丕子 » Computer Vision

关于Attribute(s)和Pattern Recognition

丕子 — Mon, 25 Apr 2011 10:45:09 +0000

Attribute：属性。这个词一直在Computer Vision领域以及Information Retrieval频频出现。基本作用大体是这样的：咱们知道有对象的概念，那么对象就有自己的属性。例如人这个对象，可以把投、躯干、四肢看做属性。如果把一个人的一个Action看做对象，那么他的属性可以包括有没有弯腰、有没有伸胳膊、有没有曲腿等等。如果把信息检索中的一个Query查询看做对象，那么属性可以包括词性、词义等等。

在对一个对象进行识别的时候，可以将几乎尽量多的属性集成起来做全局优化，因为存在集成的思想，考虑越全面，解决好效率问题，识别结果理论上会有所提高。

下面我大体简单的挑了几篇关于Attribute的论文，大部分在CV和IR领域。

B. Siddiquie, R. S. Feris and L. Davis. "Image Ranking and Retrieval Based on Multi-Attribute Queries". IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2011), Oral Presentation (3.5% acceptance), Colorado Springs, USA, 2011. [pdf]
R. S. Feris, B. Siddiquie, Y. Zhai, J. Petterson, L. Brown and S. Pankanti. "Attribute-based Vehicle Search in Crowded Surveillance Videos". ACM International Conference on Multimedia Retrieval (ICMR 2011), Oral Presentation (16% acceptance), Trento, Italy, 2011. [pdf]
Jingen Liu, Benjamin Kuipers, and Silvio Savarese, Recognizing Human Actions by Attributes, to appear in IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, 2011
Discriminative Image Warping with Attribute Flow. Weiyu Zhang (University of Pennsylvania), Praveen Srinivasan, Jianbo Shi(CVPR 2011)
Interactively Building a Discriminative Vocabulary of Nameable Attributes (PDF)Devi Parikh, Kristen Grauman(CVPR 2011)
High Level Describable Attributes for Predicting Aesthetics and Interestingness (PDF).Sagnik Dhar (Stony Brook University), Vicente Ordonez (Stony Brook University), Tamara Berg (Stony Brook University)(CVPR 2011)
Sharing Features Between Objects and Their Attributes. Sung Ju Hwang, Fei Sha, Kristen Grauman(CVPR 2011)
Combining attributes and Fisher vectors for efficient image retrieval. Matthijs Douze, Arnau Ramisa (INRIA), Cordelia Schmid(CVPR 2011)
Attribute-Centeric Recognition for Cross-category Generalization (PDF).Ali Farhadi, Ian Endres, Derek Hoiem(CVPR 2010)
Attribute and Simile Classifiers for Face Verification (PDF)Neeraj Kumar, Alexander C. Berg, Peter N. Belhumeur, Shree K. Nayar(ICCV 2009)
Joint learning of visual attributes, object classes and visual saliency (PDF)Gang Wang, David Forsyth(ICCV 2009)
Automatic Attribute Discovery and Characterization (PDF).Tamara Berg, Alexander Berg, Jonathan Shih(ECCV 2010)
Human Attributes from 3D Pose Tracking (PDF),Leonid Sigal, David Fleet, Niko Troje, Micha Livne(ECCV 2010)
Attribute-based Transfer Learning for Object Categorization with Zero or One Training Example.Xiaodong Yu, Yiannis Aloimonos(ECCV 2010)
A Discriminative Latent Model of Object Classes and Attributes (PDF).Yang Wang, Greg Mori(ECCV 2010)

当然还有很多文章，不过今年最多。有兴趣的可以看看。

SIGGRAPH2011和IJCAI2011关于CV的Paper

丕子 — Sat, 23 Apr 2011 04:32:58 +0000

- A selection of computer vision related papers -
See IJCAI 2011 page for a non selective list.

Accommodating Human Variability in Human-Robot Teams through Theory of Mind: Laura Hiatt, Anthony Harrison, Greg Trafton
Aesthetic Guidelines Driven Photography By Robots: Raghudeep Gadde, Kamalakar Karlapalem
Capturing an Evader in a Polygonal Environment with Obstacles: Deepak Bhadauria, Volkan Isler
Conics With A Common Axis of Symmetry: Properties and Applications to Camera Calibration: Zijian Zhao
Exploiting Probabilistic Knowledge under Uncertain Sensing for Efficient Robot Behaviour: Marc Hanheide, Nick Hawes, Charles Gretton, Alper Aydemir, Hendrik Zender, Andrzej Pronobis, Jeremy Wyatt, Moritz Göbelbecker
Robotic Object Detection: Learning to Improve the Classifiers using Sparse Graphs for Path Planning: Zhaoyin Jia, Ashutosh Saxena, Tsuhan Chen
User-dependent Aspect Model for Collaborative Activity Recognition: Wenchen Zheng, Qiang Yang

============

- A selection of computer vision related papers - Papers conditionally accepted
See Ke-Sen Huang's SIGGRAPH 2011 page for a non selective list.

Nonlinear Revision Control for Images (project, abstract): Hsiang-Ting Chen (National Tsing Hua University, Taiwan), Li-Yi Wei (Microsoft Research), Chun-Fa Chang (National Taiwan Normal University, Taiwan)
Example-based Image Color and Tone Style Enhancement: Baoyuan Wang (Zhejiang University), Yizhou Yu (University of Illinois at Urbana-Champaign and Zhejiang University), Ying-Qing Xu (Microsoft Research Asia)
Perceptually Based Tone Mapping for Low-Light Conditions: Adam G. Kirk, James F. O'Brien (University of California, Berkeley)
Depixelizing Pixel Art: Johannes Kopf (Microsoft Research), Dani Lischinski (The Hebrew University of Jerusalem)
Switchable Primaries Using Shiftable Layers of Color Filter Arrays: Behzad Sajadi, Aditi Majumder, Kazuhiro Hiwada, Atsuto Maki, Ramesh Raskar (MIT Media Lab)
Exploring Photobios: Ira Kemelmacher-Shlizerman, Rahul Garg, Steven M. Seitz (University of Washington), Eli Shechtman (Adobe Systems, Inc.)
Laplacian Filters: Edge-aware Image Processing with a Laplacian Pyramid: Sylvain Paris, Samuel W. Hasinoff (Toyota Technological Institute at Chicago), Jan Kautz (University College London)
Video-based Characters - Creating New Human Performances from a Multi-view Video Database: Feng Xu (Tsinghua University, Beijing), Yebin Liu, Carsten Stoll (Max-Planck-Institut Informatik), James Tompkin (University College London), Gaurav Bharaj (Max-Planck-Institut Informatik), Qionghai Dai (Tsinghua University, Beijing), Hans-Peter Seidel (Max-Planck-Institut Informatik), Jan Kautz (University College London), Christian Theobalt (Max-Planck-Institut Informatik)

===========

- A selection of computer vision papers -
See Ke-Sen Huang's Eurographics 2011 page for a non selective list.

State-of-the-Art Reports

State of the Art in Computational Plemoptic Imaging (PDF, project): Gordon Wetzstein, Ivo Ihrke, Douglas Lanman, Wolfgang Heidrich

Session: Quality and Scalability

Freehand HDR imaging of moving scenes with simultaneous resolution enhancement (PDF, project, results): Henning Zimmer, Andres Bruhn, Joachim Weickert

Session: Non-Photorealistic Rendering

Estimating Color and Texture Parameters for Vector Graphics (PDF, supplementary material, video): Stefan Jeschke, David Cline, Peter Wonka

Session: Image and Video

Blur-Aware Image Downsizing (PDF, project, video, results, supplementary material): Matthew Trentacoste, Rafal Mantiuk, Wolfgang Heidrich
Image Retargeting Quality Assessment (PDF, abstract): Yong-Jin Liu, Xi Luo, Yu-Ming Xuan, Wen-Feng Chen, Xiao-Lan Fu
Image and Video Abstraction by Coherence-Enhancing Filtering (PDF, project, results, videos): Jan Eric Kyprianidis, Henry Kang

注：以上内容选择CVPapers

CVPR2011录取结果

丕子 — Sat, 19 Feb 2011 03:02:45 +0000

CVPR2011论文录取已经结束了。cvpapers可以看一些论文以及连接了。这里大体看一下结果统计与分析：

At the end of the AC meeting, there were 59 papers (3.5%) accepted for orals and 381 (22.7%)accepted as posters, for an overall acceptance rate of 26.4% where Percentages are computed using the 1677 papers that entered the review process. In addition to the acceptances, there were 1050 formal rejections during the AC meeting, while 187 papers were rejected for administrative reasons e.g. dual submissions) or were withdrawn by the authors after reviewing. (These 1677 papers are in addition to the 353 "submissions" deleted by the administrator or by authors before reviewing began, taking the total CVPR paper entries to 2020.)

Oral真是很难中啊，不错加上poster还可以说得过去了，牛会就是牛会，就是难中。

下面分析一下各个方向的录取情况：

The following table shows additional stats showing the per-area acceptance rate and also the percentage of submissions/orals and posters for that area compared to the overall CVPR2011 pool.

Primary Subject Area	Area Acceptance Rate	% of all CVPR11 Submissions	% of all CVPR11 orals	% of all CVPR11 Posters
Vision for Robotics	16%	1.13%	0.00%	0.79%
Human Identification	17%	1.07%	1.69%	0.52%
Face and Gesture Analysis	21%	5.84%	3.39%	4.99%
Performance Evaluation	22%	0.54%	0.00%	0.52%
Applications of Computer Vision	23%	5.01%	3.39%	4.46%
Motion and Tracking	23%	7.10%	10.17%	5.51%
Sensors	23%	0.78%	0.00%	0.79%
Early and Biologically-inspired Vision	24%	2.44%	1.69%	2.36%
Object Detection	25%	5.49%	8.47%	4.72%
Scene Understanding	26%	2.80%	5.08%	2.36%
Medical Image Analysis	26%	3.40%	0.00%	3.94%
Shape Representation and Matching	28%	3.82%	3.39%	4.20%
Vision for Graphics	29%	0.42%	0.00%	0.52%
Image and Video Retrieval	29%	4.95%	8.47%	4.99%
Color and Texture	29%	1.43%	1.69%	1.57%
Stereo and Structure from Motion	30%	4.89%	3.39%	6.04%
Video Surveillance	31%	2.15%	1.69%	2.62%
Segmentation and Grouping	31%	6.74%	5.08%	8.40%
Shape-from-X	32%	2.21%	1.69%	2.89%
Document Analysis	33%	0.72%	1.69%	0.79%
Illumination and Reflectance Modeling	33%	1.25%	1.69%	1.57%
Computational Photography and Video	34%	3.46%	8.47%	3.94%
Object Recognition	35%	5.66%	6.78%	7.61%
Statistical Methods and Learning	35%	7.87%	3.39%	11.55%
Video Analysis and Event Recognition	35%	4.89%	8.47%	6.30%
Optimization Methods	36%	2.62%	6.78%	3.15%
Image-Based Modeling	38%	2.03%	3.39%	2.89%
Withdrawn/Admin Rejects	0%	9.30%	0.00%	0.00%

恭喜获奖的同学了，唉，自己什么时候能够有一篇。

The program schedule is still being put together, but here is the list of accepted papers. This will be updated when dates/times are determined.

