), Gang Zeng* (Peking University), Hongbin Zha (Pekin University)
Symmetry-Aware Isometric Matching of Incomplete 3D Surfaces: Yusuke Yoshiyasu* (AIST)
Generalized Max Pooling: Naila Murray* (Xerox Research Center Europe), Florent Perronnin
The Synthesizability of texture examples ( PDF, project, code): Dengxin Dai* (ETH), Hayko Riemenschneider (ETH), Luc Van Gool (ETH)
Unsupervised Learning of Dictionaries of Hierarchical Compositional Models ( PDF): Jifeng Dai* (Tsinghua University), UCLA, Yi Hong (UCLA), WENZE Hu (UCLA), Ying Nian Wu (UCLA)
Temporal Segmentation of Egocentric Videos ( PDF, project): Yair Poleg (Hebrew University), Chetan Arora* (Hebrew University of Jerusalem), Shmuel Peleg (Hebrew University)
Efficient Action Localization with Approximately Normalized Fisher Vectors ( PDF) - formely: Efficient Localization with Fisher Vectors using Approximate Normalizations: Dan Oneata (INRIA), Jakob Verbeek*, Cordelia Schmid (INRIA)
Fast Approximate Inference in Higher Order MRF-MAP Labeling Problems ( PDF, project): Chetan Arora* (Hebrew University of Jerusalem), S.N. Maheshwari, Subhashis Banerjee, Prem Kalra
Multi Label Generic Cuts: Optimal Inference in Multi Label Multi Clique MRF-MAP Problems ( PDF, project): Chetan Arora* (Hebrew University of Jerusalem), S.N. Maheshwari
Submodular Object Recognition ( PDF): Fan Zhu (The University of Sheffield), Zhuolin Jiang (Huawei Noah\'s Ark Lab), Ling Shao* (The University of Sheffield)
A Probabilistic Framework for Multitarget Tracking with Mutual Occlusions ( PDF): Menglong Yang* (Sichuan University), Yiguang Liu (Sichuan University), Longyin Wen ( ia.ac.cn), Zhisheng You (Sichuan University), Stan Li (ia.ac.cn)
Multi-fold MIL Training for Weakly Supervised Object Localization ( PDF): Ramazan Gokberk Cinbis* (INRIA), Jakob Verbeek, Cordelia Schmid (INRIA)
Fast Supervised Hashing with Decision Trees for High-Dimensional Data ( technical report): Guosheng Lin* (The University of Adelaide), Chunhua Shen (University of Adelaide), Qinfeng Shi (The University of Adelaide), Anton van den Hengel (University of Adelaide), David Suter (The University of Adelaide)
Point Matching in the Presence of Outliers in Both Point Sets: A Concave Optimization Approach: Wei Lian , Lei Zhang* (The Hong Kong Polytechnic University)
Robust Surface Reconstruction via Triple Sparsity ( PDF): Hicham Badri* (INRIA), Hussein Yahia (INRIA), Driss Aboutajdine (CNRST , URAC 29)
Robust Estimation of 3D Human Poses from Single Images ( PDF, supplementary material): CHUNYU WANG (Peking University), Yizhou Wang* (Peking University), Zhouchen Lin (Peking University), Alan Yuille (University of California at Los Angeles), Wen Gao (Peking University)
A Minimal Solution to the Generalized Pose-and-Scale Problem ( PDF): Jonathan Ventura* ( Graz University of Technology), Clemens Arth ( Graz University of Technology), Gerhard Reitmayr ( Qualcomm Austria Research Center), Dieter Schmalstieg ( Graz University of Technology)
Deep Fisher Kernels: Mayu Sakurada (The University of Tokyo), Vladyslav Sydorov (National Technical University of Ukraine), Christoph Lampert* (IST Austria)
MILCut: A Sweeping Line Multiple Instance Learning Paradigm for Interactive Image Segmentation ( PDF): Jiajun Wu* (Tsinghua University), Yibiao Zhao (UCLA), Jun-Yan Zhu (UC Berkeley), Zhuowen Tu (UCSD)
Beyond Comparing Image Pairs: Setwise Active Learning for Relative Attributes ( PDF): Lucy Liang (University of Texas at Austin), Kristen Grauman* (University of Texas at Austin)
Immediate, scalable object category detection: Yusuf Aytar* (University of Oxford), Andrew Zisserman (Oxford)
Blind Multi-Image Restoration: Haichao Zhang* (Duke University)
Data-driven Flower Petal Modeling with Botany Priors: Chenxi Zhang* (University of Kentucky), Mao Ye (University of Kentucky), BO FU (University of Kentucky), Ruigang Yang (University of Kentucky)
Saliency Detection on Light Fields ( PDF, dataset): Nianyi Li* (University of Delaware), Jinwei Ye (University of Delaware), Yu Ji (University of Delaware), Haibin Ling (Temple University), Jingyi Yu (University of Delaware)
Pedestrian Detection in Low-resolution Imagery by Learning Multi-scale Intrinsic Motion Structures (MIMS): Jiejie Zhu* (SRI International)
Measuring Distance Between Unordered Sets of Different Sizes: Andrew Gardner* (Louisiana Tech University), Jinko Kanno (Louisiana Tech University), Rastko Selmic (Louisiana Tech University), Christian Duncan (Quinnipiac University)
Strokelets: A Learned Multi-Scale Representation for Scene Text Recognition ( PDF): Cong Yao, Xiang Bai*(Huazhong University of Science and Technology), Baoguang Shi, Wenyu Liu
Inferring Analogous Attributes: Chao-Yeh Chen* (The Univ. of Texas at Austin), Kristen Grauman (University of Texas at Austin)
Online Object Tracking, Learning and Parsing with And-Or Graphs ( PDF, project): Yang Lu (UCLA), Tianfu Wu* (University of California , Los), Song Chun Zhu (UCLA)
Co-Segmentation of Textured 3D Shapes with Sparse Annotations ( PDF, supplementary material): Mehmet Ersin Yumer* (Carnegie Mellon University), Won Chun, Ameesh Makadia (Google Research)
Quasi Real-Time Summarization for Consumer Videos ( PDF): Bin Zhao* (CMU), Eric Xing (Carnegie Mellon University)
Beyond Human Opinion Scores: Blind Image Quality Assessment based on Synthetic Scores: Peng Ye* (University of Maryland), David Doermann (University of Maryland)
Detecting Objects using Deformation Dictionaries: Bharath Hariharan* (Berkeley), Piotr Dollar (Miscrosoft Research Redmond), Larry Zitnick
Using k-poselets for detecting people and localizing their keypoints: Bharath Hariharan* (Berkeley), Georgia Gkioxari , Ross Girshick (UCB), Jitendra Malik (University of California at Berkeley)
Super Normal Vector for Activity Recognition Using Depth Sequences: Xiaodong Yang* (City College of New York , CUNY), Yingli Tian (City University of New York)
Weighted Nuclear Norm Minimization with Application to Image Denoising: Shuhang Gu (The Hong Kong Polytechnic University), Lei Zhang* (The Hong Kong Polytechnic University), Xiangchu Feng (Xidian University), Wangmeng Zuo (Harbin Institute of Technology)
Semi-Supervised Coupled Dictionary Learning for Person Re-identification: Xiao Liu* (Zhejiang University), Mingli Song (zju), Dacheng Tao , Xingchen Zhou (zju), Chun Chen (zju), Jiajun Bu (zju)
Object-based Multiple Foreground Video Co-segmentation ( PDF): Huazhu Fu* (Nanyang Technological University), Dong Xu, Bao Zhang (Tianjin University), Stephen Lin
A 3D Feature for Moving Range Scanning Systems: Xiangqi Huang (The Univ. of Tokyo), Bo Zheng* (The Univ. of Tokyo), Takeshi Masuda (The National Inst. of Adv. Industrial Sci. and Tech. , AIST), Katsushi Ikeuchi (Univerity of Tokyo)
Learning Fine-grained Image Similarity with Deep Ranking ( PDF): Jiang Wang* (Northwestern University), Yang Song (Google), Thomas Leung (Google), Charles Rosenberg (Google), James Philbin (Google), Bo Chen (Caltech), Ying Wu (Northwestern University)
Domain Adaptation on the Statistical Manifold: Mahsa Baktashmotlagh* (NICTA), Mehrtash Harandi , Brian Lovell , Mathieu Salzmann (NICTA)
Human Action Recognition Based on Context-Dependent Graph Kernels: Baoxin Wu* (NLPR , IACSA), Chunfeng Yuan (NLPR , IACAS), Weiming Hu (NLPR , CASIA)
Towards Good Practices for Action Video Encoding ( PDF): Jianxin Wu* (Nanjing University), Yu Zhang (NTU.sg), Weiyao Lin (Shanghai Jiao Tong University)
Multi-source Deep Learning for Human Pose Estimation: Wanli Ouyang* (Chinese University of Hong Kong), Xiaogang Wang (Chinese University of Hong Kong), Xiao Chu (The Chinese University of Hong Kong)
Beta Process Multiple Kernel Learning: Bingbing Ni* (ADSC Singapore), Pierre Moulin (UIUC)
SCAMS: Simultaneous Clustering and Model Selection ( PDF): Zhuwen Li* (NUS), Loong-Fah Cheong (NUS), Steven Zhiying Zhou (NUS)
Collective Matrix Factorization Hashing for Multimodal Data: Guiguang Ding (Tsinghua University), Yuchen Guo (Tsinghua University), Jile Zhou* (Tsinghua University)
Co-localization in Real-World Images: Kevin Tang* (Stanford University), Armand Joulin (Stanford University), Li-Jia Li (Yahoo! Research), Li Fei-Fei (Stanford University)
User-Specific Hand Modeling from Monocular Depth Sequences: Jonathan Taylor* (Microsoft Research), Richard Stebbing (University of Oxford), Varun Ramakrishna , Cem Keskin (Microsoft Research), Jamie Shotton (Microsoft Research), Shahram Izadi (Microsoft Research), Andrew Fitzgibbon (Microsoft Research), Aaron Hertzmann
Multi-feature Spectral Clustering with Minimax Optimization: Hongxing Wang* (NTU), Chaoqun Weng (NTU), Junsong Yuan (Nanyang Technological University)
DAISY Filter Flow: A Generalized Discrete Approach to Dense Correspondences: Hongsheng Yang (University of North Carolina at Chapel Hill), Wen-Yan Lin (Oxford Brookes University), Jiangbo Lu* (ADSC Singapore)
Occlusion Geodesics for Online Multi-Object Tracking ( project,videos): Horst Possegger* (Graz University of Technology), Thomas Mauthner (TU Graz), Peter Roth, Horst Bischof (Graz University of Technology)
Multi-target Tracking with Motion Context in Tensor Power Iteration: Xinchu Shi* (NLPR), Haibin Ling (Temple University), Weiming Hu (NLPR , CASIA), Chunfeng Yuan (NLPR , IACAS)
Facial Expression Recognition via a Boosted Deep Belief Network: Ping Liu* (University of south carolina), shizhong han (university of south carolina), zibo meng (university of south carolina), Yan Tong (university of south carolina)
Bayesian Active Contours with Affine-Invariant, Elastic Shape Prior: Darshan Bryner* (Florida State University), Anuj Srivastava
Frequency-Based 3D Reconstruction of Transparent and Specular Objects: Ding Liu* (University of Alberta), Xida Chen (University of Alberta), Yee-Hong Yang
Bi-label Propagation for Generic Multiple Object Tracking ( PDF): Wenhan Luo* (Imperial College London), Tae-Kyun Kim (Imperial College London), Bjorn Stenger (Cambridge Research Laboratory , Toshiba Research Europe), Xiaowei Zhao (Imperial College London), Roberto Cipolla (Cambridge)
Bayesian Active Appearance Models - formely: Probabilistic Active Appearance Models: Joan Alabort-i-Medina* (Imperial College London), Stefanos Zafeiriou (Imperial College London)
Transformation Pursuit for Image Classification ( PDF): Mattis Paulin* (Inria), Jerome Revaud (Inria), Zaid Harchaoui (Inria), Florent Perronnin (XRCE), Cordelia Schmid (Inria)
