ICCV 2009 Paper List
ICCV 2009 Paper List (www.iccv2009.org)
Following is the full list with some of my own comment. I am an audience this time, wish next time I am on the list!!
Orals (48 papers)
| Paper ID | Title |
| 23 | A HOG-LBP Human Detector with Partial Occlusion Handling Human Detection |
| 79 | Image Sequence Geolocation with Human Travel Priors GeoLocation |
| 150 | Reconstructing Building Interiors from Images Interior Building Reconstruction |
| 244 | Time-Constrained Photography ??? |
| 253 | Storyboard Sketches for Content Based Video Retrieval CBIR |
| 254 | Sparsity Induced Similarity Measure for Label Propagation Labeling |
| 332 | Modelling Activity Global Temporal Dependencies using Time Delayed Probabilistic Graphical Model |
| 337 | Globally Optimal Affine Epipolar Geometry from Apparent Contours Multi-View Geometry |
| 350 | Human Detection Using Partial Least Squares Analysis Human Detection |
| 376 | Similarity Functions for Categorization: from Monolithic to Category Specific |
| 402 | Filter Flow |
| 473 | Learning a dense multi-view representation for detection, viewpoint classification and synthesis of object categories Dense Representation |
| 528 | Finding Shareable Informative Patterns and Optimal Coding Matrix for Multiclass Boosting |
| 550 | Discriminative Metric Learning in Nearest Neighbor Models for Image Auto-Annotation |
| 632 | Curvature Regularity for Region-based Image Segmentation and Inpainting: A Linear Programming Relaxation |
| 714 | A Prism-based System for Multispectral Video Acquisition |
| 721 | Shift-Map Image Editing |
| 879 | Semi-Automatic Stereo Extraction From Video |
| 891 | Landmark-Based Sparse Color Representations for Color Transfer Large-Scale Image based Application |
| 953 | Compact Signatures for High-Speed Interest Point Description and Matching |
| 1036 | An efficient algorithm for Co-segmentation |
| 1057 | Attributes and Simile Classifiers for Face Verification |
| 1099 | A Shape-Based Object Class Model for Knowledge Transfer |
| 1124 | Kernel Methods for Weakly Supervised Mean Shift Clustering |
| 1220 | Action Detection in Complex Scenes with Spatial and Temporal Ambiguities |
| 1250 | Coded Aperture Pairs for Depth From Defocus |
| 1255 | Globally Optimal Extraction of Multi-Part Objects |
| 1269 | Decomposing a Scene into Geometric and Semantically Consistent Regions |
| 1433 | Image Segmentation with A Bounding Box Prior |
| 1562 | Is Dual Linear Self-Calibration Artificially Ambiguous? Calibration ? |
| 1600 | Light Field Video Stabilization |
| 1676 | Learning With Dynamic Group Sparsity |
| 1749 | Modeling Deformable Objects from a Single Depth Camera |
| 1761 | Max-Margin Additive Classifiers for Detection |
| 1767 | Quasi-Periodic Event Analysis for Video Retrieval |
| 1832 | You'll never walk alone: modeling social behavior for multi-target tracking |
| 1979 | Super-Resolution from a Single Image Seems Amazing |
| 1998 | On Feature Combination for Multiclass Object Classification |
| 2054 | Illumination Estimation from a Single Outdoor Image |
| 2117 | Activity Recognition using the velocity histories of tracked keypoints |
| 2125 | Shape from Flicker |
| 2160 | Local Distance Functions: A Framework, New Algorithms, and an Evaluation |
| 2162 | Looking Around the corner using Transient Imaging |
| 2234 | A Unified Model for Global, Multi-Class Object Detection |
| 2274 | Combining efficient object localization and image classification |
| 2314 | Building Rome in a Day !!!!!!!!!!!!!!!!! Real Time ? Very interested in this paper |
| 2374 | Boundary Ownership by Lifting to 2.5D |
| 2449 | A linear formulation of shape from specular flow |
Posters (260 papers)
| Paper ID | Title |
| 7 | Tracking in Unstructured Crowded Scenes |
| 13 | Learning Pedestrian Dynamics from the Real World |
| 27 | Resilient Subclass Discriminant Analysis |
| 29 | Spoke features for learning irregular shapes |