ACCEPTED ORAL PAPERS
ID	Title	Authors
22	Towards Cross-Cateogory Knowledge Propagation for Learning Visual Concepts	Guo-Jun Qi (ECE, UIUC); Yong Rui (Microsoft Corporation); Qi Tian (University of Texas at San Antonio); Thomas Huang (UIUC)
26	Smoothly Varying Affine Stitching	Wen Yan Lin (Nus); Siying Liu (i2r.a-star.edu.sg); Yasuyuki Matsushita; Tian Tsong Ng (i2r.a-star.edu.sg)
47	Real-time Human Pose Recognition in Parts from Single Depth Images	Jamie Shotton (Microsoft Research Cambridge); Andrew Fitzgibbon; Mat Cook; Andrew Blake;
48	Online Domain-Adaptation of a Pre-Trained Cascade of Classifiers	Vidit Jain (Yahoo! Labs); Eric Learned-Miller;
63	Coupled Information-Theoretic Encoding for Face Photo-Sketch Recognition	Wei Zhang (CUHK); Xiaogang Wang (The Chinese University of Hong Kong); Xiaoou Tang;
84	Image Ranking and Retrieval Based on Multi-Attribute Queries	Behjat Siddiquie (University of Maryland); Rogerio Feris; Larry Davis;
108	Glare Encoding of High Dynamic Range Images	Mushfiqur Rouf (University of British Columbia); Rafal Mantiuk (Bangor University); Wolfgang Heidrich; Matthew Trentacoste (University of British Columbia); Cheryl Lau (University of British Columbia)
118	Wide-angle Micro Sensors for Vision on a Tight Budget	Sanjeev Koppal; Todd Zickler; Ioannis Gkioulekas (Harvard University)
189	Recognizing Human Actions by Attributes	Jingen Liu (UMich)
220	Space-Time Super-Resolution from a Single Video	Oded Shahar (The Weizmann Institute of Science); Alon Faktor (The Weizmann Institute of Science); Michal Irani;
247	Occlusion Boundary Detection and Figure/Ground Assignment from Optical Flow	Patrik Sundberg (UC Berkeley); Jitendra Malik (UC Berkeley); Michael Maire (California Institute of Technology); Pablo Arbelaez; Thomas Brox (Albert-Ludwigs-University Freiburg)
260	Accelerated Low-Rank Visual Recovery by Random Projection	Yadong Mu (NUS, Singapore); Jian Dong; Xiaotong Yuan (NUS.EDU.SG); Ju Sun (National Uni. of Singapore); Shuicheng Yan;
346	Multiobject Tracking as Maximum Weight Independent Set	William Brendel (Oregon State University); Mohamed Amer (Oregon State University); Sinisa Todorovic;
364	Internal Statistics of a Single Natural Image	Maria Zontak (The Weizmann Institute of Science); Michal Irani;
382	FlowBoost - Appearance Learning from Sparsely Annotated Video	Karim Ali (EPFL); Francois Fleuret (Idiap Research Institute); David Hasler;
461	Scale Invariant cosegmentation for image groups	Lopamudra Mukherjee (Univ of Wisconsin Whitewater); Vikas Singh; Jiming Peng (University of Illinois Urbana Champaign)
474	Markerless Motion Capture of Interacting Characters Using Multi-view Image Segmentation	Yebin Liu (Max Planck Institute); Carsten Stoll (Max-Planck-Institut für Informatik); Juergen Gall; Hans-Peter Seidel (MPI Informatik); Christian Theobalt;
498	Large-Scale Live Active Learning: Training Object Detectors with Crawled Data and Crowds	Sudheendra Vijayanarasimhan; Kristen Grauman;
502	Iterative Quantization: A Procrustean Approach to Learning Binary Codes	Yunchao Gong (UNC Chapel Hill); Svetlana Lazebnik (University of North Carolina at Chapel Hill)
521	Contour Based Joint Clustering of Multiple Segmentations	Daniel Glasner (Weizmann Institute of Science); Shiv Vitaladevuni (Raytheon BBN Technologies); Ronen Basri;
586	From 3D Scene Geometry to Human Workspace	Abhinav Gupta; Scott Satkin (CMU); Alyosha Efros; Martial Hebert;
656	Describing Images: Understanding and Generating Image Descriptions	Girish Kulkarni (Stony Brook University); Visruth Premraj (Stony Brook University); Sagnik Dhar (Stony Brook University); Siming Li (Stony Brook University); Alexander Berg ; Yejin Choi (Stony Brook University); Tamara Berg (Stony Brook University)
697	Sparsity-based Image Denoising via Dictionary Learning and Structural Clustering	Weisheng Dong; Xin Li (WVU)
783	Stacked Convolutional Independent Subspace Analysis for Action Recognition	Quoc Le (Stanford University); Will Zou (Stanford University ); Serena Yeung (Stanford University); Andrew Ng (Stanford University)
791	Sparse Approximated Nearest Points for Image Set Classification	Yiqun Hu (University of Western Australia); Ajmal Mian (University of Western Australia); Robyn Owens (University of Western Australia)
838	Intrinsic Dense 3D Surface Tracking	Yun Zeng; Chaohui Wang (Ecole Centrale Paris/INRIA); Yang Wang; David Gu; Dimitris Samaras; Nikos Paragios;
859	Compact Hashing with Joint Optimization of Search Accuracy and Time	Junfeng He (Columbia University); Regunathan Radhakrishnan; Shih-Fu Chang; Claus Bauer;
891	Boundary Preserving Dense Local Regions	Jaechul Kim (University of Texas at Austin); Kristen Grauman;
912	Image Retrieval with Geometry-Preserving Visual Phrases	Yimeng Zhang (Cornell University); Zhaoyin Jia (Cornell University); Tsuhan Chen;
930	Uncovering Vein Patterns from Color Skin Images for Forensic Analysis	Chaoying Tang (Nanyang Technological Univ.); Adams Wai Kin Kong (Nanyang Technological University ); Noah Craft (Los Angeles Biomedical Research Institute)
972	Rectification and 3D reconstruction of Curved Document Images	Yuandong Tian (Carnegie Mellon University); Srinivasa Narasimhan;
1187	Earth Mover’s Prototypes: a Convex Learning Approach for Discovering Activity Patterns in Dynamic Scenes	Elisa Ricci (Fondazione Bruno Kessler); Gloria Zen (Fondazione Bruno Kessler)
1193	Three-Dimensional Kaleidoscopic Imaging	Ilya Reshetouski (Saarland University); Alkhazur Manakov (Saarland University); Hans-Peter Seidel (MPI Informatik); Ivo Ihrke;
1200	Scale and Rotation Invariant Matching Using Linearly Augmented Trees	Hao Jiang (Boston College); Tai-Peng Tian (Boston University); Stan Sclaroff (Boston University)
1234	Submodularity beyond submodular energies: coupling edges in graph cuts	Stefanie Jegelka (Max Planck Institute); Jeff Bilmes;
1238	From Partial Shape Matching through Local Deformation to Robust Global Shape Similarity for Object Detection	Tianyang Ma (Temple University); LonginJan Latecki;
1240	A Non-convex Relaxation Approach to Sparse Dictionary Learning	Jianping Shi (Zhejiang University); Xiang Ren (Zhejiang University); Jingdong Wang; Guang Dai (ZJU); Zhihua Zhang;
1270	Analytical Projection Model for Non-Central Catadioptric Cameras with Quadric Mirrors	Amit Agrawal; Yuichi Taguchi (Mitsubishi Electric Research Labs); Srikumar Ramalingam (MERL)
1277	Kernelized Structural SVM Learning for Supervised Object Segmentation	Luca Bertelli (Google); Tianli Yu (Google Inc.); Diem Vu (Google Inc.); Salih Gokturk (Google Inc)
1294	A Theory of Differential Photometric Stereo for General Isotropic BRDFs	Jiamin Bai (UC Berkeley); Manmohan Chandraker (UC Berkeley); Ravi Ramamoorthi (UC Berkeley)
1310	Parsing Human Motion with Structured Ensembles of Stretchable Models	Ben Sapp; David Weiss (University of Pennsylvania); Ben Taskar;
1341	A Bayesian Approach to Adaptive Video Super Resolution	Ce Liu (Microsoft Research New England); Deqing Sun;
1379	Principal Regression Analysis	Jason Saragih (CSIRO)
1420	Discrete-Continuous Optimization for Large-scale Structure from Motion	David Crandall (Indiana University); Andrew Owens (MIT); Noah Snavely; Daniel Huttenlocher;
1491	Active Learning for Piecewise Planar 3D Reconstruction	Adarsh Kowdle (Cornell University); Yao-Jen Chang (Cornell University); Andrew Gallagher; Tsuhan Chen;
1496	A generative model for 3D urban scene understanding from movable platforms	Andreas Geiger (Karlsruhe Institute of Technology); Martin Lauer (Karlsruhe Institute of Technology); Raquel Urtasun;
1549	A Study of Nesterov’s Scheme for Lagrangian Decomposition and MAP Labeling	Bogdan Savchynskyy (Heidelberg University); Jörg Kappes (Heidelberg University); Stefan Schmidt (Heidelberg University); Christoph Schnörr;
1632	Stable Multi-Target Tracking in Real-Time Surveillance Video	Ben Benfold (University of Oxford); Ian Reid (University of Oxford)
1633	A Coarse-to-fine approach for fast deformable object detection	Marco Pedersoli (Univ. Autònoma de Barcelona); Andrea Vedaldi (Oxford); Jordi Gonzàlez (Univ. Autònoma de Barcelona)
1713	Nonlinear Shape Manifolds as Shape Priors in Level Set Segmentation and Tracking	Victor Prisacariu (University of Oxford); Ian Reid (University of Oxford)
1768	What You Saw is Not What You Get: Domain Adaptation Using Asymmetric Kernel Transforms	Brian Kulis; Kate Saenko; Trevor Darrell (ICSI, UC Berkeley)
1781	Separating Reflective and Fluorescent Components of An Image	Cherry Zhang (University of Waterloo); Imari Sato;
1798	Recognition Using Visual Phrases	Ali Farhadi (UIUC); Mohammad Amin Sadeghi (University of Illinois at Urbana-Champaign)
1868	Single-Image Shadow Detection and Removal using Paired Regions	Ruiqi Guo (UIUC); Qieyun Dai (UIUC); Derek Hoiem (UIUC)
1874	Automatic Photo-to-Terrain Alignment for the Annotation of Mountain Pictures	Lionel Baboud (MPI Informatik); Martin Cadik (MPI Informatik); Elmar Eisemann (MPI Informatik, Telecom ParisTech); Hans-Peter Seidel (MPI Informatik)
1890	Cross-View Action Recognition via View Knowledge Transfer	Jingen Liu (UMich)
1913	Robust Tracking Using Local Sparse Appearance Model and K-Selection	Baiyang Liu (Rutgers University); junzhou Huang (Rutgers University, CBIM); Casimir Kulikowski (Rutgers); Lin Yang (UMDNJ)
1961	Intrinsic Images Decomposition Using a Local and Global Sparse Representation of Reflectance	Li Shen (I2R); Chuohao Yeo (i2r.a-star.edu.sg)
1978	Articulated Pose Estimation with Flexible Mixtures-of-Parts	Yi Yang; Deva Ramanan;