Dense Non-Rigid Shape Correspondence using Random Forests ( PDF): Emanuele Rodola* (TU Munich), Samuel Rota Bulo` (FBK), Thomas Windheuser (TU Munich), Matthias Vestner (TU Munich), Daniel Cremers (TU Munich)
Finding the Subspace Mean or Median to Fit Your Need: Timothy Marrinan* (Colorado State University), Michael Kirby (Colorado State University), Bruce Draper (Colorado State University), Chris Peterson
Deblurring Text Images via L0-Regularized Intensity and Gradient Prior ( PDF): Jinshan Pan* (DUT), Zhe Hu (UC , Merced), Zhixun Su (Dalian University of Technology), Ming-Hsuan Yang (UC Merced)
Manifold Based Dynamic Texture Synthesis from Extremely Few Samples: Hongteng Xu* (Georgia Institute of Technolog), Hongyuan Zha (Georgia Institute of Technology), Mark Davenport (Georgia Tech)
Super-Resolving Noisy Images: Abhishek Singh* (University of Illinois), Fatih Porikli (Australian National University), Narendra Ahuja (University of Illinois at Urbana-Champaign)
Local Readjustment for High-Resolution 3D Reconstruction ( PDF, supplementary material): Siyu Zhu (HKUST), Tian Fang (HKUST), Jianxiong Xiao (Princeton), Long Quan (HKUST)
Dual-Space Decomposition of 2D Complex Shapes: Guilin Liu* (George Mason University), Zhonghua Xi (George Mason University), Jyh-Ming Lien (George Mason University)
Aliasing Detection and Reduction in Plenoptic Imaging: Zhaolin Xiao (Northwestern Polytechnical University), Qing Wang* (Northwestern Polytechnical University), Jingyi Yu , Guoqing Zhou (Northwestern Polytechnical University)
Finding Vanishing Points via Point Alignments in Image Primal and Dual Domains: JosÃƒÂ© Lezama* (CMLA - ENS Cachan), Rafael Grompone von Gioi (CMLA - ENS Cachan), Jean-Michel Morel (Ecole Normale Superieure de Cachan), Gregory Randall (Universidad de la RepÃƒÂºblica , Uruguay)
Investigating Haze-relevant Features in A Learning Framework for Image Dehazing: Ketan Tang* (HKUST), Jianchao Yang (Adobe), Jue Wang
Stacked Progressive Auto-Encoder (SPAE) for Face Recognition Across Poses: Meina Kan* (Chinese Academy of Sciences), Shiguang Shan (Chinese Academy of Sciences), Hong Chang (Chinese Academy of Sciences), Xilin Chen
Locality in Generic Instance Search from One Example: Ran Tao* (University of Amsterdam), Efstratios Gavves (University of Amsterdam), Cees Snoek (University of Amsterdam), Arnold Smeulders (University of Amsterdam)
High Quality Photometric Reconstruction using a Depth Camera ( project, PDF): Sk Mohammadul Haque (Indian Institute of Science), Avishek Chatterjee (Indian Institute of Science), Venu Madhav Govindu (Indian Institute of Science)
Is Rotation a Nuisance in Shape Recognition?: Qiuhong Ke (Beijing Forestry University), Yi Li* (NICTA)
Orientation Robust Textline Detection in Natural Images: Le Kang (University of Maryland), Yi Li* (NICTA)
Detection, Rectification and Segmentation of Co-planar Repeated Patterns: James Pritts* (Czech Technical University), Ondrej Chum , Jiri Matas (Czech Technical University)
Discriminative Blur Detection Features ( PDF, project, dataset, code): Jianping Shi* (CUHK), Li Xu (Chinese University of Hong Kong), Jiaya Jia (CUHK)
Visual Tracking via Probability Continuous Outlier Model: Dong Wang* (DUT), Huchuan Lu (DUT)
Clothing Co-Parsing by Joint Image Segmentation and Labeling: Wei Yang (sysu.edu.cn), Liang Lin* (Sysu.edu.cn), Ping Luo
Randomized Max-Margin Compositions for Visual Recognition: Angela Eigenstetter* (University of Heidelberg), Bjorn Ommer
Learning Expressionlets on Spatio-Temporal Manifold for Dynamic Facial Expression Recognition: Mengyi Liu* (ICT , CAS), Shiguang Shan (Chinese Academy of Sciences), Ruiping Wang (Institute of Computing Technology , Chinese Academy of Sciences), Xilin Chen
Switchable Deep Network for Pedestrian Detection: Ping Luo , Yonglong Tian* (CUHK)
Patch-based Evaluation of Image Segmentation: Christian Ledig* (Imperial College London), Wenzhe Shi , Wenjia Bai , Daniel Rueckert (Imperial College London)
Learning to Learn, from Transfer Learning to Domain Adaptation: A Unifying Perspective: Novi Patricia* (Idiap Research Institute), Barbara Caputo (Idiap)
Who Do I Look Like? Determining Parent-Offspring Resemblance via Genetic Features: Afshin Dehghan* (University of Central Florida), Enrique Ortiz (UCF)
From Human-Annotated to Machine-Discovered Concepts using Consensus Regularization: Afshin Dehghan* (University of Central Florida), Haroon Idrees (University of Central Florida)
Bags of Spacetime Energies for Dynamic Scene Recognition: Christoph Feichtenhofer* (Graz University of Technology), Axel Pinz (Graz University of Technology), Richard Wildes (York University)
3D Reconstruction from Accidental Motion ( project, PDF): Fisher Yu* (Princeton University), David Gallup (Google Inc.)
Using Projection Kurtosis Concentration Of Natural Images For Blind Noise Covariance Matrix Estimation: Siwei Lyu* (University at Albany , SUNY)
Ask the image: supervised pooling to preserve feature locality: Sean Ryan Fanello* (IIT), Nicoletta Noceti (Universita' di Genova), Carlo Ciliberto (IIT), Giorgio Metta (IIT), Francesca Odone (Universita' di Genova)
Light Field Stereo Matching Using Bilateral Statistics of Surface Cameras: Can Chen (UDEL), Haiting Lin* (UDEL), Zhan Yu (UDEL), Sing Bing Kang (Microsoft Research), Jingyi Yu
Video Classification Based on Generalized Maximum Co-occurrence Cliques: Amir Roshan Zamir* (CRCV @ UCF), Shayan Modiri Assari (University Of Central Florida)
Congruency-Based Reranking: Itai Ben Shalom (Tel Aviv University), Adiel Ben Shalom (Tel Aviv University), Noga Levy* (Tel Aviv University), Lior Wolf , Tamir Hazan (Haifa University), Nachum Dershowitz (Tel Aviv University), Yaniv Bar (Tel Aviv University), Roni Shweka (The Friedberg Genizah Project), Yaacov Choueka (The Friedberg Genizah Project)
Predicting User Annoyance Using Image Attributes: Gordon Christie (Virginia Tech), Amar Parkash , Ujwal Krothapalli (Virginia Tech), Devi Parikh* (Virginia Tech)
Talking Heads: Detecting Humans and Recognizing Their Interactions ( PDF): Minh Hoai* (University of Oxford), Andrew Zisserman (Oxford)
3D Modeling from Wide Baseline Range Scans using Contour Coherence: Ruizhe Wang* (USC), Jongmoo Choi (USC), Gerard Medioni (USC)
Fisher and VLAD with FLAIR: Koen Van de Sande* (University of Amsterdam), Cees Snoek (University of Amsterdam), Arnold Smeulders (Centrum Wiskunde &), Informatica
Stable Learning in Coding Space for Multi-Class Decoding and Its Extension for Multi-Class Hypothesis Transfer Learning: Bang Zhang* (National ICT Australia), Yi Wang (National ICT Australia), Yang Wang (National ICT Australia), fang Chen (National ICT Australia)
PatchMatch Based Joint View Selection and Depthmap Estimation: Enliang Zheng* (UNC-Chapel Hill), Vladimir Jojic (UNC-Chapel Hill), Enrique Dunn , Jan-Michael Frahm
Asymmetric sparse kernel approximations for large-scale visual search ( PDF): Damek Davis* (UCLA), Stefano Soatto (University of California at Los Angeles), Jonathan Balzer (UCLA)
Multiple Granularity Analysis for Fine-grained Action Detection: Bingbing Ni* (ADSC Singapore), Pierre Moulin (UIUC)
Active Annotation Translation: Steven Branson* (California Institute of Technology), Pietro Perona (California Institute of Technology)
Scattering Parameters and Surface Normals from Homogeneous Translucent Materials using Photometric Stereo: Bo Dong (College of William &), Mary, Kathleen Moore (College of William &), Mary, Weiyi Zhang (College of William &), Mary, Pieter Peers* (College of William &), Mary
Three Guidelines of Online Learning for Large-Scale Visual Recognition: Yoshitaka Ushiku* (Univ. of Tokyo), Tatsuya Harada (Univ. of Tokyo)
The Secrets of Salient Object Segmentation ( PDF, supplementary material): Yin Li (Georgia Institute of Technolog), Xiaodi Hou* (Caltech), Christof Koch (Allen Institute for Brain Science), James Rehg (Georgia Institute of Technology), Alan Yuille (University of California at Los Angeles)
Higher-Order Clique Reduction Without Auxiliary Variables: Hiroshi Ishikawa* (Waseda University)
Discriminative Ferns Ensemble for Hand Pose Recognition: Eyal Krupka* (Microsoft Research), Aharon Bar Hillel (Microsoft Research), Ben Klein (Microsoft Research), Alon Vinnikov (Microsoft Research), Daniel Freedman (Microsoft Research), Simon Stachniak (Microsoft R&),D
Large-scale Visual Font Recognition - formely: Large-scale visual font recognition: Guang Chen, Jianchao Yang (Adobe Research), Hailin Jin (Adobe Research), Jonathan Brandt (Adobe Research), Eli Shechtman, Aseem Agarwala (Adobe), Tony Han (University of Missouri)
Bregman Divergences for Infinite Dimensional Covariance Matrices: Mehrtash Harandi* , Mathieu Salzmann (NICTA), Fatih Porikli (Australian National University)
Multilabel Ranking with Inconsistent Rankers: Xin Geng* (Southeast University), Longrun Luo (Southeast University)
Deep Learning Hidden Identity Features for Face Verification: Yi Sun* (CUHK), Xiaogang Wang (Chinese University of Hong Kong), Xiaoou Tang (Chinese University of Hong Kong)
Latent Dictionary Learning for Sparse Representation based Classification: Meng Yang* (ETH Zuich), Luc Van Gool (ETH)
CID: Combined Image Denoising in Spatial and Frequency Domains Using Web Images: Huanjing Yue (School), Xiaoyan Sun* (Microsoft Research Asia), Jingyu Yang (Tianjin University), Feng Wu (Microsoft Research Asia)
A New Perspective on Material Classification and Ink Identification: Rakesh Shiradkar (NUS), Li Shen (A*STAR Singapore), George Landon (Eastern Kentucky University), Sim Heng Ong (NUS), Ping Tan*
Fast Rotation Search with Stereographic Projections for 3D Registration: Alvaro Parra Bustos* (The University of Adelaide), Tat-Jun Chin (University of Adelaide), David Suter (The University of Adelaide)
Filter Pairing Neural Network for Person Re-identification: Wei Li (The Chinese University of Hong Kong), Rui Zhao* (CUHK), Tong Xiao (The Chinese University of Hong Kong), Xiaogang Wang (Chinese University of Hong Kong)
Sequential Convex Relaxation for Mutual-Information-Based\\Unsupervised Figure-Ground Segmentation: Youngwook Kee* (KAIST), Mohamed Souiai (TUM), Daniel Cremers (TUM), Junmo Kim (KAIST)
A Convex Relaxation of Ambrosio-Tortorelli's Elliptic Functional \\for the Mumford-Shah Functional: Youngwook Kee* (KAIST), Junmo Kim (KAIST)
Recovering Surface Details under General Unknown Illumination Using Shading and Coarse Multi-view Stereo: DI XU* (NTU), Qi Duan , Jianmin Zheng , Juyong Zhang (USTC), Jianfei Cai , Tat-Jen Cham (Nanyang Technological University)
