CVPR2015 interesting paper(Part 1)

还没仔细看，以下是我感兴趣的文章。从标题和摘要看的。

非常想看：

4 Expanding Object Detector’s Horizon: Incremental Learning Framework for Object Detection in Videos [full paper] [ext. abstract]
Alina Kuznetsova, Sung Ju Hwang, Bodo Rosenhahn, Leonid Sigal
看题目有点意思。思路大致能够猜清楚。
32 Delving Into Egocentric Actions [full paper] [ext. abstract]
Yin Li, Zhefan Ye, James M. Rehg
主要是想看一下Egocentric的常用处理手段。
47 Deep Neural Networks Are Easily Fooled: High Confidence Predictions for Unrecognizable Images [full paper] [ext. abstract]
Anh Nguyen, Jason Yosinski, Jeff Clune
arxiv上的没仔细看。
48 Deformable Part Models are Convolutional Neural Networks [full paper] [ext. abstract]
Ross Girshick, Forrest Iandola, Trevor Darrell, Jitendra Malik
arxiv上的没仔细看。
55 Nested Motion Descriptors [full paper] [ext. abstract]
Jeffrey Byrne
看题目比较有意思。
65 Building a Bird Recognition App and Large Scale Dataset With Citizen Scientists: The Fine Print in Fine-Grained Dataset Collection [full paper] [ext. abstract]
Grant Van Horn, Steve Branson, Ryan Farrell, Scott Haber, Jessie Barry, Panos Ipeirotis, Pietro Perona, Serge Belongie
做数据集的话需要看。这篇会给出一些思路。
106 Mid-Level Deep Pattern Mining [full paper] [ext. abstract]
Yao Li, Lingqiao Liu, Chunhua Shen, Anton van den Hengel
看过摘要，了解下idea。
108 Understanding Image Representations by Measuring Their Equivariance and Equivalence [full paper] [ext. abstract]
Karel Lenc, Andrea Vedaldi
重磅炸弹。