ACCEPTED POSTER PAPERS
13	Efﬁcient approximations to the marginal likelihood in blind deconvolution	Anat Levin (Weizmann Institute of Science); Yair Weiss; Bill Freeman; Fredo Durand (MIT)
14	Natural Image Denoising: Optimality and Inherent Bounds	Anat Levin (Weizmann Institute of Science); Boaz Nadler (Weizmann Inst of Science)
15	A Sobolev-type Metric for Polar Active Contours	Maximilian Baust (CAMP, TU Munich); Anthony J. Yezzi; Gozde Unal (Sabanci University); Nassir Navab (CAMP, TU Munich)
18	Multi-target Tracking by Continuous Energy Minimization	Anton Andriyenko (TU Darmstadt); Konrad Schindler (ETH Zurich)
24	Are Sparse Representations Really Relevant for Image Classification?	Roberto Rigamonti (EPFL); Matthew Brown (EPFL); Vincent Lepetit;
45	Noise Resistant Graph Ranking for Improved Web Image Search	Wei Liu (Columbia University); Yu-Gang Jiang (Columbia University); Jiebo Luo; Shih-Fu Chang;
49	Learning Effective Human Pose Estimation from Inaccurate Annotation	Sam Johnson (University of Leeds); Mark Everingham;
51	Shape Grammar Parsing via Reinforcement Learning	Olivier Teboul (Ecole Centrale Paris); Iasonas Kokkinos; Panagiotis Koutsourakis (Ecole Centrale Paris); Loic Simon (ECP); Nikos Paragios;
55	Truncated Message Passing	Justin Domke;
57	Structured Light 3D Scanning Under Global Illumination	Mohit Gupta; Amit Agrawal; Ashok Veeraraghavan; Srinivasa Narasimhan;
59	Adaptive Shape Composition: A New Framework for Shape Prior Modeling	Shaoting Zhang (Rutgers University); junzhou Huang (Rutgers University, CBIM); Yiqiang Zhan (Siemens); Dimitris Metaxas;
60	Entropy Rate Superpixel Segmentation	Ming-Yu Liu (Umd.edu,merl.com); Oncel Tuzel (MERL); Srikumar Ramalingam (MERL); Rama Chellappa (UMD)
72	Affinity Learning on a Tensor Product Graph with Applications to Shape and Image Retrieval	Xingwei Yang (Temple University); LonginJan Latecki;
73	Scene Shape from Textures of Objects	Nadia Payet (Oregon State University); Sinisa Todorovic;
77	What Makes a Chair a Chair?	Helmut Grabner; Juergen Gall; Luc VanGool;
80	Recovery of Corrupted Low-Rank Matrices via Half-Quadratic based Nonconvex Minimization	Ran He (Institute of Automation Chines); zhenan sun ( Institute of Automation Chinese Academy of Sciences); Tieniu Tan; Wei-Shi Zheng (Queen Mary University of London)
86	Contextualizing Object Detection and Classification	Zheng Song (National University of Singapo); Qiang Chen (National Univ. of Singapore); Zhongyang Huang (Panasonic Singapore Laboratories); Yang Hua (PSL); Shuicheng Yan;
96	A fully automated greedy square jigsaw puzzle solver	Dolev Pomeranz (Ben Gurion University); Michal Shemesh (Ben Gurion University); Ohad Ben-Shahar (Ben-Gurion University)
103	Efficient MCMC Sampling with Implicit Shape Representations	Jason Chang (MIT); John Fisher III (MIT)
104	A Complete Statistical Inverse Ray Tracing Approach to Multi-view Stereo	Shubao Liu (Brown University); David Cooper (Brown University)
112	A Robust Method for Vector Field Learning with Application to Mismatch Removing	Ji Zhao (Huazhong Univ of Sci & Tech); Ma Jiayi;
116	Optimal Similarity Registration of Volumetric Images	Effrosyni Kokiopoulou (ETH Zurich); Michail Zervos (University of Athens, Department of Informatics and Telecommunications); Daniel Kressner (ETH Zurich, Seminar for Applied Mathematics); Nikos Paragios;
123	Inertial sensor-aligned visual feature descriptors	Daniel Kurz (Metaio); Selim Ben Himane (metaio GmbH)
127	Visual textures as realizations of multivariate log-Gaussian Cox processes	Huu-Giao Nguyen (Telecom Bretgane); Ronan Fablet (Institut Telecom / Telecom Bretagne); Jean-Marc Boucher (Institut Telecom / Telecom Bretagne)
135	GraphTrack: Faster than Realtime Tracking in Videos	Brian Amberg (University of Basel); Thomas Vetter;
155	Discriminative Image Warping with Attribute Flow	Weiyu Zhang (University of Pennsylvania); Praveen Srinivasan; Jianbo Shi;
157	Interreflections removal for photometric stereo by using spectrum-dependent albedo	Miao Liao (University of Kentucky); Xinyu Huang (North Carolina Central University); Ruigang Yang (University of Kentucky)
159	Global Contrast based Salient Region Detection	Ming-Ming Cheng (Tsinghua University); Guo-Xin Zhang (Tsinghua University); Niloy Mitra (IIT Delhi / KAUST); Xiaolei Huang; Shi-Min Hu (Tsinghua University)
162	Towards a practical lipreading system	Ziheng Zhou (University of Oulu); Matti Pietik; Guoying Zhao (University of Oulu, Finland)
164	Multiview Specular Stereo Reconstruction of Large Mirror Surfaces	Jonathan Balzer (KAUST); Sebastian Hoefer; Juergen Beyerer;
168	Unbiased Look at Dataset Bias	Antonio Torralba; Alyosha Efros;
169	Partial similarity based nonparametric scene parsing in certain environment	Honghui Zhang (HKUST); Long Quan;
174	Majorization-Minimization mixture model determination in image segmentation	Giorgos Sfikas (University of Strasbourg); Christophoros Nikou (University of Ioannina); Nikos Galatsanos (University of Patras); Christian Heinrich (University of Strasbourg)
176	PLS Based Multi-Modal Face Recognition	Abhishek Sharma (University of Maryland CP); David Jacobs (UMIACS)
180	Exploring Aligned Complementary Image Pair for Blind Motion Deblurring	Wen Li (School of Electronics and Info); Jun Zhang (School of Electronics and Information Engineering, Beihang University); Qionghai Dai (Tsinghua University)
185	A Branch and Contract Algorithm For Globally Optimal Fundamental Matrix Estimation	Yinqiang Zheng (Tokyo Institute of Technology); Shigeki Sugimoto (Tokyo Institute of Technology); Masatoshi Okutomi;
198	Learning A Discriminative Dictionary for Sparse Coding via Label Consistent K-SVD	Zhuolin Jiang (University of Maryland); Zhe Lin (Adobe Systems, Inc.); Larry Davis;
209	Efficient Subwindow Search with Submodular Score Functions	Senjian An (Curtin University); Patrick Peursum; Wanquan Liu (curtin university); Svetha Venkatesh;
211	Foreground-Background Segmentation using Iterated Distribution Matching	Viet Pham (University of Tokyo); Keita Takahashi (The University of Tokyo); Takeshi Naemura (The University of Tokyo)
212	Shared Parts for Deformable Part-based Models	Patrick Ott (University of Leeds)
216	NonLinear Refinement of Structure from Motion Reconstruction by Taking Advantage of a Partial Knowledge of the Environment	Mohamed Tamaazousti (CEA LIST); Vincent Gay-Bellile; Sylvie Naudet Colette (CEA LIST); steve bourgeois; michel dhome;
219	Effective 3D Object Detection and Regression Using Probabilistic Segmentation Features in CT Images	Le Lu (Siemens ); Jinbo Bi (University of Connecticut); Matthias Wolf; Marcos Salganicoff;
227	Submodular Decomposition Framework for Inference in MRF with Global Constraints	Dmitry Vetrov; Anton Osokin (Moscow State University); Vladimir Kolmogorov;
235	Adapting an Object Detector by Considering the Worst Case: a Conservative Approach	Guang Chen (University of MIssouri); TonyX. Han;
240	AdaBoost on Low-Rank PSD Matrices for Metric Learning with Applications in Computer Aided Diagnosis	Jinbo Bi (University of Connecticut); Dijia Wu; Le Lu (Siemens ); Meizhu Liu; Yimo Tao; Matthias Wolf;
249	A Closed Form Solution to Robust Subspace Estimation and Clustering	Paolo Favaro; René Vidal; Avinash Ravichandran (Johns Hopkins University)
250	Detection Free Tracking: Exploiting Motion and Topology for Segmenting and Tracking under Entanglement.	Katerina Fragkiadaki (University of Pennsylvania); Jianbo Shi;
251	Piecing Together the Segmentation Jigsaw using Context	Xi Chen (University of Maryland); Arpit Jain (University of Maryland); Abhinav Gupta; Larry Davis;
254	Combining Randomization and Discrimination for Fine-Grained Image Categorization	Bangpeng Yao (Stanford University); Aditya Khosla; Li Fei-Fei;
263	Geometric $\ell_p$-norm Feature Pooling for Image Classification	Jiashi Feng (NUS); Bingbing Ni; Qi Tian (University of Texas at San Antonio); Shuicheng Yan;
267	Noise Suppression in Low-Light Images through Joint Denoising and Demosaicing	Priyam Chatterjee (UC Santa Cruz); Neel Joshi; Sing Bing Kang (Microsoft Research); Yasuyuki Matsushita;
276	Fast Cost-Volume Filtering for Visual Correspondence and Beyond	Christoph Rhemann (Vienna University of Technolog); Asmaa Hosni (Vienna University of Technology); Michael Bleyer (Vienna University of Technology); Carsten Rother; margrit Gelautz (Vienna University of Technology)
277	Hello neighbor: accurate object retrieval with k-reciprocal nearest neighbors	Qin Danfeng (ETH Zurich); Stephan Gammeter (ETH Zurich); Lukas Bossard (ETH Zurich); Till Quack; Luc VanGool;
279	Motion Denoising with Application to Time-lapse Photography	Michael Rubinstein (MIT CSAIL); Ce Liu (Microsoft Research New England); Bill Freeman;
282	Efficient Training for Pairwise or Higher Order MRFs via Dual Decomposition	Nikos Komodakis;
287	Recovering Shape from a Single Image of a Mirrored Surface from Curvature Constraints	Marshall Tappen (UCF)
295	Instantly Telling What Happens in a Video Sequence Using Light Features	Liang Wang (Harbin Institute of Technology); Yizhou Wang; Tingting Jiang (School of EECS, Peking University); Wen Gao (Peking University);
297	Locality-Sensitive Support Vector Machine by Exploring Local Feature Correlation for Web Image Annotation	Guo-Jun Qi (ECE, UIUC); Qi Tian (University of Texas at San Antonio); Thomas Huang (UIUC)
298	Image Annotation via Preferential Random Walk on Bi-relational Graph of Images and Semantic Labels	Hua Wang (Univ. of Texas at Arlington); Heng Huang (University of Texas at Arlington, Department of Computer Science and Engineering); Chris Ding;
300	Learning structured prediction models for interactive image labeling	Thomas Mensink (XRCE); Jakob Verbeek; Gabriela Csurka (XRCE)
301	Joint Face Alignment with A Generic Deformable Face Model	Cong Zhao (Chinese University of Hong Kon); Wai-Kuen Cham; Xiaogang Wang (The Chinese University of Hong Kong)
307	Regression-Based Label Fusion for Multi-Atlas Segmentation	Hongzhi Wang (University of Pennsylvania); Jung Wook Suh; John Pluta; Murat Altinay; Paul Yushkevich;
308	Energy Based Multiple Model Fitting for Non-Rigid Structure from Motion	Chris Russell; Joao Fayad (Queen Mary, UoL); Lourdes Agapito;
310	How does Person Identity Recognition Help Multi-Person Tracking?	Cheng-Hao Kuo (USC); Ram Nevatia;
311	Aggregating Gradient Distributions into Intensity Orders: A Novel Local Image Descriptor	Bin Fan; Fuchao Wu; Zhanyi Hu;
314	Multi-agent event recognition in structured scenarios	Vlad Morariu (University of Maryland); Larry Davis;
324	Establishing Feature Correspondences via Hyper-graph Matching Using Reweighted Random Walks	Jungmin Lee (Seoul National University); Minsu Cho; Kyoung Mu Lee (Seoul National Uniersity)
327	High-quality shape from multi-view stereo and shading under general illumination	Chenglei Wu (Max Planck Institut Informatik); Bennett Wilburn; Yasuyuki Matsushita; Christian Theobalt;
331	Predicting Image Matching using Affine Distortion Models	Daniel Fleck (American University); Zoran Duric;
337	Sparse Concept Coding for Visual Analysis	Deng Cai; Xiaofei He;
338	Fast and High-Performance Template Matching Method	Alexander Sibiryakov (Mitsubishi Electric)
339	High-Frequency Shape and Albedo from Shading using Natural Image Statistics	Jonathan Barron (UC Berkeley); Jitendra Malik (UC Berkeley)
341	Robust Sparse Coding for Face Recognition	Meng Yang (The Hong Kong Polytechnic University); Lei Zhang (The Hong Kong Polytechnic University)
345	Foreground Segmentation of Live Videos using Locally Competing 1SVMs	Minglun Gong; Li Cheng (Bioinformatics Institute)
348	Extracting Vanishing Points across Multiple Views	Michael Hornacek (VRVis Research Center); Stefan Maierhofer (VRVis)
352	Multifactor Analysis Based on Factor-Dependent Geometry	Sung Won Park (Carnegie Mellon University)
353	Object Association Across PTZ Cameras using Logistic MIL	Karthik Sankaranarayanan (Ohio State University); Jim Davis;
361	Query-Specific Visual Semantic Spaces for Web Image Re-ranking	Ke Liu (CUHK); Xiaogang Wang (The Chinese University of Hong Kong)