Fully Automated Non-rigid Segmentation with Distance Regularized Level Set Evolution Initialized and Constrained by Deep-structured Inference: Tuan Ngo (University of Adelaide), Gustavo Carneiro*
Non-rigid Segmentation using Sparse Low Dimensional Manifolds and Deep Belief Networks: Jacinto Nascimento (Instituto Superior Tecnico), Gustavo Carneiro*
3D-aided face recognition robust to expression and pose variations: Baptiste Chu* (Morpho Safran Group / Ecole Centrale de Lyon), Sami Romdhani (Morpho Safran Group), Liming Chen (Ecole Centrale Lyon)
Remote Heart Rate Measurement From Face Videos Under Realistic Situations: Xiaobai Li* (University of Oulu), Jie Chen (University of Oulu), Guoying Zhao (University of Oulu), Matti PietikÃƒÂ¤inen (University of Oulu)
Discriminative Feature-to-Point Matching in Image-Based Localization: Michael Donoser* , Dieter Schmalstieg (Graz University of Technology)
Action localization by tubelets from motion: Mihir Jain* (INRIA), Jan Van Gemert (UVA), Herve Jegou (INRIA), Patrick Bouthemy (INRIA), Cees Snoek (University of Amsterdam)
Noising versus Smoothing for Vertex Identification in Unknown Shapes ( bibtex, videos): Konstantinos A. Raftopoulos* ( CEDRIC-CNAM), Marin Ferecatu ( CEDRIC-CNAM)
Multiple Structured-Instance Learning for Semantic Segmentation with Uncertain Training Data ( PDF): Feng-Ju Chang (University of Southern California), Yen-Yu Lin* (Academia Sinica), Kuang-Jui Hsu (Academia Sinica)
Constructing Robust Affinity Graph for Spectral Clustering: Xiatian Zhu* (Queen Mary Univ. of London), Chen Change Loy , Shaogang Gong (Queen Mary University of London)
Reconstructing Evolving Tree Structures in Time Lapse Sequences: PrzemysÃ…â€šaw GÃ…â€šowacki* (EPFL); Miguel Pinheiro (Czech Technical University in Prague); Raphael Sznitman (EPFL); Engin Turetken (CVLab EPFL); Daniel Lebrecht (University of Geneva); Anthony Holtmaat (University of Geneva); Jan Kybic (Czech Technical University in Prague); Pascal Fua (EPFL)
Scene Parsing with Object Instances and Occlusion Ordering ( PDF) - formely: Beyond Pixel Labels: Image Parsing with Object Instances and Occlusion Ordering: Joseph Tighe* (UNC Chapel Hill), Marc Niethammer (UNC Chapel Hill), Svetlana Lazebnik (UIUC)
Very Fast Solution to the PnP Problem with Algebraic Outlier Rejection: Luis Ferraz* (Universitat Pompeu Fabra), Xavier Binefa (Universitat Pompeu Fabra), Francesc Moreno-Noguer (Institut de Robotica i Informatica Industrial , UPC/CSIC)
A Hierarchical Probabilistic Model for Facial Feature Detection: Yue Wu* (RPI), Ziheng Wang (RPI), Qiang Ji
Active Sampling for Subjective Image Quality Assessment: Peng Ye* (University of Maryland), David Doermann (University of Maryland)
Informed Haar-like Features Improve Pedestrian Detection: Shanshan Zhang* (University of Bonn), Christian Bauckhage (Fraunhofer IAIS (Sankt Augsitin , Germany)), Armin Cremers
Shadow Removal from Single RGB-D Images: Yao Xiao* (HKUST), Efstratios Tsougenis (HKUST), Chi-keung Tang
Sign Language Spotting using Hierarchical Sequential Patterns with Temporal Intervals: Nicolas Pugeault* (University of Surrey), Eng-Jon Ong (University of Surrey), Richard Bowden , Oscar Koller (Human Language Technology and Pattern Recognition Group , RWTH Aachen University)
Accurate Localization and Pose Estimation for Large 3D Models: Linus SvÃƒÂ¤rm (Lund University), Olof Enqvist , Magnus Oskarsson* (Lund University), Fredrik Kahl (Lund University)
Efficient Nonlinear Markov Models for Human Motion ( PDF): Andreas Lehrmann* ( MPI for Intelligent Systems), Peter Gehler ( MPI for Intelligent Systems), Sebastian Nowozin ( Microsoft Research)
Object Partitioning using Local Convexity: Simon Christoph Stein* (Universitaet Goettingen), Jeremie Papon (University of Goettingen), Markus Schoeler (Universitaet Goettingen), Florentin Woergoetter (Universitaet Goettingen)
Minimal Scene Descriptions from Structure from Motion Models: Song Cao* (Cornell University), Noah Snavely
Efficient High-Resolution Stereo Matching using Local Plane Sweeps ( PDF, project): Sudipta Sinha* (Microsoft Research), Daniel Scharstein, Richard Szeliski (Microsoft Research)
Two-Class Weather Classification ( PDF, project, dataset, code) - formely: Two-Class Weather Labeling: Cewu Lu* (The Hong Kong University of Sc), DI LIN (CUHK), Jiaya Jia (CUHK), Chi-keung Tang
A Procrustean Markov Process for Non-Rigid Structure Recovery: Minsik Lee* (Seoul National University), Chong-Ho Choi (Seoul National University), Songhwai Oh (Seoul National University)
Distance Encoded Product Quantization: Jae-Pil Heo* (KAIST), Zhe Lin (Adobe), Sung-eui Yoon (KAIST)
Gyro-Based Multi-Image Deconvolution for Removing Handshake Blur: Sung Hee Park* (Stanford University), Marc Levoy
Joint Motion Segmentation and Background Subtraction in Dynamic Scenes: Adeel Mumtaz* (City University of Hong Kong), Weichen Zhang (City University of Hong Kong), Antoni Chan (City University Hong Kong)
Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition ( PDF) - formely: Leveraging Hierarchical Parametric Network for Skeletal Joints Action Segmentation and Recognition: Di Wu (The University of Sheffield), Ling Shao* (The University of Sheffield)
T-Linkage: a Continuous Relaxation of J-Linkage for Multi-Model Fitting: Luca Magri* (UniversitÃƒ degli Studi Milano), Andrea Fusiello
Partial Symmetry in Polynomial Systems and Its Application in Computer Vision: Yubin Kuang* (Centre for Mathematical Scienc), Yinqiang Zheng (National Institute of Informat), Kalle Astroem (Lund University)
Decorrelated Vectorial Total Variation ( PDF, code): Shunsuke Ono* (Tokyo Institute of Technology), Isao Yamada (Tokyo Institute of Technology)
Locally Linear Hashing for Extracting Non-Linear Manifolds: Go Irie* (NTT), Zhenguo Li (Columbia University), Xiao-Ming Wu (Columbia University), Shi-Fu Chang (Columbia University)
Gesture Recognition Portfolios for Personalization: Angela Yao* , Luc Van Gool (ETH), Pushmeet Kohli
Additive Quantization for Extreme Vector Compression: Artem Babenko* (MIPT), Victor Lempitsky (Skoltech)
Covariance descriptors for 3D shape matching and retrieval: Hedi Tabia* (ETIS/ENSEA (University of Cergy-Pontoise (CNRS (UMR 8051 , France)))), Hamid Laga (Phenomics and Bioinformatics Research Centre , University of South Australia), David Picard (ETIS/ENSEA, University of Cergy-Pontoise, CNRS, France), Philippe-Henri Gosselin (ETIS/ENSEA, University of Cergy-Pontoise, CNRS, France)
Photometric Bundle Adjustment for Dense Multi-View 3D Modeling: AmaÃ¯Â¿Â½l Delaunoy* (ETH), Marc Pollefeys (ETH)
Super-resolving Appearance of 3D Deformable Shapes from Multiple Videos: Jean-Sebastien Franco* (Grenoble Universities), Vagia Tsiminaki (Inria), Edmond Boyer (Inria)
Relative Parts: Distinctive Parts for Learning Relative Attributes ( PDF) - formely: Relative Parts: Disctinctive Parts for Learning Relative Attributes: Ramachandruni N. Sandeep* (IIIT HYDERABAD), Yashaswi Verma (IIIT-Hyderabad , India), C.V. Jawahar (IIIT Hyderabad)
SeamSeg: Video Object Segmentation using Patch Seams ( PDF): Avinash Ramakanth (Indian Institute of Science), Venkatesh Babu Radhakrishnan* (Indian Institute of Science)
Beat the MTurkers: Automatic Image Labeling from Weak 3D Supervision: Liang-Chieh Chen* (UCLA), Sanja Fidler (Toyota Technnological Institute), Alan Yuille (University of California at Los Angeles), Raquel Urtasun (University of Toronto)
A Hierarchical Context Model for Event Recognition in Surveillance Video: Xiaoyang Wang* (RPI), Qiang Ji
Tell Me What You See and I will Show You Where It Is ( project, PDF): Jia Xu* (University of Wisconsin-Madison), Alexander G. Schwing (University of Toronto), Raquel Urtasun (University of Toronto)
Event Detection using Multi-Level Relevance Labels and Multiple Features: Zhongwen Xu* (The University of Queensland), Ivor W. Tsang , Yi Yang (CMU), Zhigang Ma (Carnegie Mellon University), Alexander Hauptmann (Carnegie Mellon University)
Fast and Robust Archetypal Analysis for Representation Learning: Yuansi Chen* (UC Berkeley), Julien Mairal (INRIA), Zaid Harchaoui (INRIA)
Superpixel-grounded Deformable Part Models: Eduard Trulls* (IRI , UPC/CSIC), Iasonas Kokkinos (Ecole Central de Paris), Francesc Moreno-Noguer (Institut de Robotica i Informatica Industrial , UPC/CSIC), Alberto Sanfeliu (IRI , UPC/CSIC)
Relative Pose Estimation for a Multi-Camera System with Known Vertical Direction ( PDF): Gim Hee Lee* (ETH Zurich), Marc Pollefeys (ETH Zurich), Friedrich Fraundorfer (TU Munich)
Mirror Symmetry Histograms for Capturing Geometric Properties in Images: Marcelo Cicconet* (NYU), Davi Geiger (NYU), Michael Werman , Kristin Gunsalus (NYU)
Region-based Discriminative Feature Pooling for Scene Text Recognition ( PDF): Chen-Yu Lee (UCSD), Anurag Bhardwaj (eBay Research Labs), Wei Di (eBay Research Labs), Vignesh Jagadeesh (eBay Research Labs), Robinson Piramuthu (eBay Research Labs)
Turning Mobile Phones into 3D Scanners: Kalin Kolev* (ETH), Petri Tanskanen (ETH Zurich), Pablo Speciale (ETH Zurich), Marc Pollefeys (ETH)
Predicting Multiple Attributes via Relative Multi-task Learning ( PDF): Lin Chen, Qiang Zhang, Baoxin Li ( Arizona State University)
Lacunarity Analysis on Image Patterns for Texture Classification: Yuhui Quan (nus.edu.sg), Yong Xu* (South China University of Technology), Yuping Sun (South China University of Technology), Yu Luo (South\\ China University of Technology)
Pseudoconvex Proximal Splitting for $L_\infty$ Problems in Multiview Geometry: Anders Eriksson* (University of Adeliade)
Robust Scale Estimation in Real-Time Monocular SFM for Autonomous Driving ( videos) - formely: High Accuracy Monocular Localization for Autonomous Driving Using Adaptive Ground Estimation: Shiyu Song (UC San Diego), Manmohan Chandraker* ( NEC Labs America)
Multi-Cue Visual Tracking Using Robust Feature-Level Fusion Based on Joint Sparse Representation: Xiangyuan Lan (Hong Kong Baptist University), Pong C YUEN* (Hong Kong Baptist University), Andy Jinhua Ma (Hong Kong Baptist University)
Mixing Body-Part Sequences for Human Pose Estimation ( PDF): Anoop Cherian (Inria), Julien Mairal (Inria), Karteek Alahari (Inria), Cordelia Schmid (Inria)
3D Pose from Motion for Cross-view Action Recognition via Non-linear Circulant Temporal Encoding ( PDF, project, videos, code): Ankur Gupta (UBC), Julieta Martinez (UBC), Jim Little (UBC), Robert Woodham (UBC)