一般想看：

1 Going Deeper With Convolutions [full paper] [ext. abstract]
Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich
这个arxiv已经看过了。核心就是提出了一个inception层，其实相当于做了一个多尺度卷积，能够在某一层上自动学习到最好的表示。实际效果和VGG差不多，因为VGG采用小Kernel来模拟大kernel，其实效果上差不多。Christian Szegedy的另一篇batch normalization的也是必看文章，非常好用。
6 What do 15,000 Object Categories Tell Us About Classifying and Localizing Actions? [full paper] [ext. abstract]
Mihir Jain, Jan C. van Gemert, Cees G. M. Snoek
这篇文章的主要创新点是，做action recognition时，采用object作为辅助识别，论文研究了action具有object的preference。具体细节没看。idea还不错。
12 Leveraging Stereo Matching With Learning-Based Confidence Measures [full paper] [ext. abstract]
Min-Gyu Park, Kuk-Jin Yoon
14 Efficient Sparse-to-Dense Optical Flow Estimation Using a Learned Basis and Layers [full paper] [ext. abstract]
Jonas Wulff, Michael J. Black
optical flow已经向learning进军了。
20 Attributes and Categories for Generic Instance Search From One Example [full paper] [ext. abstract]
Ran Tao, Arnold W.M. Smeulders, Shih-Fu Chang
这篇paper关注的主题是3D鞋子的检索，作者说object retrieval方法会在鞋检索上失效( We observe that what works for buildings loses its generality on shoes.)。具体解决方案没看，如果涉及到3D object retrieval方法，可以看看这篇。
24 A Geodesic-Preserving Method for Image Warping [full paper] [ext. abstract]
Dongping Li, Kaiming He, Jian Sun, Kun Zhou
可能以后会有用。
25 Shape Driven Kernel Adaptation in Convolutional Neural Network for Robust Facial Traits Recognition [full paper] [ext. abstract]
Shaoxin Li, Junliang Xing, Zhiheng Niu, Shiguang Shan, Shuicheng Yan
论文idea不错，但技术路线总感觉有点复杂，值得一看。
36 Deep Transfer Metric Learning [full paper] [ext. abstract]
Junlin Hu, Jiwen Lu, Yap-Peng Tan
应该是比较常规的文章，看样子是提出一个loss function。粗略看了下，我的判断没错。转需。
40 Predicting Eye Fixations Using Convolutional Neural Networks [full paper] [ext. abstract]
Nian Liu, Junwei Han, Dingwen Zhang, Shifeng Wen, Tianming Liu
早晚的事，刚出现。
43 Modeling Local and Global Deformations in Deep Learning: Epitomic Convolution, Multiple Instance Learning, and Sliding Window Detection [full paper] [ext. abstract]
George Papandreou, Iasonas Kokkinos, Pierre-André Savalle
技术大杂烩
44 Grasp Type Revisited: A Modern Perspective on a Classical Feature for Vision [full paper] [ext. abstract]
Yezhou Yang, Cornelia Fermüller, Yi Li, Yiannis Aloimonos
动作识别已经做这么细了，grasp分类，我勒个去。
49 Hypercolumns for Object Segmentation and Fine-Grained Localization [full paper] [ext. abstract]
Bharath Hariharan, Pablo Arbeláez, Ross Girshick, Jitendra Malik
扩展filterbank，一个思想。
50 Mapping Visual Features to Semantic Profiles for Retrieval in Medical Imaging [full paper] [ext. abstract]
Johannes Hofmanninger, Georg Langs
看题目就Overview一下技术路线吧，应该没什么新idea。
58 Deep Hierarchical Parsing for Semantic Segmentation [full paper] [ext. abstract]
Abhishek Sharma, Oncel Tuzel, David W. Jacobs
随便看看
59 Designing Deep Networks for Surface Normal Estimation [full paper] [ext. abstract]
Xiaolong Wang, David Fouhey, Abhinav Gupta
随便看看。
62 SUN RGB-D: A RGB-D Scene Understanding Benchmark Suite [full paper] [ext. abstract]
Shuran Song, Samuel P. Lichtenberg, Jianxiong Xiao
新数据集介绍。
70 Radial Distortion Homography [full paper] [ext. abstract]
Zuzana Kukelova, Jan Heller, Martin Bujnak, Tomas Pajdla
看题目以后应该用得着。
71 Efficient Object Localization Using Convolutional Networks [full paper] [ext. abstract]
Jonathan Tompson, Ross Goroshin, Arjun Jain, Yann LeCun, Christoph Bregler
看看技术路线。
73 How Do We Use Our Hands? Discovering a Diverse Set of Common Grasps [full paper] [ext. abstract]
De-An Huang, Minghuang Ma, Wei-Chiu Ma, Kris M. Kitani
今年grasp classification井喷。
74 Rotating Your Face Using Multi-Task Deep Neural Network [full paper] [ext. abstract]
Junho Yim, Heechul Jung, ByungIn Yoo, Changkyu Choi, Dusik Park, Junmo Kim
看看技术路线。
75 Is Object Localization for Free? - Weakly-Supervised Learning With Convolutional Neural Networks [full paper] [ext. abstract]
Maxime Oquab, Léon Bottou, Ivan Laptev, Josef Sivic