363	Non-negative Local Coordinate Factorization for Image Representation	Yan Chen (Zhejiang University); Xiaofei He;
376	Discriminative Tag Learning on YouTube Videos with Latent Sub-tags	Weilong Yang (Simon Fraser University); George Toderici (Google Inc.)
388	Simultaneous Dimensionality Reduction and Human Age Estimation via Kernel Partial Least Squares Regression	Guodong Guo; Guowang Mu (Hebei University of Technology)
390	Symmetric Piecewise Planar Object Reconstruction from a Single Image	Tianfan XUE (IE Department, CUHK); Jianzhuang LIU (CUHK)
395	Fast Unsupervised Ego-Action Learning for First-person Sports Videos	Kris Kitani (UCSD); Yoichi Sato; Takahiro Okabe; Akihiro Sugimoto (NII)
405	action recognition by dense trajectories	Heng Wang (Chinese Academy of Sciences); Alexander Kläser; Cordelia Schmid; Cheng-Lin Liu (CASIA)
407	Gated Classifiers: Boosting under High Intra-Class Variation	Oscar Danielsson (KTH); Babak Rasolzadeh (KTH); Stefan Carlsson (KTH)
408	Radiometric Calibration by Transform Invariant Low-rank Structure	Joon-Young Lee (KAIST); Boxin Shi (The University of Tokyo); Yasuyuki Matsushita; InSo Kweon; Katsushi Ikeuchi;
426	Registration for 3D Surfaces with Large Deformations Using Quasi-Conformal Curvature Flow	Wei Zeng (Stony Brook University); David Gu;
428	Proposal Generation for Object Detection using Cascaded Ranking SVMs	Ziming Zhang (Oxford Brookes University); Jonathan Warrell; Philip Torr (Oxford Brookes University)
429	Clues from the Beaten Path: Location Estimation with Bursty Sequences of Tourist Photos	Chao-Yeh Chen (University of Texas at Austin); Kristen Grauman;
430	Learning photographic global tonal adjustments with a database of input/output image pairs	Vladimir Bychkovsky (MIT / CSAIL); Sylvain Paris; Eric Chan (Adobe Systems Inc.); Fredo Durand (MIT)
431	Enhancing by Saliency-guided Decolorization	Codruta Ancuti (Hasselt University); Cosmin Ancuti (Hasselt University); Philippe Bekaert (Hasselt University)
437	From Co-saliency to Co-segmentation: An Efficient and Fully Unsupervised Energy Minimization Model	Kai-Yueh Chang (National Tsing Hua University); Tyng-Luh Liu; Shang-Hong Lai (NTHU)
438	Optimal Spatio-Temporal Path Discovery for Video Event Detection and Localization	Du Tran (NTU); Junsong Yuan (Nanyang Technological University)
439	Continuously Tracking and See-through Occlusion Based on A New Hybrid Synthetic Aperture Imaging Model	Tao Yang (Nrothwestern Polytechnic Univ.); Yanning Zhang (NWPU); Xiaomin Tong (School of Computer Science, Northwestern Polytechnical University); Xiaoqiang Zhang (School of Computer Science, Northwestern Polytechnical University); Rui Yu (School of Computer Science, Northwestern Polytechnical University)
445	High Resolution Multispectral Video Capture with a Hybrid Camera System	Xun Cao (Tsinghua University); Xin Tong; Qionghai Dai (Tsinghua University); Stephen Lin;
451	A Polar Representation of Motion and Implications for Optical Flow	Yair Adato (Ben Gurion ); Todd Zickler; Ohad Ben-Shahar (Ben-Gurion University)
463	Minimum Error Bounded Efficient L1 Tracker with Occlusion Detection	Xue Mei; Haibin Ling; Yi Wu (Temple University)
464	An $L_1$-based variational model for Retinex theory and its application to medical images	Wenye Ma (UCLA); Jean-Michel Morel (CMLA); Stanley Osher (UCLA); Aichi Chien (UCLA)
470	Simulating Human Saccadic Scanpaths on Natural Images	Wei Wang (Graduate University of Chinese Academy and Sciences); Cheng Chen; Yizhou Wang; Tingting Jiang (School of EECS, Peking University); Fang Fang; Yuan Yao;
475	Time and Space Efficient Spectral Clustering via Column Sampling	Mu Li (Shanghai Jiao Tong University); Xiao-Chen Lian; James Kwok (HKUST); Bao-Liang Lu;
476	Spatial-DiscLDA for Visual Recognition	Zhenxing Niu (Xidian university); Gang Hua; Xinbo Gao; Qi Tian (University of Texas at San Antonio)
478	Least Squares Surface Reconstruction from Gradients: Direct Algebraic Methods with Spectral, Tikhonov, and Constrained Regularization	Matthew Harker (University of Leoben); Paul O'Leary (University of Leoben)
487	A Two-Stage Denoising Approach for Seeing ThroughWater Clearly	Omar Oreifej (University of Central Florida); Guang Shu (University of Central Florida); Teresa Pace (University of Central Florida); Mubarak Shah;
497	CrossTrack: Robust 3D Tracking from Two Cross-Sectional Views	Mohamed Hussein; Fatih Porikli;
499	A Deformation and Lighting Insensitive Metric for Face Recognition	Anne Jorstad (University of Maryland); David Jacobs; Alain Trouvé (Ecole Normale Superieure de Cachan)
506	Constructing Image Panoramas using Dual-Homography Warping	Junhong GAO (NUS); Michael Brown; Seon Joo Kim;
512	Sparse Reconstruction Cost for Abnormal Event Detection	Yang Cong (Nanyang Technological of Unive); Junsong Yuan (Nanyang Technological University); Ji Liu (University of Wisconsin–Madison);
515	Scenario-Based Video Event Recognition by Constraint Flow	Suha Kwak (POSTECH); Bohyung Han (POSTECH); Joon Han (POSTECH)
523	Ordinal Hyperplanes Ranker with Cost Sensitivities for Age Estimation	Kuang-Yu Chang (Academia Sinica); Chu-Song Chen; Yi-Ping Hung (NTU)
533	Global temporal registration of multiple non-rigid surface sequences	Peng Huang (University of Surrey); Adrian Hilton; Chris Budd (University of Surrey)
538	Collaborative Personalization of Image Enhancement	Juan Caicedo (Universidad Nacional de Colomb); Ashish Kapoor; Sing Bing Kang (Microsoft Research)
541	Learning Temporally Consistent Rigidities	Jean-Sebastien Franco (Grenoble Universities); Edmond Boyer;
543	Scalable Multi-class Object Detection	Nima Razavi (ETH Zurich); Juergen Gall; Luc VanGool;
553	Scene Flow Estimation by Growing Correspondence Seeds	Jan Cech (INRIA); Jordi Sanchez-Riera (INRIA); Radu Horaud;
554	Pose-Robust Recognition of Low-Resolution Face Images	Soma Biswas (University of Notre Dame); Gaurav Aggarwal; Patrick Flynn;
568	Learning to Recognize Objects in Egocentric Activities	Alireza Fathi (Georgia Institute of Technolog); Xiaofeng Ren; James Rehg;
571	Importance Filtering for Image Retargeting	Yuanyuan Ding (Epson Research and Development); Jing Xiao (Epson R& D)
576	Learning a Blind Measure of Perceptual Image Quality	Huixuan Tang (University of Toronto); Neel Joshi; Ashish Kapoor;
578	A Scalable Dual Approach to Semidefinite Metric Learning	Chunhua Shen (NICTA); Junae Kim (Australian National University); Lei Wang (Australian National University)
590	Making the Right Moves: Guiding Alpha-Expansion using Local Primal-Dual Gaps	Dhruv Batra; Pushmeet Kohli;
592	Finding the Weakest Link in Person Detectors	Devi Parikh; Larry Zitnick;
593	Interactively Building a Discriminative Vocabulary of Nameable Attributes	Devi Parikh; Kristen Grauman;
596	Inference for Order Reduction in MRFs	Andrew Gallagher; Dhruv Batra; Devi Parikh;
597	Learning and Matching Multiscale Template Descriptors for Real-Time Detection, Localization and Tracking	Taehee Lee (UCLA); Stefano Soatto;
599	Multi-layer Group Sparse Coding -- for Concurrent Image Classification and Annotation	Shenghua Gao (Nanyang Technological Univ.); Liang-Tien Chia (Nanyang Technological University); Ivor W. Tsang;
605	Topologically-Robust 3D Shape Matching Based on Diffusion Geometry and Seed Growing	Avinash Sharma (INRIA); Radu Horaud; Jan Cech (INRIA); Edmond Boyer;
615	Fusion of GPS and Structure-from-Motion using Constrained Bundle Adjustments	Maxime Lhuillier;
618	High-resolution Hyperspectral Imaging via Matrix Factorization	Rei Kawakami; John Wright; Yu-Wing Tai (KAIST); Yasuyuki Matsushita; Moshe Ben-Ezra (Microsoft Research Asia); Katsushi Ikeuchi;
619	Real Time Head Pose Estimation with Random Regression Forests	Gabriele Fanelli (ETHZ); Juergen Gall; Luc VanGool;
628	Random Field Topic Model for Semantic Region Analysis in Crowded Scenes from Tracklets	Bolei Zhou (CUHK); Xiaogang Wang (The Chinese University of Hong Kong)
630	Edgel Inverted Index for Large-Scale Sketch-based Image Search	Yang Cao (Shanghai Jiao Tong University); Wang Changhu (microsoft); Zhang Liqing (Shanghai Jiao Tong University); Lei Zhang (Microsoft Research Asia)
631	Rank-SIFT: Learning to Rank Local Interest Points	Bing Li (Shanghai JiaoTong Univerisity); Rong Xiao; Zhiwei Li (Microsoft); Rui Cai (Microsoft Research, Asia); Bao-Liang Lu; Lei Zhang (Microsoft Research Asia)
632	Semantic structure from motion	Sid Ying-Ze Bao (University of Michigan); Silvio Savarese;
637	High Precision localization System with Visual Landmarks Fused With Range Data	Zhiwei Zhu (Sarnoff Corporation)
642	A Novel Parametrization of the Perspective-Three-Point Problem for a Direct Computation of Absolute Camera Position and Orientation	Laurent Kneip (ETH Zurich); Davide Scaramuzza; Roland Siegwart (ETH Zurich)
652	Estimating Motion and Size of Moving Non-Line-of-Sight Objects in Cluttered Environments	Rohit Pandharkar (MIT); Andreas Velten (MIT); Andrew Bardagjy (MIT); Ramesh Raskar; Moungi Bawendi; Ahmed Kirmani; Everett Lawson (MIT);
660	High Level Describable Attributes for Predicting Aesthetics and Interestingness	Sagnik Dhar (Stony Brook University); Vicente Ordonez (Stony Brook University); Tamara Berg (Stony Brook University)
662	Who are you with and where are you Going?	Kota Yamaguchi (Stony Brook University); Alexander Berg ; Luis Ortiz; Tamara Berg (Stony Brook University)
665	Using Global Bag of Features Models in Random Fields for Joint Categorization and Segmentation of Objects	Dheeraj Singaraju; René Vidal;
666	Joint Segmentation and Classification of Human Actions in Video	MinhHoai Nguyen; Zhen-zhong Lan (Carnegie Mellon University); Fernando DelaTorre;
670	Face Image Retrieval by Shape Manipulation	Brandon Smith (University of Wisconsin-Madiso); Shengqi Zhu (University of Wisconsin-Madison); Li Zhang;
678	Adequate Reconstruction of Transparent Objects on a Shoestring Budget	Sai-Kit Yeung (UCLA); Tai-Pang Wu; Chi-keung Tang; Tony F. Chan (HKUST); Stanley Osher (UCLA)
680	Face Illumination Transfer through Edge-preserving Filters	Xiaowu Chen (Beihang University); Mengmeng Chen (Beihang University); Xin Jin (Beihang University); Qinping Zhao (Beihang University)
683	Visual and Semantic Similarity in ImageNet	Thomas Deselaers (ETH Zurich/Google); Vittorio Ferrari;
686	Learning Transformation Invariant Representations from weakly-related Videos	Christian Leistner (icg tugraz); Martin Godec; Samuel Schulter; Manuel Werlberger; Amir Saffari; Horst Bischof;
692	Mining Discriminative Co-occurrence Patterns for Visual Recognition	Junsong Yuan (Nanyang Technological University); Ming Yang (NEC Laboratories America); Ying Wu (Northwestern University)
694	Large-scale image classification: fast feature extraction and SVM training	Yuanqing Lin (NEC Labs America); Fengjun Lv (NEC Labs America); Shenghuo Zhu (NEC Laboratories America); Ming Yang (NEC Laboratories America); Timothee Cour (NEC Labs America); Kai Yu; Liangliang Cao (UIUC); Thomas Huang (UIUC)
698	Blur kernel estimation using the Radon Transform	Taeg Sang Cho (MIT CSAIL); Sylvain Paris; Bill Freeman; Berthold Horn (MIT CSAIL)
700	Global Stereo Matching Leveraged by Sparse Ground Control Points	Liang Wang; Ruigang Yang (University of Kentucky)
712	Correspondence Driven Adaptation for Human Profile Recognition	Ming Yang (NEC Laboratories America); Shenghuo Zhu (NEC Laboratories America); Fengjun Lv (NEC Laboratories America); Kai Yu;
713	Translation Symmetry Detection in a Fronto-parallel View	Peng ZHAO (HKUST); Long Quan;
714	Real-time visual tracking with compressed sensing	Hanxi Li (ANU); Chunhua Shen (NICTA); Qinfeng Shi (University of Adelaide)
715	Image Classification by Non-Negative Sparse Coding, Low-Rank and Sparse Decomposition	Chunjie Zhang (Institute of Automation); Jing Liu; Qi Tian (University of Texas at San Antonio); changsheng Xu; Hanqing Lu; Songde Ma;
722	Max-margin Clustering: Detecting Margins from Projections of Points on Lines	Raghuraman Gopalan (University of Maryland); Jagan Sankaranarayanan;
725	Affine-invariant diffusion geometry for the analysis of deformable 3D shapes	Dan Raviv (Technion); Alexander Bronstein (Dept. of Electrical Engineering, Tel Aviv University, Israel); Michael Bronstein (University of Lugano); Ron Kimmel (Technion - IIT); Nir Sochen;