Better Feature Tracking Through Subspace Constraints: Bryan Poling* (University of Minnesota), Gilad Lerman (University of Minnesota), Arthur Szlam (CCNY)
Efficient Computation of Relative Pose for Multi-Camera Systems: Laurent Kneip* (Australian National University), Hongdong Li
Aerial Reconstructions via Probabilistic Data Fusion: Randi Cabezas* (MIT), Oren Freifeld (MIT), Guy Rosman (MIT), John Fisher III (MIT)
Discriminative Hierarchical Modeling of Spatio-Temporally Composable Human Activities: Ivan Lillo , Juan Carlos Niebles* (Universidad del Norte , Colombia), Alvaro Soto (Catholic University of Chile)
Unifying Spatial and Attribute Selection for Distracter-resilient Tracking: Nan Jiang* (Huazhong University of Science and Technology), Ying Wu (Northwestern University)
Complex Activity Recognition using Granger Constrained DBN (GCDBN) in Sports and Surveillance Video: Eran Swears* (Kitware), Anthony Hoogs , Qiang Ji , Kim Boyer (RPI)
Head Pose Estimation Based on Multivariate Label Distribution: Xin Geng* (Southeast University), Yu Xia (Southeast University)
Total-Variation Minimization on Unstructured Volumetric Mesh: Biophysical Applications on Reconstruction of 3D Ischemic Myocardium: Jingjia Xu* (Rochester Institute of Technology), Azar Rahimi Dehaghani (RIT), Fei Gao (Rochester Institute of Technology), Linwei Wang (RIT)
RGB-D Depth Map Enhancement with Depth and Motion in Complement: Tak-Wai Hui* (The Chinese University of Hong Kong), King-Ngi Ngan (The Chinese University of Hong Kong)
Semantic Object Selection: Ejaz Ahmed* (University of Maryland , College Park), Scott Cohen (Adobe Inc.), Brian Price
Learning-by-Synthesis for Appearance-based 3D Gaze Estimation: Yusuke Sugano* (University of Tokyo), Yasuyuki Matsushita (Microsoft Research Asia), Yoichi Sato (Univ of Tokyo)
Time Machine: Continuous Manifold Based Adaptation for Evolving Visual Domains: Judy Hoffman* (UC Berkeley), Trevor Darrell (University of California Berkeley), Kate Saenko
Real-time Simultaneous Pose and Shape Estimation for Articulated Objects with a Single Depth Camera: Mao Ye* (University of Kentucky), Ruigang Yang (University of Kentucky)
Multi-modal Learning in Loosely-organized Web Images: Kun Duan* (Indiana University), David Crandall (Indiana University), Dhruv Batra (Virginia Tech)
Visual Tracking Using Pertinent Patch Selection and Masking: Dae-Youn Lee (Korea University), Jae-Young Sim (Ulsan National Institute of Science and Technology), Chang-Su Kim*
Image Reconstruction from Bag-of-Visual-Words ( PDF): Hiroharu Kato* (The University of Tokyo), Tatsuya Harada (The University of Tokyo)
Rigid Motion Segmentation using Randomized Voting ( PDF, project, videos): Heechul Jung (KAIST), Jeognwoo Ju (KAIST), Junmo Kim (KAIST)
Salient Region Detection via High-Dimensional Color Transform ( PDF, project): Jiwhan Kim (KAIST), Dongyoon Han (KAIST), Yu-Wing Tai (KAIST), Junmo Kim* (KAIST)
Blind Image Quality Assessment using Semi-supervised Rectifier Networks: Huixuan Tang* (University of Toronto), Neel Joshi (Microsoft Research), Ashish Kapoor
Quality Assessment for Comparing Image Enhancement Algorithms: Zhengying Chen* (Peking University), Tingting Jiang (Peking University), Yonghong Tian (Peking University)
Tracking on the Product Manifold of Shape and Orientation for Tractography from Diffusion MRI: YUANXIANG WANG (University of Florida), Hesamoddin Salehian (University of Florida), Guang Cheng , Baba Vemuri* (University of Florida)
Optimizing Average Precision using Weakly Supervised Data ( PDF, project): Aseem Behl* (IIIT Hyderabad), M. Pawan Kumar, C.V. Jawahar (IIIT Hyderabad)
Pyramid-based Visual Tracking Using Sparsity Represented Mean Transform: Zhe Zhang* (CUHK), Kin Hong Wong
Similarity Comparisons for Interactive Fine-Grained Categorization ( PDF): Catherine Wah* (University of California , San Diego), Grant Van Horn (University of California , San Diego), Steven Branson (California Institute of Technology), Subhransu Maji (Toyota Technnological Institute), Pietro Perona (California Institute of Technology), Serge Belongie (University of California at San Diego)
A Cause and Effect analysis of motion trajectories for modeling actions: Sanath Narayan* (Indian Institute of Science), Kalpathi Ramakrishnan (Indian Institute of Science)
An Exemplar-based CRF for Multi-instance Object Segmentation: Xuming He* (NICTA), Stephen Gould (Australian National University)
Generating object segmentation proposals using global and local search ( PDF, code): Pekka Rantalankila (University of Oulu), Juho Kannala* (University of Oulu), Esa Rahtu (University of Oulu)
Learning Important Spatial Pooling Regions for Scene Classification ( PDF): DI LIN* (CUHK), Cewu Lu (The Hong Kong University of Sc), Renjie Liao (CUHK), Jiaya Jia (CUHK)
Multipoint Filtering with Local Polynomial Approximation and Range Guidance: Xiao Tan* (UNSW), Changming Sun (CSIRO), Tuan Pham
Real-time Model-based Articulated Object Pose Detection and Tracking with Variable Rigidity Constraints: Karl Pauwels* (University of Granada), Leonardo Rubio (University of Granada), Eduardo Ros (University of Granada)
Separable Kernel for Image Deblurring: Lu Fang* (USTC), Haifeng Liu (USTC), Feng Wu (Microsoft Research Asia)
Discrete-Continuous Depth Estimation from a Single Image: Miaomiao Liu (NICTA), Mathieu Salzmann* (NICTA), Xuming He (NICTA)
A Learning-to-Rank Approach for Image Color Enhancement: Jianzhou Yan* (Chinese University of Hong Kong), Stephen Lin , Sing Bing Kang (Microsoft Research), Xiaoou Tang (Chinese University of Hong Kong)
Gait Recognition under Speed Transition: Al Mansur* (Osaka University), Rasyid Aqmar (Osaka University), Yasushi Makihara (Osaka University), Yasushi Yagi (Osaka University)
Towards Unified Human Parsing and Pose Estimation: Jian Dong* (NUS), Qiang Chen (National University of Singapore), Xiaohui Shen (Adobe Research), Jianchao Yang (Adobe), Shuicheng Yan (National University of Singapore)
Large-Scale Optimization of Hierarchical Features for Saliency Prediction in Natural Images: Eleonora Vig* (Harvard University), Michael Dorr (Harvard Medical School), David Cox (Harvard University)
NMF-KNN: Image Annotation using Weighted Multi-view Non-Negative Matrix Factorization: Mahdi Kalayeh* (University of Central Florida), Haroon Idrees (University of Central Florida), Mubarak Shah (UCF)
Range-Sample Depth Feature for Action Recognition ( PDF) - formely: A Depth-Aware Descriptor for Action Recognition: Cewu Lu* (The Hong Kong University of Sc), Jiaya Jia (CUHK), Chi-keung Tang
Human Action Recognition across Datasets by Foreground-weighted Histogram Decomposition: Waqas Sultani* (University of Central Florida), Imran Saleemi (University of Central Florida)
Error-tolerant Scribbles Based Interactive Image Segmentation: Junjie Bai* (The University of Iowa), Xiaodong Wu (University of Iowa)
Efficient Squared Curvature: Claudia Nieuwenhuis* (UC Berkeley), Eno Toeppe (UC Berkeley), Lena Gorelick , Olga Veksler (University of Western Ontario), Yuri Boykov (University of Western Ontario)
Backscatter Compensated Photometric Stereo with 3 Sources: Chourmouzios Tsiotsios* (Imperial College London), Maria E Angelopoulou (Imperial College London), Tae-Kyun Kim (Imperial College London), Andrew J Davison (Imperial College London)
Discriminative Sparse Inverse Covariance Matrix: Application in Brain Functional Network Classification: Luping Zhou* (University of Wollongong), Lei Wang (University of Wollongong), Philip Ogunbona (University of Wollongong)
FAST LABEL: Easy and Efficient Optimization of Joint Multi-Label and Estimation Problems ( PDF): Byung-Woo Hong* ( Chung-Ang University), Ganesh Sundaramoorthi (KAUST)
Dense Semantic Image Segmentation with Objects and Attributes ( bibtex, project, PDF): Shuai Zheng ( University of Oxford), Ming-Ming Cheng ( University of Oxford), Jonathan Warrell, Paul Sturgess, Vibhav Vineet, Carsten Rother ( TU Dresden), Philip H. S. Torr ( University of Oxford)
Learning Non-Linear Reconstruction Models for Image Set Classification: Munawar Hayat* (UWA), mohammed Bennamoun (The University of Western Australia), Senjian An (University of Western Australia)
Depth and Skeleton Associated Action Recognition without Online Accessible RGB-D Cameras ( PDF): Yen-Yu Lin* (Academia Sinica), Ju-Hsuan Hua (Carnegie Mellon University), Nick Tang (Academia Sinica), Min-Hung Chen (Academia Sinica), Hong-Yuan Liao (Academia Sinica)
Subspace Tracking under Dynamic Dimensionality for Online Background Subtraction: Matthew Berger* (Air Force Research Laboratory), Lee Seversky (Air Force Research Laboratory)
Adaptive Object Retrieval with Kernel Reconstructive Hashing: Haichuan Yang* (Beihang University), Xiao Bai (Beihang University), Jun Zhou (Griffith University), Peng Ren (China University of Petroleum), Jian Cheng (Chinese Academy of Sciences), Zhihong Zhang (Xiamen University)
Learning Inhomogeneous FRAME Models for Object Patterns ( PDF): Jianwen Xie (UCLA), Wenze Hu (Google Inc.), Song Chun Zhu (UCLA), Ying Nian Wu* (UCLA)
Automatic Feature Learning for Robust Shadow Detection: Salman Khan* (The University of Western Australia), mohammed Bennamoun (The University of Western Australia), Ferdous Sohel (The University of Western Australia), Roberto Togneri (UWA)
In Search of Inliers: 3D Correspondence by Local and Global Voting: Anders Buch* (University of Southern Denmark), Yang Yang , Norbert KrÃƒÂ¼ger , Henrik Petersen
Probabilistic Labeling Cost for High-Accuracy Multi-view Reconstruction: Ilya Kostrikov (RWTH Aachen University), Esther Horbert (RWTH Aachen), Bastian Leibe*
Unified Face Analysis by Iterative Multi-Output Random Forests ( PDF): Xiaowei Zhao* (Imperial College London), Tae-Kyun Kim (Imperial College London), Wenhan Luo (Imperial College London)
SphereFlow: 6 DoF Scene Flow from RGB-D Pairs ( PDF, supplementary material, videos): Michael Hornacek* (TU Vienna), Andrew Fitzgibbon (Microsoft Research Cambridge), Carsten Rother (TU Dresden)
Partial Occlusion Handling for Visual Tracking via Robust Part Matching: Tianzhu Zhang* (ADSC Singapore), Kui Jia , Changsheng Xu , Yi Ma (Microsoft), Narendra Ahuja (University of Illinois at Urbana-Champaign)
Finding Matches in a Haystack: A Max-Pooling Strategy for Graph Matching in the Presence of Outliers: Minsu Cho* , Jian Sun (Inria), Jean Ponce (Ecole Normale Superieure)
Histograms of Pattern Sets for Image Classification and Object Recognition: Winn Voravuthikunchai* (University of Caen), bruno Cremilleux (Greyc University of Caen), Frederic Jurie (University of Caen)