| 72 | Extending Continuous Cuts: Anisotropic Metrics and Expansion Moves |
| 85 | Video stabilization using robust feature trajectories |
| 98 | Robust Matching of Building Facades under Large Viewpoint Changes |
| 105 | Robust Fitting of Multiple Structures: The Statistical Learning Approach |
| 112 | A Branch-and-Bound Algorithm for Globally Optimal Calibration of a camera-and-rotation-sensor system Calibration and Optimal |
| 140 | The Infinite Hidden Markov Random Field Model |
| 142 | Complex Volume and Pose Tracking with Probabilistic Dynamical Model and Visual Hull Constraint |
| 163 | Superresolution Texture Maps for Multiview Reconstruction |
| 170 | Constrained Clustering by Spectral Kernel Learning Kernel and Clustering |
| 185 | Efficient Human Pose Estimation via Parsing a Tree Structure Based Human Model |
| 189 | Learning Image Similarity from Flickr using Stochastic Intersection Kernel Machines Learning from large scale database |
| 196 | Group-Sensitive Multiple Kernel Learning For Object Categorization |
| 206 | BLOGS: Balanced Local and Global Search for Non-Degenerate Two View Epipolar Geometry |
| 212 | Convex Multi-Region Segmentation on Manifolds |
| 222 | Joint Edge Registration and Camera Pose Recovery |
| 255 | Unsupervised Face Alignment by Robust Nonrigid Mapping |
| 261 | Recognizing Actions by Shape-Motion Prototype Trees |
| 264 | Class Segmentation and Object Localization with Superpixel Neighborhoods |
| 278 | Simultaneous and Orthogonal Decomposition of Data using Multimodal Discriminant Analysis |
| 309 | Spectral clustering of linear subspaces for motion segmentation |
| 315 | Attached Shadow Coding: Estimating Surface Normals from Shadows under Unknown Reflectance and Lighting Conditions |
| 320 | Fast and Robust Earth Mover's Distances |
| 329 | Multiple View Semantic Segmentation for Street-view Images Large Scale and MVG |
| 348 | Gradient Domain Layer Separation under Independent Motion |
| 352 | Active Object Detection With Fixation |
| 360 | Multiscale Symmetric Part Detection and Grouping |
| 365 | Absolute Scale in Structure from Motion from a Single Vehicle Mounted Camera by Exploiting Nonholonomic Constraints |
| 368 | Image Segmentation with Simultaneous Illumination and Reflectance Estimation: An Energy Minimization Approach |
| 377 | Factorizing Scene Albedo and Depth from a Single Foggy Image |
| 381 | Directional Statistics BRDF Model |
| 389 | Domain Adaptive Semantic Diffusion for Large Scale Context-Based Video Annotation |
| 398 | Multi-Scale Object Detection by Clustering Lines |
| 408 | Local Trinary Patterns for Human Action |
| 413 | Is that you? Metric Learning Approaches for Face Identification |
| 416 | Complete Multi-View Reconstruction of Dynamic Scenes from Probabilistic Fusion of Narrow and Wide Baseline Stereo |
| 417 | Semi-Supervised Random Forests |
| 425 | Graph cuts using a Riemannian Metric induced by Tensor Voting |
| 427 | Stabilizing Motion Tracking Using Retrieved Motion Priors |
| 436 | Recovering Planar Homographies between 2D Shapes |
| 443 | Hierarchical 3D Diffusion Wavelets Shape Priors |
| 449 | Multimodal Partial Estimates Fusion |
| 450 | A New Minimal Solution to the Relative Pose of a Calibrated Stereo Camera with Small Field of View Overlap |
| 452 | Image Saliency by Isocentric Curvedness and Color |
| 457 | Measuring Demographics and Height with a Calibrated Camera |
| 461 | Plane-Based Calibration of Central Catadioptric Cameras |
| 466 | GroupSAC: Efficient Consensus in the Presence of Groupings RANSAC Related |
| 491 | Kernel Active Contour |
| 493 | Dimensionality Reduction and Principal Surfaces via Kernel Map Manifolds |
| 495 | Joint learning of visual attributes, object classes and visual saliency |
| 503 | Bayesian Poisson Regression for Crowd Counting |
| 506 | Efficient Discriminative Learning of Parts-based Models |
| 508 | Improving Accuracy of Geometric Parameter Estimation Using the Projected Score Method |