732	Nonnegative Sparse Coding for Discriminative Semi-supervised Learning	Ran He (Institute of Automation Chines); Wei-Shi Zheng (Queen Mary University of London)
734	Random Forest Voting for Fast Action Search	Gang YU (Nanyang technological Univ); Junsong Yuan (Nanyang Technological University); Zicheng Liu;
735	Wavelet Belief Propagation for Large Scale Inference Problems	Ruxandra Lasowski (Max Planck Institute Informatik); Art Tevs (Max Planck Institute Informatik); Michael Wand (Max Planck Institute Informatik); Hans-Peter Seidel;
741	A pattern framework driven by the Hamming distance for structured light-based reconstruction with a single image	Xavier Maurice (Univsersity of Strasbourg)
746	Probabilistic Event Logic for Interval-Based and Holistic Event Recognition	William Brendel (Oregon State University); Alan Fern (Oregon State University); Sinisa Todorovic;
748	Non-negative Matrix Factorization as a Feature Selection Tool for Maximum Margin Classifiers	Mithun Gupta (GE); Jing Xiao (Epson R& D)
750	Action Recognition with Multiscale Spatio-Temporal Contexts	Jiang Wang (Northwestern University); Zhuoyuan Chen (Northwestern University); Ying Wu (Northwestern University)
765	An Associate-Predict Model for Face Recognition	Qi Yin; Jian Sun; Xiaoou Tang;
774	A Global Sampling Method for Alpha Matting	Kaiming He (CUHK); Christoph Rhemann (Vienna University of Technolog); Carsten Rother; Xiaoou Tang; Jian Sun;
784	Segment an Image by Looking into an Image Corpus	Xiaobai Liu (Hust.edu.cn); Jiashi Feng (NUS); Shuicheng Yan; Hai Jin (hust.edu.cn)
788	Connecting Non-Quadratic Variational Models and MRFs	Kevin Schelten (TU Darmstadt); Stefan Roth;
790	Tag Localization with Spatial Correlations and Joint Group Sparsity	Yang Yang (The University of Queensland); Yi Yang (The University of Queensland); Zi Huang (The University of Queensland); Heng Tao Shen (The University of Queensland); Feiping Nie (University of Texas, Arlington)
793	PClines - Line Detection Using Parallel Coordinates	Markéta Dubská (Brno University of Technology); Adam Herout (Brno University of Technology); Jiří Havel (Brno University of Technology)
794	Tracking 3D Human Pose with Large Root Node Uncertainty	Ben Daubney (Swansea); Xianghua Xie (Swansea)
802	Enforcing topological constraints in random field image segmentation	Chao Chen (IST Austria); Daniel Freedman (HP Labs Israel); Christoph Lampert (I.S.T. Austria)
803	High-Dimensional Signature Compression for Large-Scale Image Classification	Jorge Sanchez (CIII); Florent Perronnin;
805	Asymmetric Distances for Binary Embeddings	Albert Gordo (CVC / XRCE); Florent Perronnin;
813	Saliency Estimation Using a Non-Parametric Low-Level Vision Model	Naila Murray (Computer Vision Centre); Maria Vanrell; Xavier Otazu; C. Alejandro Parraga;
814	High Quality Intrinsic Images Using Optimization	Jianbing Shen (Beijing Institute ofTechnology); Xiaoshan Yang (Beijing Institute of Technology)
819	Evaluation of Background Subtraction Techniques for Video Surveillance	Sebastian Brutzer; Benjamin Hoeferlin (University of Stuttgart); Gunther Heidemann (University of Stuttgart)
822	Unsing Ripley's K-function to Improve Graph-Based Clustering Techniques	Kevin Streib (Ohio State University); Jim Davis;
827	Shape Estimation in Natural Illumination	Micah Johnson; Edward Adelson (MIT)
828	Online Environment Mapping	Jongwoo Lim; Jan-Michael Frahm; Marc Pollefeys;
830	Line-Based Relative Pose Estimation	Ali Elqursh (Rutgers University); Ahmed Elgammal;
854	Generalized Projection Based M-Estimator: Theory and Applications	Sushil Mittal (Rutgers University); Saket Anand (Rutgers University); Peter Meer (Rutgers University)
856	Efficient Track Linking Methods for Track Graphs Using Network-flow and Set-cover Techniques	Zheng Wu (Boston University); Margrit Betke; Thomas Kunz (Boston University)
857	Hierarchical Semantic Indexing for Large Scale Image Retrieval	Jia Deng (Princeton University); Alexander Berg (Stony Brook University); Li Fei-Fei;
858	Learning to Find Occlusion Regions	Ahmad Humayun (UCL); Oisin Mac Aodha (UCL); Gabriel Brostow;
868	Learning Hierarchical Poselets for Human Parsing	Yang Wang; Duan Tran (UIUC); Zicheng Liao (UIUC)
873	Learning Non-Local Range Markov Random Field for Image Restoration	Sun Jian (Xi'an Jiaotong University); Marshall Tappen;
874	Blind Deconvolution Using A Normalized Sparsity Measure	Dilip Krishnan (New York University); Rob Fergus;
875	Supervised Hypergraph Labeling	Toufiq Parag; Ahmed Elgammal;
879	Learning the Easy Things First: Self-Paced Visual Category Discovery	Yong Jae Lee (University of Texas at Austin); Kristen Grauman;
883	Online Detection of Unusual Events in Videos via Dynamic Sparse Coding	Bin Zhao (Carnegie Mellon University); Li Fei-Fei; Eric Xing;
889	Auto Directed Video Stabilization with Robust L1 Optimal Camera Paths	Matthias Grundmann; Vivek Kwatra; Irfan Essa;
892	From Region Similarity to Category Discovery	Carolina Galleguillos (U.C San Diego); Brian McFee (U.C San Diego); Serge Belongie (UCSD); Gert Lanckriet (U.C San Diego)
926	Deformation and Illumination Invariant Feature Point Descriptor	Francesc Moreno (Institut de Robotica i Informatica Industrial (UPC/CSIC))
929	Object Cosegmentation	Sara Vicente (UCL); Carsten Rother; Vladimir Kolmogorov;
932	Probabilistic Simultaneous Pose and Non-Rigid Shape Recovery	Francesc Moreno (Institut de Robotica i Informatica Industrial (UPC/CSIC)); Josep Porta (Institut de Robotica i Informatica Industrial (CSIC-UPC))
938	Projective Alignment of Range and Parallax Data	Miles Hansard (INRIA Rhone-Alpes); Radu Horaud; Michel Amat (INRIA Rhone-Alpes); Seungkyu Lee (SAIT)
942	Relative pose problem for non-overlapping surveillance cameras with known gravity vector	Branislav Micusik;
954	Particle Filter with State Permutations for Solving Image Jigsaw Puzzles	Xingwei Yang (Temple University); Nagesh Adluru; LonginJan Latecki;
962	An Analysis of Using High-Frequency Sinusoidal Illumination to Measure the 3D Shape of Translucent Objects	Michael Holroyd (University of Virginia); Jason Lawrence (University of Virginia)
968	Tracking Low Resolution Objects by Metric Preservation	Nan Jiang (HUST); Wenyu Liu (Huazhong University of Science and Technology); Ying Wu (Northwestern University); Heng Su (Tsinghua University)
969	Learning invariance through imitation	Graham Taylor; Ian Spiro (New York University); Rob Fergus; Christoph Bregler (NYU)
971	Aesthetic Quality Classification of Photographs Based on Color Harmony	Masashi Nishiyama (University of Tokyo); Takahiro Okabe; Imari Sato; Yoichi Sato;
973	Modeling the joint density of two images under a variety of transformations	Joshua Susskind (University of Toronto); Roland Memisevic; Geoffrey Hinton (University of Toronto); Marc Pollefeys;
974	P2C2: Programmable Pixel Compressive Camera for High Speed Imaging.	Dikpal Reddy (University of Maryland); Ashok Veeraraghavan;
975	Sharing Features Between Objects and Their Attributes	Sung Ju Hwang; Fei Sha; Kristen Grauman;
976	RUNE-Tag: a High Accuracy Fiducial Marker with Strong Occlusion Resilience	Filippo Bergamasco (Università Ca' Foscari Venezia); Andrea Albarelli; Andrea Torsello; Emanuele Rodola (Università Ca' Foscari Venezia)
979	Efficient Region Search for Object Detection	Sudheendra Vijayanarasimhan; Kristen Grauman;
980	Where's Waldo: Matching People in Images of Crowds	Rahul Garg (University of Washington); Deva Ramanan; Steve Seitz; Noah Snavely;
984	Monocular 3D Scene Understanding with Explicit Occlusion Reasoning	Christian Wojek (Max-Planck-Institute Informatics); Stefan Walk (TU Darmstadt); Stefan Roth; Bernt Schiele (MPI Informatics)
989	Camera Calibration with Lens Distortion from Low-rank Textures	Zhengdong Zhang (Microsoft Research Asi); Yasuyuki Matsushita; Yi Ma;
991	Structure from motion for scenes with large duplicate structures	Richard Roberts (Georgia Institute of Technology); Sudipta Sinha; Richard Szeliski; Drew Steedly;
997	Capturing Time-of-Flight Data with Confidence	Malcolm Reynolds (University College London); Jozef Doboš (University College London); Leto Peel (BAE Systems); Tim Weyrich (University College London); Gabriel Brostow;
1009	Repetition-based Dense Single-View Reconstruction	Changchang Wu (University of Washington at Se); Changchang Wu (University of Washtingon at Seattle); Jan-Michael Frahm; Marc Pollefeys;
1010	Multicore Bundle Adjustment	Changchang Wu (University of Washington at Se); Changchang Wu (University of Washtingon at Seattle); Sameer Agarwal; Brian Curless (University of Washtingon at Seattle); Steve Seitz;
1013	Learning-based Hypothesis Fusion for Robust Catheter Tracking in 2D X-ray Fluoroscopy	Wen Wu (Siemens Corporate Research); Terrence Chen (Siemens Corporate Research); Adrian Barbu; Peng Wang (Siemens Corporate Research); Norbert Strobel; Shaohua Zhou; Comaniciu Dorin;
1015	A Direct Formulation for Totally-corrective Multi-class Boosting	Chunhua Shen (NICTA); Zhihui Hao;
1017	Modeling Human Activities as Speech	Chia-Chih Chen (UT ECE); Jake Aggarwal;
1020	Is face recognition really a Compressive Sensing problem?	Qinfeng Shi (The University of Adelaide); Anders Eriksson (University of Adelaide); Anton vandenHengel; Chunhua Shen (NICTA)
1021	Matching 2D Image Lines to 3D Models: Two Improvements and a New Algorithm	Behzad Kamgar-Parsi (ONR)
1031	Abnormal Detection Using Interaction Energy Potentials	Xinyi Cui (Rutgers University); Qingshan Liu (Rutgers University); Mingchen Gao (Rutgers University); Dimitris Metaxas;
1033	Face Recognition with Large Pose Variation	Carlos Castillo; David Jacobs;
1043	Non-Rigid Structure from Motion with Complementary Rank-3 Spaces	Paulo Gotardo (The Ohio State University); Aleix Martinez;
1052	Feature Guided Motion Artifact Reduction with Structure-Awareness in 4D CT Images	Dongfeng Han (UI); John Bayouth (UI); Qi Song; sudershan Bhatia (UI); Milan Sonka; Xiaodong Wu;
1062	Identifying Players in Broadcast Sports Videos using Conditional Random Fields	Wei-Lwun Lu (University of British Columbia); Jo-Anne Ting (University of British Columbia); Kevin Murphy; Jim Little;
1077	sLLE: Spherical Locally Linear Embedding with Applications to Tomography	Yi Fang (Purdue University); S.V.N. Vishwanathan (Purdue University); Mengtian Sun (Purdue University); Karthik Ramani (Purdue University);
1088	Graph Embedding Discriminant Analysis on Grassmannian Manifolds for Improved Image Set Matching	Mehrtash Harandi (NICTA); Sareh Shirazi (National ICT Australia (NICTA)); Conrad Sanderson (National ICT Australia (NICTA)); Brian Lovell;
1103	Multiview Registration via Graph Diffusion of Dual Quaternions	Andrea Torsello; Emanuele Rodola (Università Ca' Foscari Venezia); Andrea Albarelli;
1105	Face Recognition in Unconstrained Videos with Matched Background Similarity	Lior Wolf; Tal Hassner; Itay Maoz (Tel-Aviv University)
1106	Exhaustive Family of Energies Minimizable Exactly by a Graph Cut and Approximations of the Other Ones	Guillaume Charpiat (INRIA)
1107	An effective document image deblurring algorithm	Xiao-gang Chen (Shanghai Jiao Tong University ); Xiangjian He (University of Technology, Syd); Jie Yang (Shanghai Jiaotong University); Qiang Wu (UTS)
1112	Reduced Epipolar Cost for Accelerated Incremental SfM	Antonio Rodríguez (Universidad de Murcia); Pedro Enrique López-De-Teruel (University of Murcia); Alberto Ruiz (University of Murcia)
1113	Learning Image Vicept Description via Mixed-Norm Regularization for Large Scale Semantic Image Search	Liang LI (ICT, CAS); Shuqiang Jiang; Qingming Huang (Graduate Univ of Chinese Academy of Sciences)
1119	A Hierarchical Conditional Random Field Model for Labeling and Segmenting Images of Street Scenes	Qixing Huang (Stanford University); Mei Han; Bo Wu; Sergey Ioffe;
1120	Extracting and Locating Temporal Motifs in Video Scenes Using a Hierarchical Non Parametric Bayesian Model	Rémi Emonet (Idiap); Jagannadan Varadarajan (Idiap); Jean-Marc Odobez (Idiap)