Robust 3D Tracking with Descriptor Fields ( PDF, supplementary material): Alberto Crivellaro* (EPFL), Vincent Lepetit (EPFL)
Using a deformation field model for localizing faces and facial points under weak supervision: Marco Pedersoli* , Tinne Tuytelaars (KU Leuven), Luc Van Gool (ETH)
Seeing What You're Told: Sentence-Guided Activity Recognition In Video: Siddharth Narayanaswamy* (Purdue University), Andrei Barbu (Purdue University), Jeffrey Siskind (Purdue University)
Decomposable Nonlocal Tensor Dictionary Learning for Multispectral Image Denoising ( PDF, supplementary material): Yi Peng (Xi\'an Jiaotong University), Deyu Meng* (Xi\'an Jiao Tong University), Zongben Xu (Xi\'an Jiaotong University), Chenqiang Gao (Carnegie Mellon University), Yang Yi (The University of Queensland), Biao Zhang (Xi\'an Jiaotong University)
Class Specific 3D Object Shape Priors Using Surface Normals ( PDF, supplementary material): Christian Haene (ETH Zuerich), Nikolay Savinov (ETH Zuerich), Marc Pollefeys (ETH)
Human Shape and Pose Tracking Using Keyframes: Chun-Hao Huang* (Technische UniversitÃƒÂ¤t MÃƒÂ¼nchen), Edmond Boyer (INRIA), Slobodan Ilic
Speeding Up Tracking by Ignoring Features ( PDF): Lu Zhang* (Delft University of Technology), Hamdi Dibeklioglu (TUDelft), Laurens van der Maaten (TUDelft)
A Bayesian Framework For the Local Configuration of Retinal Junctions: Touseef Qureshi* (University of Lincoln , UK), Andrew Hunter (University of Lincoln , United Kingdom), Bashir Al-Diri (The University of Lincoln)
Fast, Approximate Piecewise-Planar Modeling Based on Sparse Structure-from-Motion and Dense Superpixels: Andras Bodis-Szomoru* (Computer Vision Lab , ETH Zurich), Hayko Riemenschneider (ETH), Luc Van Gool (ETH)
Linear Ranking Analysis: Deng Weihong* (sice.bupt.edu), Jiani Hu , Jun Guo
A Principled Approach for Coarse-to-Fine MAP Inference: Christopher Zach* (MSR Cambridge)
Accurate Object Detection with Joint Classification-Regression Random Forests - formely: Structured Output Random Forests for Accurate Object Detection: Samuel Schulter (Graz University of Technology), Christian Leistner (Microsoft Photogrammetry, Austria), Paul Wohlhart (Graz University of Technology), Peter M. Roth (Graz University of Technology), Horst Bischof (Graz University of Technology)
Geometric Urban Geo-Localization: Mayank Bansal* (University of Pennsylvania), Kostas Daniilidis (University of Pennsylvania)
Semi-supervised Spectral Clustering for Image Set Classification: Arif Mahmood* (UWA), Ajmal Mian , Robyn Owens (UWA)
Posebits for Monocular Pose Estimation: Gerard Pons-Moll* (Max Planck Institute), Bodo Rosenhahn , David Fleet (University of Toronto)
On Projective Reconstruction In Arbitrary Dimensions: Behrooz Nasihatkon* (Australian National University), Richard Hartley (Australian National University), Jochen Trumpf (Australian National University)
An Online Learned Elementary Grouping Model for Multi-target Tracking ( PDF): Xiaojing Chen* (University of California , Riverside), Zhen Qin (UC-Riverside), Le An (Univ of California , Riverside), Bir Bhanu
Efficient Structured Parsing of Facades Using Dynamic Programming ( PDF): Andrea Cohen* (ETH), Alexander Schwing (ETH), Marc Pollefeys (ETH)
Simultaneous Twin Kernel Learning for Structured Prediction: Chetan Tonde* (Rutgers University), Ahmed Elgammal (Rutgers)
Fast and Exact: Shape Segmentation Using ADMM and Structured Prediction: Haithem Boussaid* (ecole centrale paris , inria saclay), Iasonas Kokkinos (Ecole Central de Paris)
Word Channel Based Multiscale Pedestrian Detection Without Image Resizing and Using Only One Classifier: Arthur Costea* (TUCN), Sergiu Nedevschi (TUCN)
Spectral Clustering with Jensen-type kernels and their multi-point extensions: Debarghya Ghoshdastidar* (Indian Institute of Science), Ambedkar Dukkipati (Indian Institute of Science), Ajay Adsul (Indian Institute of Science), Aparna Vijayan (Indian Institute of Science)
Evolutionary Quasi-random Search for Hand Articulations Tracking ( videos, project): Iason Oikonomidis* (CSD, Univ. of Crete and Institute of Comp. Science, FORTH), Manolis I.A. Lourakis (Institute of Comp. Science, FORTH), Antonis Argyros (CSD, Univ. of Crete and Institute of Comp. Science, FORTH)
Seeing the Arrow of Time ( PDF): Lyndsey Pickup* (University of Oxford), Zheng Pan (Tsinghua University), Donglai Wei (CSAIL , MIT), Yichang Shih (CSAIL , MIT), Andrew Zisserman (Oxford), Bill Freeman (MIT), Bernhard Schoelkopf (Max Planck Institute Tuebingen)
Actionness Ranking with Lattice Conditional Ordinal Random Fields: Wei Chen (SUNY at Buffalo), Caimgin Xiong (SUNY at Buffalo), Jason Corso* (Buffalo)
Gauss-Newton Deformable Part Models for Face Alignment in-the-Wild - formely: Gauss-Newton Constrained Local Models: Georgios Tzimiropoulos* (Imperial College London), Maja Pantic
Incremental Face Alignment in the Wild ( videos): Akshay Asthana* (Imperial College London), Stefanos Zafeiriou (Imperial College London), Shiyang Cheng (Imperial College London), Maja Pantic
Hierarchical Feature Hashing for Fast Dimensionality Reduction ( PDF): Bin Zhao* (CMU)
Geometric Generative Gaze Estimation (G3E) for Remote RGB-D Cameras: Kenneth Funes Mora* (Idiap Research Institute / EPFL), Jean-Marc Odobez (Idiap Research Institute/EPFL)
Efficient feature extraction, encoding and classification\\ for action recognition: Vadim Kantorov* (INRIA), Ivan Laptev
Tissue Classification via Multispectral Convolutional Sparse Coding: Yin Zhou (ECE Department , University of Delaware), Hang Chang* (Lawrence Berkeley National Lab), Kenneth Barner (ECE Department , University of Delaware), Paul Spellman (Oregon Health Sciences University), Bahram Parvin (Lawrence Berkeley National Lab)
Nonparametric Part Transfer for Fine-grained Recognition ( PDF,project): Christoph GÃ¶ring (FSU Jena), Erik Rodner* ( FSU Jena), Alexander Freytag ( FSU Jena), Joachim Denzler ( FSU Jena)
On the quotient representation for the essential manifold: Roberto Tron* (University of Pennsylvania), Kostas Daniilidis (University of Pennsylvania)
Topic Modeling of Multimodal Data: an Autoregressive Approach: Yin Zheng* (Tsinghua University), Yu-Jin Zhang , Hugo Larochelle (UniversitÃƒÂ© de Sherbrooke)
What are you talking about? Text-to-Image Co-reference: Chen Kong (Tsinghua University), Sanja Fidler* (Toyota Technnological Institute), Mohit Bansal (TTI-C), Dahua Lin (Toyota Technnological Institute), Raquel Urtasun (University of Toronto)
Curvilinear Structure Tracking by Low Rank Tensor Approximation with Model Propagation: Erkang Cheng* (Temple University), Yu Pang (Temple University), Ying Zhu (Siemens), Haibin Ling (Temple University)
A Study on Cross-Population Age Estimation: Chao Zhang (West Virginia University), Guodong Guo*
Edge-aware Gradient Domain Optimization Framework for Image Filtering by Local Propagation: Miao Hua* (Institute of Software , Chinese Academy of Sciences), Xiaohui Bie , Wencheng Wang
Visual Semantic Search: Retrieving Videos via Complex Textual Queries: Dahua Lin* (Toyota Technnological Institute), Sanja Fidler (Toyota Technnological Institute), Chen Kong (Tsinghua University), Raquel Urtasun (University of Toronto)
Unsupervised Trajectory Modelling using Temporal Information via Minimal Paths: Brais Cancela* (University of A Coruna), Alberto Iglesias (University of A CoruÃƒÂ±a), Marcos Ortega (University of A CoruÃƒÂ±a), Manuel Penedo (University of A CoruÃƒÂ±a)
Incremental Activity Modeling and Recognition in Streaming Videos: MAHMUDUL HASAN* (UCR), Amit Roy-Chowdhury
Multi-Forest Tracker: A Chameleon in Tracking: DAVID JOSEPH TAN* (TUM), Slobodan Ilic
Reliable Multi-view Stereopsis Evaluation: Anders Dahl* (Technical University of Denmar), Henrik AanÃƒÂ¦s (Technical University of Denmark), Rasmus Jensen (Technical University of Denmark), George Vogiatzis (Aston University), Engin Tola (Aurvis Ltd, Ankara, Turkey)
Understanding Objects in Detail with Fine-grained Attributes ( PDF): Subhransu Maji (Toyota Technnological Institute), Iasonas Kokkinos (Ecole Central de Paris), Stavros Tsogkas (Ecole Centrale Paris), Ross Girshick (UCB), Matthew Blaschko (ECP), Esa Rahtu (University of Oulu), Juho Kannala (University of Oulu), Andrea Vedaldi* (Oxford University)
Efficient Hierarchical Graph-Based Segmentation of RBGD Videos: Steven Hickson* (Georgia Institute of Technolog), Irfan Essa (Georgia Institute of Technology), Henrik Christensen (Georgia Institute of Technology), Stan Birchfield (Clemson University)
Iterative Multilevel MRF Leveraging Context and Voxel Information for Brain Tumour Segmentation in MRI: Nagesh Subbanna* (McGill University), Doina Precup (McGill University), Tal Arbel (McGill Univ)
Stable Template-Based Isometric 3D Reconstruction in All Imaging Conditions by Linear Least-Squares: Ajad Chhatkuli* (ALCoV-ISIT), Daniel Pizarro , Adrien Bartoli (Universite d'Auvergne), Toby Collins (ALCoV-ISIT)
Zero-shot Event Detection using Multi-modal Fusion of Weakly Supervised Concepts: Shuang Wu (Raytheon BBN Technologies), Florian Luisier (Raytheon BBN Technologies), Sravanthi Bondugula (University of Maryland), Pradeep Natarajan* (Raytheon BBN Technologies)
Merging SVMs with Linear Discriminant Analysis: A Combined Model: Symeon Nikitidis* (Imperial College London), Stefanos Zafeiriou (Imperial College London), Maja Pantic
Dual Linear Regression Based Classification for Face Cluster Recognition: Liang Chen* (Uni. of N. British Columbia)
Transitive Distance Clustering with K-Means Duality: Zhiding Yu* (Carnegie Mellon University), Chunjing Xu (Huawei Technologies Co. Ltd.), Deyu Meng (Xi'an Jiao Tong University), Zhuo Hui (Carnegie Mellon University), Fanyi Xiao (Carnegie Mellon University), Wenbo Liu
Learning Receptive Fields for Pooling from Tensors of Feature Response: Can Xu* (UC San Diego), Nuno Vasconcelos (UC San Diego)
Generalized Pupil-Centric Imaging and Analytical Calibration for a Non-frontal Camera ( PDF): Avinash Kumar* (University of Illinois at Urbana-Champaign), Narendra Ahuja (University of Illinois at Urbana-Champaign)
Confidence-Rated Multiple Instance Boosting for Object Detection: Karim Ali* (University of California Berkeley , UML), Kate Saenko (UML)
6 Seconds of Sound and Vision: Creativity in Micro-Videos ( dataset, PDF): Miriam Redi* (Yahoo!), Neil O\'Hare (Yahoo!), Rossano Schifanella (University of Turin), Michele Trevisiol (UPF & Yahoo!), Alejandro Jaimes (Yahoo!)