| 516 | Probabilistic Occlusion Boundary Detection on Spatio-Temporal Lattices |
| 519 | Robust Dynamical Model for Simultaneous Registration and Segmentation in a Variational Framework: A Bayesian Approach |
| 521 | Higher-Order Gradient Descent by Fusion Move Graph Cut |
| 530 | Active Skeleton for Non-rigid Object Detection |
| 531 | Moving in Stereo: Efficient Structure and Motion Using Lines |
| 534 | Sparse Representation of Cast Shadows via L1-Regularized Least Squares L1 Sparse |
| 535 | Robust Visual Tracking using L1 Minimization L1 Sparse |
| 539 | Robust Multilinear Principal Component Analysis |
| 545 | Efficient Discriminative Local Learning for Object Recognition |
| 552 | Multiple Kernels for Object Detection |
| 558 | Fast Visibility Restoration from a Single Color or Gray Level Image |
| 571 | The Normalized Subspace Inclusion: Robust Clustering of Motion Subspaces |
| 582 | Coarse Registration of 3D Surface Triangulations Based on Moment Invariants with Applications to Object Alignment and Identification |
| 586 | I know what you did last summer: object-level auto-annotation of holiday snaps |
| 588 | Scale Invariance and Noise in Natural Images |
| 595 | Learning Long Term Face Aging Patterns from Partially Dense Aging Databases |
| 606 | Image Restoration using Online Photo Collections Large scale |
| 608 | Beyond the Euclidean distance: Creating effective visual codebooks using the histogram intersection kernel |
| 609 | Color Constancy using 3D Scene Geometry |
| 633 | Beyond Connecting the Dots: A Polynomial-time Algorithm for Segmentation and Boundary Estimation with Imprecise User Input |
| 690 | Scene it or not? Incremental Multiple Kernel Learning for Object Recognition |
| 697 | On Building a Large Video Database with Human Annotations |
| 698 | Convex Optimization for Multi-Class Image Labeling with a Novel Family of Total Variation Based Regularizers |
| 705 | Learning Based Digital Matting |
| 708 | Static Multi-Camera Factorization Using Rigid Motion Multi-camera MVG |
| 728 | Shadow cameras: Reciprocal views from illumination masks |
| 760 | Simultaneous Photometric Invariance And Shape Recovery |
| 778 | The One-Shot Similarity Kernel |
| 781 | Background Subtraction for Freely Moving Cameras |
| 783 | A Theory of Active Object Localization |
| 785 | Component Analysis Approach to Estimation of Tissue Intensity Distributions of 3D images |
| 806 | A Robust Boosting Tracker with Minimum Error Bound in a Co-Training Framework |
| 832 | Feature Correspondence and Deformable Object Matching via Agglomerative Correspondence Clustering |
| 833 | Active Subspace Learning for Image Retrieval |
| 836 | Simultaneous Color Constancy and Depth Map Estimation for Radiometrically Varying Stereo Images |
| 837 | Automatic Learning and Extraction of Multi-Local Features |
| 838 | Finding Good Composition in Panoramic Scenes |
| 869 | Subspace matching: Unique solutions to point matching with geometric constraints |
| 872 | Using individuality to track individuals: Clustering individual trajectories in crowds using local appearance and frequency trait |
| 873 | Fast multi- action recognition using mined dense spatial temporal features |
| 882 | Dense 3D reconstruction method using a single pattern for fast moving object/ Reconstruction |
| 890 | Quantifying Contextual Information for Object Detection |
| 899 | High-resolution Shape Reconstruction from Multiple Range Images based on Simultaneous Estimation of Surface and Motion |
| 903 | Feature-Centric Efficient Subwindow Search |
| 904 | Implicit Color Segmentation Features for Pedestrian Detection |
| 945 | Power watersheds: a new image segmentation framework extending graph cuts, random walker and optimal spanning forest |
| 947 | Optimal Correspondences from Pairwise Constraints May be given feature and metric, be defining cost function, solve the optimal. Or we can start from the feature, toward the application |