现在都从classification转到localization上来了啊。。
78 Region-Based Temporally Consistent Video Post-Processing [full paper] [ext. abstract]
Xuan Dong, Boyan Bonev, Yu Zhu, Alan L. Yuille
看题目有点意思，论文还没看。
79 Global Refinement of Random Forest [full paper] [ext. abstract]
Shaoqing Ren, Xudong Cao, Yichen Wei, Jian Sun
Random forest模型压缩。
80 Adaptive Region Pooling for Object Detection [full paper] [ext. abstract]
Yi-Hsuan Tsai, Onur C. Hamsici, Ming-Hsuan Yang
玩pooling的，看下技术路线。
81 Discriminative and Consistent Similarities in Instance-Level Multiple Instance Learning [full paper] [ext. abstract]
Mohammad Rastegari, Hannaneh Hajishirzi, Ali Farhadi
MIL好久不见。
82 MUlti-Store Tracker (MUSTer): A Cognitive Psychology Inspired Approach to Object Tracking [full paper] [ext. abstract]
Zhibin Hong, Zhe Chen, Chaohui Wang, Xue Mei, Danil Prokhorov, Dacheng Tao
看题目很有意思。
83 Finding Action Tubes [full paper] [ext. abstract]
Georgia Gkioxari, Jitendra Malik
看看Action tubes是啥，估计是概念炒作。
84 Learning a Convolutional Neural Network for Non-Uniform Motion Blur Removal [full paper] [ext. abstract]
Jian Sun, Wenfei Cao, Zongben Xu, Jean Ponce
CNN拯救世界，随便看着玩吧。。。
85 Complexity-Adaptive Distance Metric for Object Proposals Generation [full paper] [ext. abstract]
Yao Xiao, Cewu Lu, Efstratios Tsougenis, Yongyi Lu, Chi-Keung Tang
看题目有点想看下摘要。
86 High-Fidelity Pose and Expression Normalization for Face Recognition in the Wild [full paper] [ext. abstract]
Xiangyu Zhu, Zhen Lei, Junjie Yan, Dong Yi, Stan Z. Li
想看下技术路线。
88 Sparse Convolutional Neural Networks [full paper] [ext. abstract]
Baoyuan Liu, Min Wang, Hassan Foroosh, Marshall Tappen, Marianna Pensky
额，看题目应该能猜个八九不离十。
89 FaceNet: A Unified Embedding for Face Recognition and Clustering [full paper] [ext. abstract]
Florian Schroff, Dmitry Kalenichenko, James Philbin
arxiv看过。
90 Cascaded Hand Pose Regression [full paper] [ext. abstract]
Xiao Sun, Yichen Wei, Shuang Liang, Xiaoou Tang, Jian Sun
今年hand pose的好多。
92 The Application of Two-Level Attention Models in Deep Convolutional Neural Network for Fine-Grained Image Classification [full paper] [ext. abstract]
Tianjun Xiao, Yichong Xu, Kuiyuan Yang, Jiaxing Zhang, Yuxin Peng, Zheng Zhang
今年multi level或者coarse to fine好流行。
93 End-to-End Integration of a Convolution Network, Deformable Parts Model and Non-Maximum Suppression [full paper] [ext. abstract]
Li Wan, David Eigen, Rob Fergus
看看技术路线。
95 Neuroaesthetics in Fashion: Modeling the Perception of Fashionability [full paper] [ext. abstract]
Edgar Simo-Serra, Sanja Fidler, Francesc Moreno-Noguer, Raquel Urtasun
只是被Neuro吸引。
96 Part-Based Modelling of Compound Scenes From Images [full paper] [ext. abstract]
Anton van den Hengel, Chris Russell, Anthony Dick, John Bastian, Daniel Pooley, Lachlan Fleming, Lourdes Agapito
额。
98 Pooled Motion Features for First-Person Videos [full paper] [ext. abstract]
Michael S. Ryoo, Brandon Rothrock, Larry Matthies
看看技术路线。
105 ActivityNet: A Large-Scale Video Benchmark for Human Activity Understanding [full paper] [ext. abstract]
Fabian Caba Heilbron, Victor Escorcia, Bernard Ghanem, Juan Carlos Niebles
又一新数据集。
107 Prediction of Search Targets From Fixations in Open-World Settings [full paper] [ext. abstract]
Hosnieh Sattar, Sabine Müller, Mario Fritz, Andreas Bulling
这领域不了解，随便看看。
113 Multispectral Pedestrian Detection: Benchmark Dataset and Baseline [full paper] [ext. abstract]
Soonmin Hwang, Jaesik Park, Namil Kim, Yukyung Choi, In So Kweon
新领域，看起来是老做法。
119 Interleaved Text/Image Deep Mining on a Very Large-Scale Radiology Database [full paper] [ext. abstract]
Hoo-Chang Shin, Le Lu, Lauren Kim, Ari Seff, Jianhua Yao, Ronald M. Summers
想看下摘要。
120 Learning Semantic Relationships for Better Action Retrieval in Images [full paper] [ext. abstract]
Vignesh Ramanathan, Congcong Li, Jia Deng, Wei Han, Zhen Li, Kunlong Gu, Yang Song, Samy Bengio, Charles Rosenberg, Li Fei-Fei
新坑。