RAPS: Robust and Efficient Automatic Construction of Person-Specific Deformable Models: Christos Sagonas (Imperial College London), Stefanos Zafeiriou* (Imperial College London), Yannis Panagakis (Imperial College London), Maja Pantic
Persistence-based Object Recognition: Frederic Chazal* (INRIA), MAksim Ovsjanikov (Ecole Polytechnique), Chunyuan Li (Concordia University)
Region-based particle filter for video object segmentation: David Varas* (UPC), Ferran Marques (UPC)
Fast and robust identification of persistent homotopy types of noisy images: Vitaliy Kurlin* (Durham University)
Learning optimal features for salient object detection ( PDF, supplementary material): Song Lu* (SVCL lab , UCSD), Vijay Mahadevan (Yahoo), Nuno Vasconcelos (UC San Diego)
Fast and Reliable Two-View Translation Estimation: Johan Fredriksson* (Matematikcentrum lund), Olof Enqvist , Fredrik Kahl (Lund University)
Single Image Super-resolution using Deformable Patches ( PDF): Yu Zhu* (School of CS , NPU), Yanning Zhang (School of CS , NPU), Alan Yuille (University of California at Los Angeles)
Learning to Group Objects: Victoria Yanulevskaya* (University of Trento), Jasper Uijlings (University of Trento), Nicu Sebe (University of Trento)
Enriching Visual Knowledge Bases via Object Discovery and Segmentation ( PDF, project) - formely: Object Discovery and Segmentation via Discriminative Visual Subcategories: Xinlei Chen (Carnegie Mellon University), Abhinav Shrivastava (Carnegie Mellon University), Abhinav Gupta (Carnegie Mellon University)
Better Shading for Better Shape Recovery: Moumen El-Melegy* (Assiut University)
Human Pose Estimation: New Benchmark and State of the Art Analysis: Leonid Pishchulin* (Max Planck Institute for Infor), Mykhaylo Andriluka (Max Planck Institute), Peter Gehler (MPI Intelligent Systems), Bernt Schiele (Max Planck Institute)
Automatic Construction of Deformable Models In-The-Wild: Epameinondas Antonakos* (Imperial College London), Stefanos Zafeiriou (Imperial College London)
Scalable Object Detection using Deep Neural Networks ( PDF): Dumitru Erhan* (Google), Christian Szegedy, Alexander Toshev (Google), Dragomir Anguelov (Google)
The Photometry of Intrinsic Images: Marc Serra* (UAB - CVC), Robert Benavente (UAB , CVC), Maria Vanrell (UAB , CVC), Dimitris Samaras (SBU), Olivier Penacchio (UAB , CVC)
Scalable Multitask Representation Learning for Scene Classification: Maksim Lapin* (MPI Informatics), Matthias Hein , Bernt Schiele (Max Planck Institute)
Incorporating Scene Context and Object Layout into Appearance Modeling: Hamid Izadinia (University of Washington), Fereshteh Sadeghi* (University of Washington), Ali Farhadi (University of Washington)
Instance-weighted Transfer Learning of Active Appearance Models: Daniel Haase (FSU Jena), Erik Rodner* , Joachim Denzler (FSU Jena)
RIGOR: Recycling Inference in Graph Cuts for generating Object Regions ( project, PDF) - formely: FastSeg: More Efficiency on Multiple Figure-Ground Segmentations: Ahmad Humayun* (Georgia Institute of Technology), Fuxin Li (Georgia Institute of Technology), James M. Rehg (Georgia Institute of Technology)
Random Laplace Feature Maps for Semigroup Kernels on Histograms: Jiyan Yang* (Stanford University), Vikas Sindhwani (IBM Research Center), Quanfu Fan (IBM), Haim Avron (Thomas J. Watson Research Center), Michael Mahoney (Stanford University)
Laplacian Coordinates for Seeded Image Segmentation: Wallace Casaca* (Brown University / USP), Gustavo Nonato (ICMC-USP), Gabriel Taubin (Brown University)
Quality Dynamic Human Body Modeling Using a Single Low-cost Depth Camera: Qing Zhang* (University of Kentucky), BO FU (University of Kentucky)
A Reverse Hierarchy Model for Predicting Eye Fixations ( PDF): Tianlin Shi (Tsinghua University), Ming Liang (Tsinghua University), Xiaolin Hu* (Tsinghua University)
A Novel Chamfer Template Matching Method Using Variational Mean Field: Thanh Nguyen*
Efficient Pruning LMI Conditions for Branch-and-Prune Rank and Chirality-Constrained Estimation of the Dual Absolute Quadric - formely: Efficient pruning LMI conditions for Branch-and-Prune Rank and Chirallity-Constrained Estimation of the Dual Absolute Quadric: Adlane Habed* (University of Strasbourg), Danda Pani Paudel (University of Bourgogne), CÃ©dric Demonceaux (University of Bourgogne), David Fofi (University of Bourgogne)

你可能感兴趣的:(机器学习,computer,vision)

具身智能的视觉-语言导航综述
24年2月来自曲阜师范、华东师大和哈工大的论文“Vision-LanguageNavigationwithEmbodiedIntelligence:ASurvey”。作为人工智能领域的长期愿景，具身智能的核心目标是提升智体与环境的感知、理解和交互能力。视觉-语言导航（VLN）作为实现具身智能的重要研究路径，致力于探索智体如何利用自然语言与人进行有效沟通，接收并理解指令，并最终依靠视觉信息实现精准导
开源模型应用落地-qwen模型小试-Qwen2.5-7B-Instruct-玩转ollama（一）开源技术探险家开源模型-实际应用落地 #深度学习自然语言处理语言模型
一、前言在AI大模型百花齐放的时代，很多人都对新兴技术充满了热情，都想尝试一下。然而，实际上要入门AI技术的门槛非常高。除了需要高端设备，还需要面临复杂的部署和安装过程，这让很多人望而却步。在这样的背景下，Ollama的出现为广大开发者和爱好者提供了一条便捷的道路，极大地降低了应用机器学习的门槛。Ollama的优势在于其极致的简化。通过这个平台，用户可以轻松下载、运行和管理各种机器学习模型，而无需
机器学习之——认识机器学习 -睡到自然醒~ golang 重构开发语言
首先，什么是机器学习？参照百度百科的讲解，“机器学习是一门多领域交叉学科，设计概率论、统计学、逼近论、凸分析、算法复杂度理论等多门学科。专门研究计算机怎样模拟或实现人类的学习能力，以获取新的知识或技能，重新组织已有的知识结构使之不断改善自身的性能。”什么意思呢？也就是说，机器学习是一门跨领域的学科，是一种能够让机器模仿人类学习能力的一种学科。在Andrew的课程中，提到了几个机器学习的定义：1，A
Epoch 老兵发新帖人工智能
在深度学习和机器学习中，Epoch（轮次或周期）是一个核心训练概念，指模型在整个训练数据集上完成一次完整遍历的过程。以下是关于Epoch的详细解析：一、核心定义基本含义Epoch表示模型将所有训练数据完整学习一次的过程。例如：若训练集有10,000个样本，则1个Epoch即模型用这10,000个样本训练一轮。与相关概念的关系Batch（批次）：数据集被分割成的小组（如每批32个样本）。Iterat
Python --- day 10 Opencv模块的使用 AnAn__kang python opencv 开发语言
系列文章目录前言今天博主带大家进入Opencv的学习，这是一个专门针对处理图像和视频的一个模块，大家以理解为主，增强自己的编程思维，再后续我们训练模型时会大批量的处理图片时会经常用到这个模块。1OpenCV介绍OpenCV（开放源代码计算机视觉库）是一个开源的计算机视觉和机器学习软件库。由一系列C++类和函数构成，用于图像处理、计算机视觉领域的算法实现。1.1OpenCV优势**开源免费：**完全
深度学习图像分类数据集—百种病虫害分类 AI街潜水的八角深度学习图像数据集深度学习分类人工智能
该数据集为图像分类数据集，适用于ResNet、VGG等卷积神经网络，SENet、CBAM等注意力机制相关算法，VisionTransformer等Transformer相关算法。数据集信息介绍：百种病虫害识别分类，训练集45095张，验证集7508张，测试集22619张具体类别为以下：insect_classes=["rice_leaf_roller","rice_leaf_caterpillar
机器学习数据预处理阶段为什么需要——归一化处理
参考：https://www.cnblogs.com/bjwu/p/8977141.html通常，在DataScience中，预处理数据有一个很关键的步骤就是数据的标准化。这里主要引用sklearn文档中的一些东西来说明，主要把各个标准化方法的应用场景以及优缺点总结概括，以来充当笔记。提升模型精度在机器学习算法的目标函数(例如SVM的RBF内核或线性模型的l1和l2正则化)，许多学习算法中目标函数
车辆云端威胁情报共享系统的多维解析与发展路径百态老人大数据人工智能