1124	Total Variation for Cyclic Structures	Evgeny Strekalovskiy (Technical University Munich); Daniel Cremers;
1140	Learning People Detection Models from Few Training Samples	Leonid Pishchulin (MPI Informatics); Christian Wojek (Max-Planck-Institute Informatics); Arjun Jain; Thorsten Thormaehlen (MPI Informatics); Bernt Schiele (MPI Informatics)
1170	Vehicle Tracking Across Nonoverlapping Cameras Using Joint Kinematic and Appearance Features	Bogdan Matei; Harpreet Sawhney (SRI International Sarnoff); Supun Samarasekera (Sarnoff Corporation)
1172	Topology-adaptive Multi-view Photometric Stereo	Yusuke Yoshiyasu (Keio University)
1183	The Magic Sigma	Dirk Padfield (GE Global Research)
1205	Object Stereo - Joint Stereo Matching and Object Segmentation	Michael Bleyer (Vienna University of Technology); Carsten Rother; Pushmeet Kohli; Daniel Scharstein; Sudipta Sinha;
1210	Functional Categorization of Objects using Real-time Markerless Motion Capture	Juergen Gall; Andrea Fossati; Luc VanGool;
1211	Graph Matching through Entropic Manifold Alignment	Francisco Escolano (University of Alicante); Edwin Hancock; Miguel Lozano (University of Alicante)
1215	Hybrid Generative-Discriminative Classification using Posterior Divergence	Xiong Li (Shanghai Jiao Tong University); Tai Sing Lee (Department of Computer Science, Carnegie Mellon University); Yuncai Liu (Department of Automation, Shanghai Jiao Tong University)
1228	Illumination Estimation and Cast Shadow Detection through a Higher-order Graphical Model	Alexandros Panagopoulos (Stony Brook University); Chaohui Wang (Ecole Centrale Paris/INRIA); Dimitris Samaras; Nikos Paragios;
1230	A Large-scale Benchmark Dataset for Event Recognition in Surveillance Video	Sangmin Oh; Anthony Hoogs; A.G.Amitha Perera; Chia-Chih Chen (UT ECE); Jong Taek Lee (The University of Texas at Austin); Jake Aggarwal; Hyungtae Lee (University of Maryland, College Park); Larry Davis; Xiaoyang Wang (Rensselaer Polytechnic Institute); Eran Swears (RPI); Qiang Ji; Kishore Reddy (University Of Central Florida); Mubarak Shah; Carl Vondrick (University of California, Irvi); Hamed Pirsiavash; Deva Ramanan; Jenny Yuen (MIT); Antonio Torralba; Bi Song (UCR); Anesco Fong (Univ. of California, Riverside); Amit Roy-Chowdhury; Mita Desai (DARPA)
1231	Learning Affinities and Dependencies for Multi-Target Tracking using a CRF Model	Bo Yang (USC); Chang Huang (University of Southern California); Ram Nevatia;
1232	2D Nonrigid Partial Shape Matching Using MCMC and Contour Subdivision	Yu Cao (University of South Carolina); Zhiqi Zhang (University of South Carolina); Irina Czogiel (Max Planck Institute for Molecular Genetics); Ian Dryden (University of South Carolina); Song Wang;
1235	A Multichannel Edge-Weighted Centroidal Voronoi Tessellation Algorithm for 3D Superalloy Image Segmentation	Yu Cao (University of South Carolina); Lili Ju (University of South Carolina); Qin Zou (University of South Carolina); Chengzhang Qu (Wuhan University, China); Song Wang;
1243	Using 3D Scene Structure to Improve Tracking	Jan Prokaj (Univ of Southen California); Gerard Medioni;
1260	Structure from motion blur in low light	Yali Zheng (Chongqing University); Shohei NOBUHARA (Kyoto University); Yaser Sheikh;
1261	Combining attributes and Fisher vectors for efficient image retrieval	Matthijs Douze; Arnau Ramisa (INRIA); Cordelia Schmid;
1278	Person Re-identification by Probabilistic Relative Distance Comparison	Wei-Shi Zheng (QUEEN MARY UNIVERSITY OF LONDO); Shaogang Gong; Tao Xiang;
1279	Branch and Track	Steve Gu (Duke University); Carlo Tomasi;
1280	Semi-Supervised Video Segmentation	Ignas Budvytis (Cambridge University); Vijay Badrinarayanan; Roberto Cipolla (Cambridge University)
1288	Total Recall II: Query Expansion Revisited	Ondrej Chum; Andrej Mikulik (CMP, CTU in Prague); Michal Perdoch (CMP, CTU in Prague); Jiri Matas;
1291	Finding Fiducial Points with Local Detectors and a Consensus of Global Models	Peter Belhumeur; David Jacobs (UMIACS); David Kriegman (UCSD/KBVT)
1297	Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects	Hamed Pirsiavash; Deva Ramanan; Charless Fowlkes (UC Irvine)
1298	TaylorBoost: First and Second-order Boosting Algorithms with Explicit Margin Control	Mohammad Saberian (UC San Diego); Hamed Masnadi-Shirazi (UC San Diego); Nuno Vasconcelos;
1305	O(N) Implicit Subspace Embedding for Unsupervised Multi-scale Image Segmentation	Hongbo Zhou (SIUC); Qiang Cheng (SIUC)
1313	A Global Optimization Approach to Robust Multi-Model Fitting	Jin Yu (The University of Adelaide); Tat-Jun Chin (The University of Adelaide); David Suter;
1316	Shape Based Pedestrian Parsing	Yihang Bo (Beijing Jiaotong University, Beijing,China); Charless Fowlkes (UC Irvine)
1319	City-Scale Landmark Identification on Mobile Devices	David Chen (Stanford University); Georges Baatz (Department of Computer Science, ETH Zurich); Kevin Koeser; Sam Tsai; Ramakrishna Vedantham (Nokia Research Center, Palo Alto); Timo Pylvanainen (Nokia Research Center, Tampere); kimmo Roimela (Nokia Research Center); Xin Chen (Navteq); Jeff Bach (Navteq); Marc Pollefeys; Bernd Girod; Radek Grzeszczuk;
1323	2.5D Building Modeling with Topology Control	Qian-Yi Zhou (USC); Ulrich Neumann (USC)
1325	From Active Contours to Active Surfaces	Akshaya Mishra (Tornado Medical System); Paul Fieguth (University of Waterloo); David Clausi (University of Waterloo)
1329	Which parts of the face give out your identity?	Jesus Ocegueda-Gonzalez (University of Houston); Shishir Shah (University of Houston); Ioannis Kakadiaris;
1343	Evaluating Combinational Color Constancy Methods on Real-World Images	Bing Li (Chinese Academy of Sciences)
1348	Reconstructing an image from its local descriptors	Philippe Weinzaepfel (ENS Cachan Bretagne); Herve Jegou; Patrick Perez (Technicolor)
1350	A Theory of Multi-perspective Defocusing	Yuanyuan Ding (Epson Research and Development); Jingyi Yu;
1380	Comparing Data-Dependent and Data-Independent Embeddings for Classification and Ranking of Internet Images	Yunchao Gong (UNC Chapel Hill); Svetlana Lazebnik (University of North Carolina at Chapel Hill)
1381	Novel 4-D Open-Curve Active Contour and Curve Completion Approach for Automated Tree Structure Extraction	Yu Wang (Rensselaer Polytechnic Inst.); Arunachalam Narayanaswamy (Rensselaer Polytechnic Instituite); Badri Roysam;
1382	Illumination Invariant Feature Extraction Based on Natural Images Statistics and Optimal Filtering	Lu-Hung Chen (UNC at Chapel Hill); Yang Yao-Hsiagn (National Taiwan University); Chu-Song Chen; Ming-Yen Cheng;
1383	Linearity of Each Channel Pixel Values from a Surface in and out of Shadows and Its Applications	Dong Tian (Sia); dong tang (sia.ac)
1393	A Segmentation-aware Object Detection Model with Occlusion Handling	Tianshi Gao (Stanford University); Benjamin Packer; Daphne Koller;
1397	Action Recognition using Context and Appearance Distribution Features	Xinxiao Wu (NTU); Dong Xu; Lixin Duan (NTU, Singapore); Jiebo Luo;
1398	Registration of Camera Captured Documents Under Non-rigid Deformation	Venkata Edupuganti (Dept. of CS, NJIT); Suryaprakash Kompalli (Hewlett Packard Labs); Vinayak Agarwal (Hewlet Packard Labs, India)
1422	Exploring Knowledge Transfer and Zero-Shot Learning in a Large-Scale Setting	Marcus Rohrbach (MPI Informatics); Bernt Schiele (MPI Informatics); Michael Stark (MPI Informatics)
1430	A Generalized Probabilistic Framework for Compact Codebook Creation	Lingqiao Liu (Australian National University); Lei Wang (Australian National University); Chunhua Shen (NICTA)
1431	Structure-from-Motion Based Hand-Eye Calibration Using $L_{\infty}$ Minimization	Jan Heller (CTU in Prague); Michal Havlena (CTU in Prague); Tomas Pajdla (CTU Prague); Akihiro Sugimoto (NII)
1434	Biased Normalized Cuts	Subhransu Maji; Nisheeth Vishnoi (Microsoft Research, India); Jitendra Malik (UC Berkeley)
1435	Action Recognition from a Distributed Representation of Pose and Appearance	Subhransu Maji; Lubomir Bourdev (UC Berkeley); Jitendra Malik (UC Berkeley)
1446	Efficient Groupwise Non-rigid Registration of Textured Surfaces	Kirill Sidorov (Cardiff University); Stephen Richmond (Cardiff University); David Marshall (Cardiff University)
1451	Feature- and Depth-Supported Modified Total Variation Optical Flow for 3D Motion Field Estimation in Real Scenes	Thomas Müller (Daimler Research); Jens Rannacher (Universität Heidelberg); Clemens Rabe (Daimler Research); Uwe Franke (Daimler Research)
1452	A general method for the Point of Regard estimation in 3D space	Fiora Pirri (Sapienza Università di Roma); Matia Pizzoli (Sapienza Università di Roma); Alessandro Rudi (Sapienza Università di Roma)
1456	Classification with Invariant Scattering	Joan Bruna (Ecole Polytechnique); Stéphane Mallat (École Polytechnique)
1464	Sparse Image Representation with Epitomes	Louise Benoit (ENS); Julien Mairal; Francis Bach (INRIA); Jean Ponce;
1484	Multi-spectral SIFT for Scene Category Recognition	Matthew Brown; Sabine Susstrunk (EPFL)
1492	Unsupervised Auxiliary Visual Words Discovery for Large-Scale Image Object Retrieval	Yin-Hsi Kuo (National Taiwan University and Academia Sinica); Hsuan-Tien Lin; Wen-Huang Cheng; Yi-Hsuan Yang; Winston Hsu;
1494	Deterministically Maximizing Feasible Subsystem for Robust Model Fitting with Unit Norm Constraint	Yinqiang Zheng (Tokyo Institute of Technology); Shigeki Sugimoto (Tokyo Institute of Technology); Masatoshi Okutomi;
1500	Distributed Message Passing for Large Scale Graphical Models	Alexander Schwing (ETHZ); Hazan Tamir; Marc Pollefeys; Raquel Urtasun;
1501	Reconstruction of relief objects from line drawings	Michael Kolomenkin (Technion); George Leifman (Technion); Ilan Shimshoni; Ayellet Tal (Technion)
1506	Efficient Euclidean Distance Transform Using Perpendicular Bisector Segmentation	Jun Wang (Peking University); Ying Tan (Peking University)
1511	Variable Grouping for Energy Minimization	Taesup Kim (KAIST); Sebastian Nowozin; Pushmeet Kohli; Chang D. Yoo;
1513	Actom Sequence Models for Efficient Action Detection	Adrien Gaidon (INRIA); Harchaoui Zaid; Cordelia Schmid;
1518	Supervised Hierarchical Pitman-Yor Process for Natural Scene Segmentation	Alex Shyr (UC Berkeley); Trevor Darrell (ICSI, UC Berkeley); Michael Jordan (UC Berkeley); Raquel Urtasun;
1523	A Unified Framework for Locating and Recognizing Human Actions	Yuelei Xie (Institute of computing technology, Chinese Academy of Science); Hong Chang; Zhe Li (Institute of computing technology, Chinese Academy of Science); Luhong Liang (Institute of computing technology, Chinese Academy of Science); Xilin Chen; Debin Zhao;
1529	Learning Better Image Representations Using `Flobject Analysis'	Inmar Givoni (University of Toronto); Patrick Li (University of Toronto); Brendan Frey (University of Toronto)
1531	3D Motion Reconstruction for Real-World Camera Motion	Yingying Zhu (University of Queensland); Mark Cox; Simon Lucey;
1532	Generalized Group Sparse Classifiers with Application in fMRI Brain Decoding	Bernard Ng; Rafeef Abugharbieh;
1560	Bayesian Deblurring with Integrated Noise Estimation	Uwe Schmidt (TU Darmstadt); Kevin Schelten (TU Darmstadt); Stefan Roth;
1561	Distributed Computer Vision Algorithms Through Distributed Averaging	Roberto Tron (Johns Hopkins University); René Vidal;
1570	Exploring Relations of Visual Codes for Image Classification	yongzhen Huang; Kaiqi Huang (NLPR,CASIA); Tieniu Tan;
1573	A Novel Supervised Level Set Method for Non-Rigid Object Tracking	Xin Sun (Harbin Institute of Technology); Hongxun Yao; Shengping Zhang (Harbin Institute of Technology)
1574	MKPM: a multiclass extension of the Kernel Projection Machine	Sylvain Takerkart (CNRS); Liva Ralaivola (LIF)
1575	Unsupervised Local Color Correction for Coarsely Registered Images	Miguel Riem de Oliveira (University of Aveiro); Angel Sappa (Computer Vision Center); Vitor Santos (University of Aveiro, Portugal)
1576	Object Segmentation by Alignment of Poselet Activations to Image Contours	Thomas Brox (Albert-Ludwigs-University Freiburg); Lubomir Bourdev (UC Berkeley); Subhransu Maji; Jitendra Malik (UC Berkeley)