| 955 | Display-Camera Calibration from Eye Reflections |
| 962 | A framework for visual saliency detection with applications to image thumbnailing |
| 973 | Optimizing Parametric Total Variation Models |
| 974 | Tracking a Hand Manipulating an Object |
| 977 | Single View Reconstruction Using Shape Grammars for Urban Environments |
| 997 | Robust Facial Feature Tracking using Multiscale Biased Linear Predictors |
| 1005 | 3D reconstruction from image collections with a single known focal length |
| 1009 | GraphCut-Solvable Hierarchical CRFs for Object Class Image Segmentation |
| 1017 | Segmentation, Ordering and Tracking using Graphical Models |
| 1018 | A Latent Model of Discriminative Aspect |
| 1024 | Unlabeled data improves word prediction |
| 1027 | A Probabilistic Framework for Partial Intrinsic Symmetries in Geometric Data |
| 1032 | Bayesian selection of scaling laws for motion modeling in images |
| 1033 | Top-Down Color Attention for Object Recognition |
| 1035 | Detecting Objects in Large Image Collections and Videos by Efficient Subimage Retrieval |
| 1038 | Automatic annotation of human actions in video |
| 1043 | A Hand-held Photometric Stereo Camera for 3-D Modeling 3-D Modeling Stereo Camera |
| 1049 | Detection and Removal of Chromatic Moving Shadows in Surveillance Scenarios |
| 1050 | Joint optimization of segmentation and appearance models |
| 1056 | Learning Actions From the Web |
| 1058 | Learning Deformable Action Templates from Crowded Videos |
| 1063 | Active Appearance Models with Rotation Invariant Kernels |
| 1065 | Level Set Segmentation with Both Shape and Intensity Priors |
| 1073 | Robust Tracking-by-Detection using a Detector Confidence Particle Filter |
| 1076 | Beyond Visual Vocabularies: Incremental Action Recognition Using Feature-Tree |
| 1085 | Template-Free Monocular Reconstruction of Deformable Surfaces |
| 1095 | Seeing 3D Objects in a Single 2D Image |
| 1097 | RankBoost with L1 regularization for Facial Expression Recognition and Intensity Estimation |
| 1108 | Optimal Multiple Surfaces Searching for Video/Image Resizing - A Graph-Theoretic Approach |
| 1110 | Subspace Constrained Mean-Shift |
| 1114 | Body-Relative Navigation Guidance Using Uncalibrated Cameras |
| 1121 | Evaluating Information Contributions of Bottom-up and Top-down Processes |
| 1125 | Multi-perspective Stereo Matching and Volumetric Reconstruction |
| 1133 | Deformable Model Fitting with a Mixture of Local Experts |
| 1134 | Scene Shape Priors for Superpixel Segmentation |
| 1135 | Detecting Interpretable and Accurate Scale-Invariant keypoints |
| 1143 | The Swap and Expansion Moves Revisited and a New Move |
| 1145 | Face Recognition With Contiguous Occlusion Using Markov Random Fields |
| 1146 | Structure and Kinematics Triangulation with a Rolling Shutter Stereo Rig |
| 1148 | An Information Theoretic Approach for Tracker Performance Evaluation |
| 1151 | Which Faces to Tag: Adding Prior Constraints into Active Learning |
| 1152 | Non-Local Sparse Models for Image Restoration |
| 1158 | Is a detector only good for detection? |
| 1159 | LIVEcut: Learning-based Interactive Video Segmentation by Evaluation of Multiple Propagated Cues |
| 1160 | Exact-RANSAC: Sample Consensus with Guaranteed Global Optimality RANSAC |
| 1162 | Efficient subset selection based on the Renyi entropy |
| 1172 | Non-Euclidean Image-Adaptive Radial Basis Functions for 3D Interactive Segmentation |
| 1176 | Adaptive Fragments-Based Tracking of Non-Rigid Objects Using Level Sets |
| 1186 | A Near Optimal Acceptance-Rejection Algorithm for Exact Cross-Correlation Search |
| 1187 | Weighted Graph Characteristics from Oriented Line Graph Polynomials |
| 1204 | Spectral Control of Viscous Alignment for Deformation Invariant Matching |
| 1211 | Heterogeneous Feature Machines for Visual Recognition |
| 1215 | Efficient Indexing for Large Scale Visual Search |