第一部分：内容本质提取原始内容描述了一个闭环网络安全体系：“车辆实时上传异常行为日志至安全运营中心（VSOC），云端通过机器学习分析攻击模式并下发全局防御策略”。其核心架构包含：数据采集层：车辆端持续收集异常行为日志数据，包含CAN总线通信模式、网络流量特征及驾驶行为数据传输层：通过V2X通信协议和OTA更新通道实现车云双向通信分析层：安全运营中心(VSOC)采用CNN-BiSRU等深度学习模型进
过拟合、欠拟合及其解决方案；梯度消失、梯度爆炸；循环神经网络进阶 Ryan_sz1
1、过拟合、欠拟合及其解决方案过拟合、欠拟合机器学习或者训练深度神经网络的时候经常会出现欠拟合和过拟合这两个问题，但是，一开始我们的模型往往是欠拟合的，也正是因为如此才有了优化的空间，我们需要不断的调整算法来使得模型的表达能拿更强。但是优化到了一定程度就需要解决过拟合的问题了。也就是说欠拟合是模型表达能力不够，达不到很好的表达效果。而过拟合是在训练集的范围内表达能力过强，导致完全拟合了训练集。解决
数字人系统：AI界的超级巨星，你准备好了吗？优秘智能UMI 数字人人工智能深度学习计算机视觉机器学习自然语言处理语言模型图像处理
在这个日新月异的科技时代，每一个创新的火花都可能点燃一场变革的燎原之火。今天，我们要聊的，正是那颗在AI领域熠熠生辉的璀璨新星——优秘数字人系统。它不仅仅是技术的飞跃，更是对未来生活方式的深刻重塑，一场关于人机交互、智能共生的美好预演。技术原理：深度解析与智能构建的奥秘1.深度学习：智能的基石数字人系统的核心技术之一在于深度学习。深度学习是一种模仿人脑神经网络结构和功能的机器学习技术，通过构建多层
聚焦基础研究突破，北电数智联合复旦大学等团队提出“AI安全”DDPA方法入选ICML CSDN资讯人工智能安全数据要素大数据
近日，由北电数智首席科学家窦德景教授牵头，联合复旦大学和美国奥本大学等科研团队共同研发，提出一种DDPA（DynamicDelayedPoisoningAttack）新型对抗性攻击方法，为机器学习领域的安全研究提供新视角与工具，相关论文已被国际机器学习大会（ICML2025）收录。ICML由国际机器学习学会（IMLS）主办，聚焦深度学习、强化学习、自然语言处理等机器学习前沿方向，是机器学习与人工智
格灵深瞳视觉算法面试30问全景精解机＿长算法面试职场和发展
格灵深瞳视觉算法面试30问全景精解——AI感知×智能安防×场景创新：格灵深瞳视觉算法面试核心考点全览前言格灵深瞳（GREATVISION）作为国内领先的人工智能与计算机视觉企业，专注于智慧安防、智能交通、智慧零售等领域，推动视觉算法在大规模城市级场景的落地。格灵深瞳视觉算法岗位面试不仅考察候选人对视觉基础理论的扎实掌握，更关注其在复杂场景下的创新能力与工程实践。本文精选30个高质量面试问题，涵盖基
阿里云态势感知和安骑士有什么区别？阿腾云
阿里云态势感知和安骑士均是阿里云云盾安全产品，态势感知属于安全管理类的产品，安骑士数据服务器安全类产品，阿里云百科网来详细说下阿里云态势感知和安骑士之间的区别：态势感知和安骑士的区别简单来说，安骑士是检测云服务器漏洞的，态势感知提供安全类的大数据分析服务。态势感知：安全大数据分析平台，通过机器学习和结合全网威胁情报，发现传统防御软件无法覆盖的网络威胁，溯源攻击手段、并且提供可行动的解决方案。安骑士
「日拱一码」035 机器学习——调参过程可视化胖达不服输「日拱一码」机器学习人工智能调参过程可视化神经网络 python 模型可解释性
目录超参数搜索的3D曲面可视化交互式3D可视化神经网络学习率的3D可视化SVM超参数的3D决策边界可视化超参数优化的3D动画超参数搜索的3D曲面可视化##超参数搜索的3D曲面可视化importnumpyasnpimportmatplotlib.pyplotaspltfrommpl_toolkits.mplot3dimportAxes3Dfromsklearn.datasetsimportmake_
数据质量是机器学习项目的核心痛点，AI技术能提供智能化解决方案。 zzywxc787 python pandas numpy 人工智能自动化运维 AI编程
一、数据质量诊断系统（Python实现）importpandasaspdimportnumpyasnpimportmatplotlib.pyplotaspltfromsklearn.clusterimportKMeansfromsklearn.ensembleimportIsolationForestfromtensorflow.keras.modelsimportSequentialfromte
喷丝板检测软件上位机开发深圳市由你创科技上位机开发 c#qt
一、核心功能模块1、硬件控制运动控制：通过Modbus/RS485/EtherCAT控制高精度电移台（需±1μm精度），实现喷丝板XY轴扫描定位。光源控制：调节环形LED/同轴光源亮度（支持PWM或0-10V模拟信号），优化成像对比度。相机控制：支持GigE/USB3Vision相机（建议500万像素以上），触发采集、参数调节（曝光/增益）。2、机器视觉检测孔洞识别：使用OpenCV的HoughC
7.机器学习-十大算法之一拉索回归（Lasso）算法原理讲解以山河作礼。 #机器学习算法机器学习算法回归
7.机器学习-十大算法之一拉索回归（Lasso）算法原理讲解一·摘要二·个人简介三·前言四·原理讲解五·算法流程六·代码实现6.1坐标下降法6.2最小角回归法七·第三方库实现7.1scikit-learn实现（坐标下降法）：7.2scikit-learn实现（最小角回归法）：一·摘要拉索回归（LassoRegression）是一种线性回归的正则化形式，它通过引入L1范数惩罚项来实现模型的稀疏性，从
机器学习算法之回归算法福葫芦机器学习回归算法
一、回归算法思维导图二、算法概念、原理、应用场景和实例代码1、线性回归1.1、概念‌‌线性回归算法是一种统计分析方法，用于确定两种或两种以上变量之间的定量关系。‌线性回归算法通过建立线性方程来预测因变量（y）和一个或多个自变量（x）之间的关系。其基本形式为y=wx+e，其中w是权重，x是自变量，e是误差项。1.2、算法原理线性回归算法的核心在于找到最佳的拟合直线，使得预测值与实际值之间的误差最小。
7篇1章7节：机器学习算法解读，与数值预测回归模型构建 MD分析用R探索医药数据科学机器学习算法回归 r语言数据挖掘
机器学习是当今数据分析和人工智能的核心工具之一，其算法广泛应用于分类、回归、排序和推荐等领域。本篇将详细讲解机器学习的四大经典算法类型，并以回归问题为例深入探讨数值预测的关键步骤，包括数据准备、线性回归模型构建、模型预测及误差评估，帮助读者更系统地理解和掌握机器学习的基础知识及实际应用。一、机器学习的算法在数据科学和人工智能的浪潮中，机器学习算法成为了解决各种数据问题的关键工具。机器学习主要处理四
PyTorch图像分类系列——流程概览 VAMOT PyTorch图像分类系列 pytorch 深度学习分类计算机视觉
一、加载数据1.使用torchvision.datasets的方法加载经典数据集在此网址查看支持哪些经典数据集：Datasets—Torchvision0.18documentation(pytorch.org)data_train=torchvision.datasets.CIFAR10(root="CIFAR10",train=True,transform=ToTensor(),target_
Pytorch图像二分类代码 AlexNet 望舒向晚 Pytorch pytorch 深度学习机器学习
importtorchimporttorch.nnasnnimporttorch.optimasoptimimporttorch.utils.dataimporttorch.nn.functionalasFimporttorchvisionfromtorchvisionimporttransformsfromPILimportImagedefcheck_image(path):try:im=Ima
基于逻辑回归的图像二分类算法实现（Pytorch版）哎呦哥哥、图像分类 pytorch 逻辑回归分类
基于逻辑回归的图像二分类算法实现（Pytorch版）数据集模型代码数据集链接：FastFoodClassificationDataset我们只使用Burger和Pizza这两类。模型代码importtorchimporttorch.nnasnnfromtorchvision.models.utilsimportload_state_dict_from_urlmodel_urls={'resnet5
计算机视觉：人工智能的“眼睛” 人工智能教程人工智能计算机视觉机器学习算法 pytorch python 数据结构
前言在人工智能的众多领域中，计算机视觉（ComputerVision）无疑是其中最为引人注目的方向之一。它赋予了机器“看”的能力，使计算机能够像人类一样理解和解释视觉信息。从自动驾驶汽车到医疗影像诊断，从安防监控到虚拟现实，计算机视觉的应用场景无处不在，深刻地改变着我们的生活和工作方式。本文将深入探讨计算机视觉的核心技术、应用场景以及未来的发展趋势，帮助您全面了解这一充满活力的领域。一、计算机视觉
支持向量机SVM 李昊哲小课 sklearn 人工智能机器学习支持向量机算法机器学习 sklearn 人工智能数据挖掘
支持向量机SVM一、支持向量机算法支持向量机（SupportVectorMachine，SVM）是一种用于分类和回归分析的机器学习算法。分类场景举例（更容易理解）假设现在有一个二维平面上散落着一些点，这些点分为两类，一类是红色的圆形点，另一类是蓝色的方形点。我们的任务就是找到一条直线，能够把这两类点尽可能准确地分开。支持向量机算法做的事情就和这个类似。算法核心思想它不是随便找一条能分开两类数据的直
高斯混合模型（GMM）中的协方差矩阵类型与聚类形状关系详解码字的字节机器学习机器学习人工智能高斯混合模型 GMM
高斯混合模型（GMM）简介高斯混合模型（GaussianMixtureModel,GMM）是概率统计与机器学习交叉领域的重要模型，其核心思想是通过多个高斯分布的线性组合来描述复杂数据分布。与单一高斯分布不同，GMM能够捕捉数据中的多模态特性，这使得它在处理真实世界非均匀分布数据时展现出独特优势。从数学形式上看，一个包含K个分量的GMM可表示为：其中(\pi_k)是第k个高斯分量的混合系数（满足(\
OpenCV引擎：驱动实时应用开发的科技狂飙芯作者 DD：计算机科学领域 opencv 计算机视觉
在人工智能与计算机视觉技术迅猛发展的今天，实时图像处理已成为工业自动化、自动驾驶、医疗诊断、增强现实等领域的核心技术需求。而**OpenCV（OpenSourceComputerVisionLibrary）**作为全球最活跃的开源计算机视觉库，正以其强大的算法生态、跨平台兼容性以及持续进化的架构设计，成为驱动实时应用开发的“数字引擎”。本文将深入剖析OpenCV如何通过技术创新突破实时处理的性能极
机器学习初学者理论初解 Mikhail_G 机器学习人工智能
大家好!为什么手机相册能自动识别人脸？为什么购物网站总能推荐你喜欢的商品？这些“智能”背后，都藏着一位隐形高手——机器学习（MachineLearning）。一、什么是机器学习？简单说，机器学习是教计算机从数据中自己找规律的技术。就像教孩子认猫：不是直接告诉他“猫有尖耳朵和胡须”，而是给他看100张猫狗照片，让他自己总结出猫的特征。传统程序vs机器学习传统程序：输入规则+数据→输出结果（例：按“温
Embedding与向量数据库玖月初玖大模型应用开发基础人工智能 embedding 数据库
1.Embedding是什么EmbeddingModel是一种机器学习模型，它的核心任务是将离散的、高维的符号（如单词、句子、图片、用户、商品等）转换成连续的、低维的向量（称为“嵌入”或“向量表示”），并且这个向量能有效地捕捉原始符号的语义、关系或特征。1.1通俗理解EmbeddingModel是让计算机“理解”世界的核心工具，把“文字、图片、音频”等信息变成一串有意义的数字我们称之为“向量”。类
2023年第10期(NeuroImage)：DomainATM：多中心医学图像数据标准化工具箱影浮科技ImageFlow
基本信息1.标题：DomainATM:Domainadaptationtoolboxformedicaldataanalysis.2.期刊：NeuroImage3.IF/JCR/分区：7.4/Q1/中科院一区4.DOI：10.1016/j.neuroimage.2023.119863目录1、导读2、背景动机3、研究目的4、工具箱介绍5、测试试验6、局限不足1导读域适应（DA）是基于机器学习的现代医
在NLP深层语义分析中，深度学习和机器学习的区别与联系
在自然语言处理（NLP）的深层语义分析任务中，深度学习与机器学习的区别和联系主要体现在以下方面：一、核心区别特征提取方式机器学习：依赖人工设计特征（如词频、句法规则、TF-IDF等），需要领域专家对文本进行结构化处理。例如，传统情感分析需人工定义“情感词库”或通过词性标注提取关键成分。深度学习：通过神经网络自动学习多层次特征。例如，BERT等模型可从原始文本中捕获词向量、句法关系甚至篇章级语义，无
遍历dom 并且存储（将每一层的DOM元素存在数组中）换个号韩国红果果 JavaScript html
数组从0开始！！ var a=[],i=0; for(var j=0;j<30;j++){ a[j]=[];//数组里套数组，且第i层存储在第a[i]中 } function walkDOM(n){ do{ if(n.nodeType!==3)//筛选去除#text类型 a[i].push(n); //con
Android+Jquery Mobile学习系列(9)-总结和代码分享白糖_ JQuery Mobile
目录导航经过一个多月的边学习边练手，学会了Android基于Web开发的毛皮，其实开发过程中用Android原生API不是很多，更多的是HTML/Javascript/Css。个人觉得基于WebView的Jquery Mobile开发有以下优点： 1、对于刚从Java Web转型过来的同学非常适合，只要懂得HTML开发就可以上手做事。 2、jquerym