1585	Statistics of Real-World Hyperspectral Images	Ayan Chakrabarti; Todd Zickler;
1588	Style Transfer Matrix Learning for Unsupervised Writer Adaptation	Xu-Yao Zhang (National Laboratory of Pattern Recognition, Chinese Academy of Sciences); Cheng-Lin Liu (CASIA)
1598	Shape from Specular Flow: Is One Flow Enough?	Yuriy Vasilyev (Harvard University); Todd Zickler; Steven Gortler (Harvard University); Ohad Ben-Shahar (Ben-Gurion University)
1604	Support Tucker Machines	Irene Kotsia (Queen Mary University of Londo); Ioannis Patras;
1607	Robust Classification via Structured Sparse Representation	Ehsan Elhamifar (Johns Hopkins University); René Vidal;
1609	Nonlocal Matting	Philip Lee (Northwestern University); Ying Wu (Northwestern University)
1620	Multiscale Geometric and Spectral Analysis of Plane Arrangements	Guangliang Chen (Duke University); Mauro Maggioni;
1635	A Brute-Force Algorithm for Reconstructing a Scene from Two Projections	Olof Enqvist (Lund University); Fangyuan Jiang (Lund University); Fredrik Kahl;
1639	Reflection Detection in Image Sequences	Mohamed Ahmed (Trinity College Dublin); Francois Pitie; Anil Kokaram;
1645	The importance of intermediate representations for the modeling of 2D shape detection: Endstopping and curvature tuned computations	Antonio Rodriguez-Sanchez (York University); John Tsotsos;
1646	Activity Recognition using Dynamic Subspace Angles	Octavia Camps; Mario Sznaier (Northeastern University); Binlong Li (Northeastern University); Teresa Mao (Northeastern University); Mustafa Ayazoglu (Northeastern University)
1662	Using Specular Highlights as Pose Invariant Features for 2D-3D Pose Estimation	Aaron Netz (University of Haifa); Margarita Osadchy;
1666	Adapted Gaussian Models for Image Classification	Mandar Dixit (UC San Diego); Nikhil Rasiwasia (UCSD); Nuno Vasconcelos;
1669	Probabilistic Gaze Estimation Without Active Personal Calibration	Jixu Chen (Rensselaer Polytechnic Inst.); Qiang Ji;
1673	Visual Saliency Detection by Spatially Weighted Dissimilarity	Lijuan duan; chunpeng Wu; Jun Miao (ICT, CAS); Laiyun Qing; Yu Fu;
1680	Global Optimization for Optimal Generalized Procrustes Analysis	Daniel Pizarro (University of Alcala); Adrien Bartoli (Université d'Auvergne)
1682	Boosted Local Structured HOG-LBP for Object Localization	Junge Zhang; Kaiqi Huang (NLPR,CASIA); Tieniu Tan;
1687	Graph Connectivity In Sparse Subspace Clustering	Behrooz Nasihatkon (Australian National University); Richard Hartley;
1689	A RankOrder-based clustering algorithm in face annotation	Chunhui Zhu (Tsinghua University); Fang Wen (Microsoft Research Asia); Jian Sun;
1690	TVParser: An Automatic TV Video Parsing Method	Chao Liang (Chinese Academy of Sciences); changsheng Xu; Jian Cheng; Hanqing Lu;
1691	Salient Coding for Image Classification	yongzhen Huang; Kaiqi Huang (NLPR,CASIA); Tieniu Tan;
1697	Supervised Local Subspace Learning for Continuous Head Pose Estimation	Dong Huang (Carnegie Mellon University); Markus Storer (Graz University of Technology ); Fernando DelaTorre; Horst Bischof;
1703	Adaptive Random Forest - How many ``experts'' to ask before making a decision?	Alexander Schwing (ETHZ); Christopher Zach; Yefeng Zheng (Siemens Corporate Research); Marc Pollefeys;
1705	Local Isomorphism to Solve the Pre-image Problem in Kernel Methods	Dong Huang (Carnegie Mellon University); Yuandong Tian (Carnegie Mellon University); Fernando DelaTorre;
1712	Robust and Efficient Regularized Boosting Using Total Bregman Divergence	Meizhu Liu (University of Florida); Baba Vemuri;
1716	Generalized Gaussian Process Models	Antoni Chan (City University of Hong Kong); Daxiang Dong (Hong Kong University of Science and Technology)
1721	Hierarchical Anatomical Brain Networks for MCI Prediction by Partial Least Square Analysis	Luping Zhou (UNC at Chapel Hill, U.S.A); Yaping Wang (Northwestern Polytechnical University, P.R.China); Yang Li (UNC at Chapel Hill, U.S.A); Pew-Thian Yap (UNC at Chapel Hill, U.S.A); Dinggang Shen;
1725	On Dynamic Scene Geometry for View-invariant Action Matching	Anwaar Haq (Monash); Iqbal Gondal (Monash University); Mubarak Shah (UCF)
1728	Discriminative Spatial Pyramid	Tatsuya Harada (The Univ. of Tokyo); Yoshitaka Ushiku (Grad. School of Information Sc); Yuya Yamashita (The Univ. of Tokyo); Yasuo Kuniyoshi (The Univ. of Tokyo)
1734	Nonparametric Density Estimation on A Graph: Learning Framework, Fast Approximation and Application in Image Segmentation	Zhiding Yu (HKUST); Oscar Au (HKUST); Ketan Tang (HKUST)
1738	Robust, Accurate and Weakly-Supported-Surfaces preserving Multi-View Reconstruction	Michal Jancosek (CTU Prague); Tomas Pajdla (CTU Prague)
1739	Human Brain Labeling Using Image Similarities	François Rousseau (CNRS); Piotr Habas (UCSF); Colin Studholme (UCSF)
1747	Heat-Mapping: A Robust Approach Toward Perceptually Consistent Mesh Segmentation	Yi Fang (Purdue University); Mengtian Sun (Purdue University); Karthik Ramani (Purdue University)
1748	Feature Context for Image Classiﬁcation and Object Detection	Xinggang Wang (Huazhong Univ. of Sci. & Tech.); Xiang Bai (Huazhong University of Science and Technology); Wenyu Liu (Huazhong University of Science and Technology); LonginJan Latecki;
1756	Track to the future: Spatio-temporal video segmentation with long-range motion cues	José Lezama (INRIA); Karteek Alahari (ENS / INRIA - WILLOW); Josef Sivic (INRIA / Ecole Normale Superieure); Ivan Laptev;
1760	Automatic Adaptation of a Generic Pedestrian Detector to a Specific Traffic Scene	Meng Wang (The Chinese University of HK); Xiaogang Wang (The Chinese University of Hong Kong)
1761	A 3-D Marked Point Process Model for Multi-View People Detection	Ákos Utasi (MTA SZTAKI); Csaba Benedek (MTA SZTAKI)
1765	Enforcing Similarity Constraints with Integer Programming for Better Scene Text Recognition	David Smith (UMass Amherst); Jacqueline Feild (UMass Amherst); Eric Learned-Miller;
1766	Discriminative Affine Sparse Codes for Image Classification	Naveen Kulkarni (Student); Baoxin Li;
1770	On analyzing video with very small motions	Robert Pless; Nathan Jacobs (University of Kentucky); Michael Dixon (Washington University in St. Louis); Austin Abrams (Washington University in St. Louis)
1782	Learning Object Color Models from Multi-view Constraints	Trevor Owens (UC Berkeley); Kate Saenko; Trevor Darrell (ICSI, UC Berkeley); Ayan Chakrabarti; Todd Zickler;
1788	The Light-Path Less Traveled	Srikumar Ramalingam (MERL); Sofien Bouaziz (EPFL); Peter Sturm; Philip Torr (Oxford Brookes University)
1790	Learning Context for Collective Activity Recognition	Wongun Choi (University of Michigan); Silvio Savarese; Khuram Shahid;
1794	Landmark/Image-based Deformable Registration of Gene Expression Data	Uday Kurkure; Yen Le; Nikos Paragios; James Carson; Tao Ju; Ioannis Kakadiaris;
1795	Random Maximum Margin Hashing	Alexis Joly (INRIA); olivier buisson (ina)
1797	On Deep Generative Models with Applications to Recognition	Marc'Aurelio Ranzato; Joshua Susskind (University of Toronto); Volodymyr Mnih (University of Toronto); Geoffrey Hinton (University of Toronto);
1799	Online Group-Structured Dictionary Learning	Zoltan Szabo (Eotvos Lorand University); Barnabas Poczos (Carnegie Mellon University); Andras Lorincz (Eotvos Lorand University)
1805	Single Image Super-Resolution using Gaussian Process Regression	He He (The Hong Kong Polytechnic Univ); Wan-Chi Siu (The Hong Kong Polytechnic University)
1811	Robust Discriminative Wire Structure Modeling with Application to Stent Enhancement in Fluoroscopy	Xiaoguang Lu (Siemens Corporate Research); Terrence Chen (Siemens Corporate Research); Comaniciu Dorin;
1814	Dynamic Batch Mode Active Learning	Shayok Chakraborty (Arizona State University); Vineeth Balasubramanian (Arizona State University); Sethuraman Panchanathan (Arizona State University)
1818	Adaptive Metric Differential Tracking	Nan Jiang (HUST)
1823	Automated Mitosis Detection of Stem Cell Populations with high confluency in Phase-Contrast Microscopy Images	Seungil Huh (Carnegie Mellon University); Mei Chen (Intel Labs Pittsburgh)
1826	Exploiting Phonological Constraints for Handshape Inference in ASL Video	Ashwin Thangali (Boston Univsersity); Stan Sclaroff (Boston University); Carol Neidle (Boston University); Joan Nash (Boston University)
1837	Object Recognition with Hierarchical Kernel Descriptors	Bo Liefeng; Kevin Lai; Xiaofeng Ren; Dieter Fox;
1840	Learning to Share Visual Appearance for Multiclass Object Detection	Ruslan Salakhutdinov (MIT); Antonio Torralba; Josh Tenenbaum (MIT)
1842	What makes an image memorable?	Phillip Isola (MIT); Jianxiong Xiao (MIT CSAIL); Aude Oliva; Antonio Torralba;
1859	Multi-Level Inference by Relaxed Dual Decomposition for Human Pose Segmentation	Huayan Wang (Stanford University); Daphne Koller;
1866	Dirichlet Process Mixture Models on Symmetric Positive Definite Matrices for Appearance Clustering in Video Surveillance Applications	Anoop Cherian (University of Minnesota); Vassilios Morellas (University of Minnesota, Twin Cities); Nikolaos Papanikolopoulos;
1867	Learning Message-Passing Inference Machines for Structured Prediction	Stephane Ross (Carnegie Mellon University); Daniel Munoz (Carnegie Mellon University); J. Andrew Bagnell (Carnegie Mellon University)
1873	Modelling composite shapes by Gibbs Random Fields	Dmitrij Schlesinger; Boris Flach (Czech technical University Prague)
1888	A Probabilistic Model for Recursive Factorized Image Features	Sergey Karayev (UC Berkeley); Mario Fritz; Sanja Fidler (University of Ljubljana); Trevor Darrell (ICSI, UC Berkeley)
1918	Novelty detection from an Ego-centric perspective	Omid Aghazadeh (KTH); Josephine Sullivan; Stefan Carlsson;
1926	Learning Image Representations from Pixel Level via Hierarchical Sparse Coding	Kai Yu (NEC Labs America); Yuanqing Lin (NEC Labs America); John Lafferty (CMU)
1935	Context Tracker: Exploring Supporters and Distracters in Unconstrained Environments	Thang Dinh (Univ. of Southern California); Gerard Medioni;
1940	Multi-label Learning with Incomplete Class Assignments	Serhat Bucak (Michigan State University); Rong Jin (Michigan State University); Anil Jain (Michigan State University)
1950	Efficient Multi-Camera Detection, Tracking, and Identification using a Shared Set of Haar-Features	Reyes Rios-Cabrera (K.U.Leuven); Tinne Tuytelaars (K.U.Leuven); Luc VanGool;
1951	A Generative Statistical Model for Tracking Multiple Smooth Trajectories	Ernesto Brau (University of Arizona); Kobus Barnard (Universiy of Arizona); Ravi Palanivelu (University of Arizona); Damayanthi Dunatunga (University of Arizona); Tatsuya Tsukamoto (University of Arizona); Philip Lee;
1958	Sampling Bedrooms	Luca Del Pero (University of Arizona); Jinyan Guan (University of Arizona); Ernesto Brau (University of Arizona); Joseph Schlecht (University of Heidelber); Kobus Barnard (Universiy of Arizona)
1966	Contour cut: identifying salient contours in images by solving a Hermitian eigenvalue problem	Ryan Kennedy (University of Pennsylvania); Jean Gallier; Jianbo Shi;
1967	Heterogeneous Image Features Integration via Multi-View Spectral Clustering	Xiao Cai (Department of Computer Science, University of Texas at Arlington); Feiping Nie (University of Texas, Arlington); Heng Huang (University of Texas at Arlington, Department of Computer Science and Engineering); Farhad Kamangar (Department of Computer Science, University of Texas at Arlington)
1983	Image analysis by counting on a grid	Alessandro Perina (Microsoft Research); Nebojsa Jojic (Microsoft Research)
1987	Image Saliency: From Local to Global Context	Meng Wang (Boston University); Janusz Konrad (Boston University); Prakash Ishwar (Boston University); Yushi Jing (Google Research); Henry Rowley (Google)
2002	Robust Point Set Registration Using EM-ICP with Information-Theoretically Optimal Outlier Handling	Jeroen Hermans (Katholieke Universiteit Leuven); Dirk Smeets; Paul Suetens (K.U.Leuven); Dirk Vandermeulen;
2006	L1-rotation averaging using the Weiszfeld algorithm	Richard Hartley (ANU)
2021	A Probabilistic Representation for Efficient Large Scale Visual Recognition Tasks	Subhabrata Bhattacharya (UCF)