| 1216 | Human Pose Estimation Using Consistent Max-Covering |
| 1223 | Spectral Error Correcting Output Codes for Efficient Multiclass Recognition |
| 1227 | Shape Guided Contour Grouping with Particle Filters |
| 1229 | Automatic follicle quantification from 3D ultrasound data using global/local context with database guided segmentation |
| 1235 | Keyframe-Based Real-Time Camera Tracking |
| 1252 | Tracking a Large Number of Objects from Multiple Views |
| 1253 | The Self-Aware Matching Measure for Stereo |
| 1257 | Detection Driven Adaptive Multi-cue Integration for Multiple Human Tracking |
| 1277 | Non-Rigid Object Localization and Segmentation Using Eigenspace Representation |
| 1279 | Kernel Map Compression using Generalized Radial Basis Functions |
| 1283 | Optical Flow Estimation on Coarse-to-Fine Region-Trees using Discrete Optimization |
| 1289 | A New Multiview Spacetime-Consistent Depth Recovery Framework for Free Viewpoint Video Rendering Free View |
| 1304 | Reconstructing 3D motion trajectories for particle swarms by global correspondence selection ?? |
| 1319 | Patch based Within-Object Classification |
| 1323 | An Algorithm for Minimizing the Piecewise Smooth Mumford-Shah Functional |
| 1328 | Recovering the Spatial Layout of Cluttered Rooms |
| 1337 | SURF Tracking CVPR 2009 Related |
| 1396 | An Algebraic Model for fast Corner Detection |
| 1398 | Robust Graph-Cut Scene Segmentation and Reconstruction for Free-Viewpoint Video of Complex Dynamic Scenes |
| 1428 | 3D Open-Surface Shape Correspondence for Statistical Shape Modeling: Identifying Topologically Consistent Landmarks |
| 1434 | Spatio-Temporal Relationship Match: Video Structure Comparison for Recognition of Complex Human Activities |
| 1452 | Shape-based Recognition of 3D Point Clouds in Urban Environments |
| 1456 | A Biased Sampling Strategy for Object Categorization |
| 1459 | On Optimizing Subspaces for Face Recognition |
| 1460 | Seeing through water: Image restoration using model-based tracking |
| 1463 | Joint Localization and Continuous State Estimation for Visual Inference |
| 1465 | A Markov Clustering Topic Model for Mining Behaviour in Video |
| 1474 | Computation Complexity of Branch-and-Bound Model Selection |
| 1482 | Saliency Driven Total Variation Segmentation |
| 1483 | A Novel Approach to Expression Recognition from Non-frontal Face Images |
| 1499 | Mode-Detection via Median-Shift |
| 1526 | The Dimensionality of Scene Appearance |
| 1531 | Robust Motion Estimation Using Trajectory Space Learning: Applications in Aortic and Mitral Valve Modeling |
| 1532 | Piecewise-consistent Color Mappings of Images Acquired Under Various Conditions |
| 1533 | Weakly supervised discriminative localization and classification: a joint learning process |
| 1536 | A Global Perspective on MAP Inference for Low-Level Vision |
| 1542 | Diagram Techniques for Multiple View Geometry MVG |
| 1545 | Wide-Baseline Image Matching Using Line Signatures |
| 1549 | Action Recognition in Context |
| 1554 | Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations |
| 1555 | Time Series Prediction by Chaotic Modeling of Nonlinear Dynamical Systems |
| 1570 | Modeling 3D Articulated Objects from Monocular Images |
| 1573 | FLoSS: Facility Location for Subspace Segmentation |
| 1582 | Constructing Implicit 3D Shape Models for Pose Estimation |
| 1586 | Matching as a Non-Cooperative Game |
| 1589 | Piecewise Planar Stereo for Image-based Rendering |
| 1599 | Least-Squares Congealing for Large Numbers of Images |
| 1611 | Landmark Classification in Large-Scale Image Collections Large Scale Image |
| 1623 | Detection of Human Actions From A Single Example |
| 1624 | Large Displacement Optical Flow Computation without Warping |
| 1638 | Riemannian Bayesian estimation of diffusion tensor images |
| 1642 | Hierarchical Gaussianization for Image Classification |
| 1650 | Spatiotemporal Video Segmentation via Many-to-Many Partial Region Matching |