impala参考资料 dayutianfei impala
记录一些有用的Impala资料 1. 入门资料 >>官网翻译： http://my.oschina.net/weiqingbin/blog?catalog=423691 2. 实用进阶 >>代码&架构分析： Impala/Hive现状分析与前景展望：http
JAVA 静态变量与非静态变量初始化顺序之新解周凡杨 java 静态非静态顺序
今天和同事争论一问题，关于静态变量与非静态变量的初始化顺序，谁先谁后，最终想整理出来！测试代码： import java.util.Map; public class T { public static T t = new T(); private Map map = new HashMap(); public T(){ System.out.println(&quo
跳出iframe返回外层页面 g21121 iframe
在web开发过程中难免要用到iframe，但当连接超时或跳转到公共页面时就会出现超时页面显示在iframe中，这时我们就需要跳出这个iframe到达一个公共页面去。首先跳转到一个中间页，这个页面用于判断是否在iframe中，在页面加载的过程中调用如下代码： <script type="text/javascript"> //<!-- function
JAVA多线程监听JMS、MQ队列 510888780 java多线程
背景：消息队列中有非常多的消息需要处理，并且监听器onMessage（）方法中的业务逻辑也相对比较复杂，为了加快队列消息的读取、处理速度。可以通过加快读取速度和加快处理速度来考虑。因此从这两个方面都使用多线程来处理。对于消息处理的业务处理逻辑用线程池来做。对于加快消息监听读取速度可以使用1.使用多个监听器监听一个队列；2.使用一个监听器开启多线程监听。对于上面提到的方法2使用一个监听器开启多线
第一个SpringMvc例子布衣凌宇 spring mvc
第一步：导入需要的包；第二步：配置web.xml文件 <?xml version="1.0" encoding="UTF-8"?> <web-app version="2.5" xmlns="http://java.sun.com/xml/ns/javaee" xmlns:xsi=
我的spring学习笔记15-容器扩展点之PropertyOverrideConfigurer aijuans Spring3
PropertyOverrideConfigurer类似于PropertyPlaceholderConfigurer，但是与后者相比，前者对于bean属性可以有缺省值或者根本没有值。也就是说如果properties文件中没有某个bean属性的内容，那么将使用上下文（配置的xml文件）中相应定义的值。如果properties文件中有bean属性的内容，那么就用properties文件中的值来代替上下
通过XSD验证XML antlove xml schema xsd validation SchemaFactory
1. XmlValidation.java package xml.validation; import java.io.InputStream; import javax.xml.XMLConstants; import javax.xml.transform.stream.StreamSource; import javax.xml.validation.Schem
文本流与字符集百合不是茶 PrintWrite()的使用字符集名字别名获取
文本数据的输入输出; 输入;数据流,缓冲流输出;介绍向文本打印格式化的输出PrintWrite(); package 文本流; import java.io.FileNotFound
ibatis模糊查询sqlmap-mapping-**.xml配置 bijian1013 ibatis
正常我们写ibatis的sqlmap-mapping-*.xml文件时，传入的参数都用##标识，如下所示： <resultMap id="personInfo" class="com.bijian.study.dto.PersonDTO"> <res
java jvm常用命令工具——jdb命令(The Java Debugger) bijian1013 java jvm jdb
用来对core文件和正在运行的Java进程进行实时地调试，里面包含了丰富的命令帮助您进行调试，它的功能和Sun studio里面所带的dbx非常相似，但 jdb是专门用来针对Java应用程序的。现在应该说日常的开发中很少用到JDB了，因为现在的IDE已经帮我们封装好了，如使用ECLI
【Spring框架二】Spring常用注解之Component、Repository、Service和Controller注解 bit1129 controller
在Spring常用注解第一步部分【Spring框架一】Spring常用注解之Autowired和Resource注解（http://bit1129.iteye.com/blog/2114084）中介绍了Autowired和Resource两个注解的功能，它们用于将依赖根据名称或者类型进行自动的注入，这简化了在XML中，依赖注入部分的XML的编写，但是UserDao和UserService两个bea
cxf wsdl2java生成代码super出错,构造函数不匹配 bitray super
由于过去对于soap协议的cxf接触的不是很多,所以遇到了也是迷糊了一会.后来经过查找资料才得以解决. 初始原因一般是由于jaxws2.2规范和jdk6及以上不兼容导致的.所以要强制降为jaxws2.1进行编译生成.我们需要少量的修改: 我们原来的代码 wsdl2java com.test.xxx -client http://..... 修改后的代
动态页面正文部分中文乱码排障一例 ronin47
公司网站一部分动态页面，早先使用apache+resin的架构运行，考虑到高并发访问下的响应性能问题，在前不久逐步开始用nginx替换掉了apache。不过随后发现了一个问题，随意进入某一有分页的网页，第一页是正常的（因为静态化过了）；点“下一页”，出来的页面两边正常，中间部分的标题、关键字等也正常，唯独每个标题下的正文无法正常显示。因为有做过系统调整，所以第一反应就是新上
java-54- 调整数组顺序使奇数位于偶数前面 bylijinnan java
import java.util.Arrays; import java.util.Random; import ljn.help.Helper; public class OddBeforeEven { /** * Q 54 调整数组顺序使奇数位于偶数前面 * 输入一个整数数组，调整数组中数字的顺序，使得所有奇数位于数组的前半部分，所有偶数位于数组的后半
从100PV到1亿级PV网站架构演变 cfyme 网站架构
一个网站就像一个人，存在一个从小到大的过程。养一个网站和养一个人一样，不同时期需要不同的方法，不同的方法下有共同的原则。本文结合我自已14年网站人的经历记录一些架构演变中的体会。 1：积累是必不可少的架构师不是一天练成的。 1999年，我作了一个个人主页，在学校内的虚拟空间，参加了一次主页大赛，几个DREAMWEAVER的页面，几个TABLE作布局，一个DB连接，几行PHP的代码嵌入在HTM
[宇宙时代]宇宙时代的GIS是什么？ comsci Gis
我们都知道一个事实，在行星内部的时候，因为地理信息的坐标都是相对固定的，所以我们获取一组GIS数据之后，就可以存储到硬盘中，长久使用。。。但是，请注意，这种经验在宇宙时代是不能够被继续使用的宇宙是一个高维时空
详解create database命令 czmmiao database
完整命令 CREATE DATABASE mynewdb USER SYS IDENTIFIED BY sys_password USER SYSTEM IDENTIFIED BY system_password LOGFILE GROUP 1 ('/u01/logs/my/redo01a.log','/u02/logs/m
几句不中听却不得不认可的话 datageek
1、人丑就该多读书。 2、你不快乐是因为：你可以像猪一样懒，却无法像只猪一样懒得心安理得。 3、如果你太在意别人的看法，那么你的生活将变成一件裤衩，别人放什么屁，你都得接着。 4、你的问题主要在于：读书不多而买书太多，读书太少又特爱思考，还他妈话痨。 5、与禽兽搏斗的三种结局：(1)、赢了，比禽兽还禽兽。(2)、输了，禽兽不如。(3)、平了，跟禽兽没两样。结论：选择正确的对手很重要。 6
1 14:00 PHP中的“syntax error, unexpected T_PAAMAYIM_NEKUDOTAYIM”错误 dcj3sjt126com PHP
原文地址：http://www.kafka0102.com/2010/08/281.html 因为需要，今天晚些在本机使用PHP做些测试，PHP脚本依赖了一堆我也不清楚做什么用的库。结果一跑起来，就报出类似下面的错误：“Parse error: syntax error, unexpected T_PAAMAYIM_NEKUDOTAYIM in /home/kafka/test/
xcode6 Auto layout and size classes dcj3sjt126com ios
官方GUI https://developer.apple.com/library/ios/documentation/UserExperience/Conceptual/AutolayoutPG/Introduction/Introduction.html iOS中使用自动布局（一） http://www.cocoachina.com/ind
通过PreparedStatement批量执行sql语句【sql语句相同，值不同】梦见x光 sql 事务批量执行
比如说：我有一个List需要添加到数据库中，那么我该如何通过PreparedStatement来操作呢？ public void addCustomerByCommit(Connection conn , List<Customer> customerList) { String sql = "inseret into customer(id
程序员必知必会----linux常用命令之十【系统相关】 hanqunfeng Linux常用命令
一.linux快捷键 Ctrl+C : 终止当前命令 Ctrl+S : 暂停屏幕输出 Ctrl+Q : 恢复屏幕输出 Ctrl+U : 删除当前行光标前的所有字符 Ctrl+Z : 挂起当前正在执行的进程 Ctrl+L : 清除终端屏幕，相当于clear 二.终端命令 clear : 清除终端屏幕 reset : 重置视窗，当屏幕编码混乱时使用 time com
NGINX IXHONG nginx
pcre 编译安装 nginx conf/vhost/test.conf upstream admin { server 127.0.0.1:8080; } server { listen 80; &
设计模式--工厂模式 kerryg 设计模式
工厂方式模式分为三种： 1、普通工厂模式：建立一个工厂类，对实现了同一个接口的一些类进行实例的创建。 2、多个工厂方法的模式：就是对普通工厂方法模式的改进，在普通工厂方法模式中，如果传递的字符串出错，则不能正确创建对象，而多个工厂方法模式就是提供多个工厂方法，分别创建对象。 3、静态工厂方法模式：就是将上面的多个工厂方法模式里的方法置为静态，
Spring InitializingBean/init-method和DisposableBean/destroy-method mx_xiehd java spring bean xml
1.initializingBean/init-method 实现org.springframework.beans.factory.InitializingBean接口允许一个bean在它的所有必须属性被BeanFactory设置后，来执行初始化的工作，InitialzingBean仅仅指定了一个方法。通常InitializingBean接口的使用是能够被避免的，（不鼓励使用，因为没有必要
解决Centos下vim粘贴内容格式混乱问题 qindongliang1922 centos vim
有时候，我们在向vim打开的一个xml，或者任意文件中，拷贝粘贴的代码时，格式莫名其毛的就混乱了，然后自己一个个再重新，把格式排列好，非常耗时，而且很不爽，那么有没有办法避免呢？答案是肯定的，设置下缩进格式就可以了，非常简单：在用户的根目录下直接vi ~/.vimrc文件然后将set pastetoggle=<F9> 写入这个文件中，保存退出，重新登录，
netty大并发请求问题 tianzhihehe netty
多线程并发使用同一个channel java.nio.BufferOverflowException: null at java.nio.HeapByteBuffer.put(HeapByteBuffer.java:183) ~[na:1.7.0_60-ea] at java.nio.ByteBuffer.put(ByteBuffer.java:832) ~[na:1.7.0_60-ea]
Hadoop NameNode单点问题解决方案之一 AvatarNode wyz2009107220 NameNode
我们遇到的情况 Hadoop NameNode存在单点问题。这个问题会影响分布式平台24*7运行。先说说我们的情况吧。我们的团队负责管理一个1200节点的集群(总大小12PB)，目前是运行版本为Hadoop 0.20，transaction logs写入一个共享的NFS filer(注：NetApp NFS Filer)。经常遇到需要中断服务的问题是给hadoop打补丁。 DataNod