| 1652 | Ground truth dataset and baseline evaluations for intrinsic image algorithms |
| 1663 | Texel-based Texture Segmentation |
| 1666 | Image Compression with Anisotropic Triangulations |
| 1670 | Context by Region Ancestry |
| 1686 | A Study on Automatic Age Estimation using a Large Database Form Location, whether, to age, what is next ? Gender ? |
| 1690 | A Multi-Sample, Multi-Tree Approach to Bag-of-Words Image Representation for Image Retrieval |
| 1698 | Discriminative Generalized Hough Transform for Object Detection |
| 1705 | View Projection using Stratified Inverses |
| 1722 | Untangling Fibers by Quotient Appearance Manifold Mapping for Grayscale Shape Classification |
| 1729 | Label Set Perturbation for MRF based Neuroimaging Segmentation |
| 1744 | Building Recognition Using Sketch-Based Representations and Spectral Graph Matching |
| 1764 | Brain Anatomical Surface Tensor-based Morphometry with Holomorphic Differentials |
| 1770 | A Hierarchical Learning Approach for Tubular Structure Parsing in Medical Imaging |
| 1789 | Image Annotation Using Multi-label Correlated Green's Function with Crisp Posterior Multi-label Assignment |
| 1839 | Robust Image Segmentation Using Learned Priors |
| 1876 | Incremental Discriminant-Analysis of Canonical Correlations for Action Recognition |
| 1905 | A direct approach for efficiently tracking with 3D Morphable Models |
| 1932 | Illumination Aware MCMC Particle Filter for Long-Term Outdoor Multi-Object Simultaneous Tracking and Classification |
| 1963 | Minimizing energy functions on 4-connected lattices using elimination |
| 1965 | Real-time Visual Tracking via Incremental Covariance Tensor Learning |
| 1980 | Joint Learning of Pose Estimators and Features for Object Detection |
| 1982 | Simultaneous Clustering and Alignment for an Image Ensemble |
| 1987 | A Riemannian Analysis of 3D Nose Shapes For Partial Human Biometrics |
| 1988 | Efficient Privacy Preserving Video Surveillance |
| 2062 | Non-Iterative Approach for Fast and Accurate Vanishing Point Detection |
| 2087 | Packing bag-of-features |
| 2092 | Estimating Human Shape and Pose from a Single Image |
| 2122 | A hybrid generative/discriminative classification framework based on free-energy terms |
| 2136 | Non-Negative Matrix Factorization of Partial Track Data for Motion Segmentation |
| 2137 | Large Margin Object Detection in Dynamic Scenes |
| 2151 | Correlated Probabilistic Trajectories for Pedestrian Motion Detection |
| 2172 | Efficient Segmentation Using Feature-based Graph Partitioning Active Contours (GPAC) |
| 2174 | Studying Brain Morphology using Teichmüller Space Theory |
| 2198 | Segmentation and Shading Estimation in Slowly Changing Textured Images |
| 2207 | Exploiting Uncertainty in Random Sample Consensus |
| 2208 | A Robust Elastic and Partial Matching Metric for Face Recognition |
| 2212 | SCRAMSAC: Improving RANSAC鐃� Efficiency with a Spatial Consistency Filter |
| 2245 | Efficient Multi-label Ranking for Multi-class Learning: Application to Object Recognition |
| 2264 | Scene Categorization from Low Definition Video |
| 2293 | Using machine learning to predict where people look |
| 2297 | An Algebraic Approach to Affine Registration of Point Sets |
| 2298 | Tensor completion for estimating missing values in visual data |
| 2306 | Structure- and Motion-adaptive Regularization for High Accuracy Optic Flow |
| 2312 | Unsupervised Learning of High-order Structural Semantics from Images |
| 2353 | Video Scene Understanding Using Multi-scale Analysis |
| 2384 | Large-Scale Privacy Protection in Street-Level Imagery Large Scale |
| 2398 | Kernelized Locality-Sensitive Hashing for Scalable Image Search |
| 2415 | Efficient, High-Quality Image Contour Detection |
| 2425 | Actionable Information and the Ecological Approach to Visual Perception |
| 2443 | What is the Best Multi-Stage Architecture for Object Recognition? |
| 2493 | Estimating Contact Dynamics |