祝贺啊祝贺。

Is computer vision as good as thought?(By Dahua Lin@MIT)

丕子 — Tue, 14 Dec 2010 01:50:01 +0000

随手翻开这期TechTalk, 在头版的大标题computer vision的字样赫然入目。第一次在TechTalk看到自己领域的文章，自然很感兴趣。

先介绍一下，TechTalk是MIT内部一份免费派发的报纸，每周一期，主要报道学校的各种科学研究的进展。一直以来，占据这份报纸头版的主要是生命科学，能源科学，或者新材料。

这篇文章的标题是 Computer vision may not be as good as thought

文章的作者来自 McGovern Institute of Brain Research @ MIT。

文章主要是针对近期在Object recognition所取得的“进展”而发的。它开篇就旗帜鲜明地提出：

The apparent success of object recognition may be misleading because the tests being used are inadvertently stacked in favor of computers.

在MIT McGovern Institute和Harvard Rowland Institute的一项联合研究中，他们认为，被广泛用于评价object recognition性能的Caltech 101 database并不能有效反映出算法在真实条件下的能力。文章指出，object recognition的核心困难源于一个物体在形成图像过程中，由于方向，位置，光照，外界环境等等的要素影响而发生的各种变化。而以Caltech 101为代表的主流测试库，在获取过程中实际上是隐含了有利于计算机辨别的因素，而不能真实反映客观世界的复杂变化，并且掩盖了实际问题的复杂性。

The ease with which we recognize visual objects belies the computational difficulty of this feat.

在他们的实验中，他们做了一个非常naive的算法作为baseline，该算法仅仅用到了一些非常初级的信息，而且没有进行特别处理和分析。他们原以为这个算法会fail，但是他们惊奇地发现，这个naive算法在Caltech 101上表现出色(surprisingly well)，其性能甚至超过了5个最新提出的state-of-the-art的算法。

从这样的实验结果中，他们对主流的算法评价体系提出了质疑

We suspected that the supposedly natural images in current computer vision tests do not really engage the central problem of variability.

为了验证他们的想法，他们设计了这样的实验，只使用飞机和车两类物体，但是，尽可能引入各种真实变化的条件。他们发现，那些在Caltech 101上面分多类分得很好的算法，在这里分两类都分得一蹋糊涂。这个团对得到这样的结论：

The model did well on the Caltech101 image set not because it is a good model but because the so-called 'natural' images in the test set fail to adequately capture real world variability.

他们提出，computer vision的研究人员应该抛弃现有的不科学的评价体系。

作为脑科学系的研究人员，他们研究object recognition的方法，主要是探索our brain's own solution，并且尽可能地去模仿它。他们认为，这是一个正确的方向。

现在Computer Vision基本要用的几个图像特征和方法

丕子 — Sun, 12 Dec 2010 00:03:39 +0000

一直在关注Action Classification，VOC2010结果发布之后，大体看了一下，基本上就那些图像特征的使用（dense SIFT+Spatial Pyramid），然后就是乱七八糟的融合了，归结都低就是Multiple Kernel Learning以及一些近似的算法。

下面看看VOC2010关于ActionClassification部分的结果：

Average Precision (AP %)

	phoning	playing instrument	reading	riding bike	riding horse	running	taking photo	using computer	walking
BONN_ACTION	47.5	51.1	31.9	64.5	69.1	78.5	32.4	53.9	61.1
CVC_BASE	56.2	56.5	34.7	75.1	83.6	86.5	25.4	60.0	69.2
CVC_SEL	49.8	52.8	34.3	74.2	85.5	85.1	24.9	64.1	72.5
INRIA_SPM_HT	53.2	53.6	30.2	78.2	88.4	84.6	30.4	60.9	61.8
NUDT_SVM_WHGO_SIFT_CENTRIST_LLM	47.2	47.9	24.5	74.2	81.0	79.5	24.9	58.6	71.5
SURREY_MK_KDA	52.6	53.5	35.9	81.0	89.3	86.5	32.8	59.2	68.6
UCLEAR_SVM_DOSP_MULTFEATS	47.0	57.8	26.9	78.8	89.7	87.3	32.5	60.0	70.1
UMCO_DHOG_KSVM	53.5	43.0	32.0	67.9	68.8	83.0	34.1	45.9	60.4
WILLOW_A_SVMSIFT_1-A_LSVM	49.2	37.7	22.2	73.2	77.1	81.7	24.3	53.7	56.9
WILLOW_LSVM	40.4	29.9	32.2	53.5	62.2	73.6	17.6	45.8	41.5
WILLOW_SVMSIFT	47.9	29.1	21.7	53.5	76.7	78.3	26.0	42.9	56.4

各种方法的描述后面也有。

首先看看UCLEAR_SVM_DOSP_MULTFEATS的方法：

Multiple chi squared kernels are computed: spatial pyramid (SP) w/ dense SIFT, dense overlapping SP w/ HOG, texture filter, LAB values (bag-of-words w/ the above features) and edge dir hists. They are computed on full images, person bounding boxes (BB) and BB of the lower part (simple stretch-scale of person BB) expected to contain horse, bike etc. They are combined with class specific binary weights based on their perf on val set. Finally, class specific SVMs trained on train+val.

是不是感觉方法很简单？

再看看SURREY_MK_KDA的方法：

Kernel-level fusion with Spatial Pyramid Grids, Soft Assignment and Kernel Discriminant Analysis using spectral regression. 18 kernels have been generated from 18 variants of SIFT. 融合吧。

CVC_SEL的方法：

Enhanced CVC submission built upon CVC-BASE for action recognition. Standard BoW model over multiple features from CVC-BASE plus contextual object descriptors. Cross-validation procedure for action-specific feature and kernel selection. Foreground/background/neighborhood modeled separately, spatial pyramid over several features for foreground representation. Object detection based on deformable part-based detector incorporated. Late fusion of feature-specific SVM outputs for final action score.

综上所述：Spatial Pyramid w/（dense SIFT | overlap HOG）这是最好用的描述模板的方法，一起用就用Multiple Kernel融合起来，学个融合的参数，其实效果真的很好很好，不骗你。

所以说，对于一些类似这样的问题，除非你是非得自己发明一些描述子，不然用这些就能够达到一些实验的目标，当然实用也是未尝不可的。

今天？今天: 关于Phone Interview以及一些琐事

丕子 — Wed, 15 Sep 2010 14:34:09 +0000

今天过得很紧张，有点郁闷和小悲剧。

前天晚上给MSRA的Mr. Wei发的Email关于CV实习的事情，Wei很好的一个人，昨天白天就回复邮件了，说是今晚8:00给我一个phone interview，然后，按照我的心理素质，就开始忐忑了。

首先还是准备下东西吧，网上搜了一下MSRA电话面试的一些东西，很杂，也不好说。还是搜一下一些电话面试的题目吧，不过很少有我这个方向的，大部分还是一些数据结构以及算法的题目。

然后搜一些面试的注意问题，找到了一个很不错的材料《Ace that phone interview!》，英文的，关于面试的一些细节问题：

1、尽量不要坐着，走动起来有利于思维。
2、找一个安静祥和的地方。
3、打印一份简历，拿着。
4、准备一些谈论你所研究问题的基本知识和句子。
5、......

由于一直在紧张的准备，所以没有来得及看邮件，不到八点我就去校园溜达去了，等着接电话阿。结果，一直到8:30没动静，唉，心理哇凉，难道又被放鸽子了？拖着疲惫的心灵回到实验室。翻开邮件，发现Wei回复邮件了：

Hi, Page, Sorry that I need to cancel tonight’s interview due to some emergency. I will call you some time tomorrow in the daytime.

哦，这样阿，那我再准备下，明天等着你哈。Wei这个人确实不错，或许那里的JianSun太忙，连邮件都没空回吧，像我这样不起眼的邮件，唉。

今天，硕士考试的最后一门成绩出来了，专业外语78,TMD、WTF、FML！唉，真悲剧。不过，其实没大用处，只是罪恶的心理在作祟。

对了，最后再说一句，google的博客大赛今天最后一天了，同学们抓紧投票哈，山东大学的那个哥们，连接是：

http://www.google.com/intl/zh-CN/daxue/blog2010/#tab2

好了，希望明天的Phone Interview顺利！！

Computer Vision-计算机视觉的几个链接库和几本书

丕子 — Sun, 05 Sep 2010 07:34:54 +0000

今天看UIUC的大牛David Forsyth的页面，在看《Computer Vision》这本书的一些信息时，根据连接这本书参考的一些资源，找到了一些CV的资源库，拿过来分享一下。

那我先介绍下计算机视觉，计算机视觉是一门研究如何使机器“看”的科学，更进一步的说，就是指用摄影机和电脑代替人眼对目标进行识别、跟踪和测量等机器视觉，并进一步做图像处理，用电脑处理成为更适合人眼观察或传送给仪器检测的图像。作为一个科学学科，计算机视觉研究相关的理论和技术，试图建立能够从图像或者多维数据中获取‘信息’的人工智能系统。

《Conputer Vision》参考的资源库如下列表，我就不翻译了，因为需要的肯定能看懂，不需要的也不会关心这个了，呵呵：

The Computer Vision Home Page is a page at CMU with a very large collection of links, including information on people and groups, data sets, free- and share-ware, conferences, etc.
CV Online is an Evolving, Distributed, Non-Proprietary, On-Line Compendium of Computer Vision, containing lots of essays on various topics in vision (about 700 at last count).
Keith Price maintains an annotated, on-line bibliography of computer vision. We used this extensively in preparing the book, and recommend it to all.
The Vislist is an archive of the newsgroup comp.ai.vision, including job offers, calls for papers, and various other good things.
The Pixel is a bulletin board and mailing list concerned with research into image processing and computer vision.
The open directory project has a page of computer vision links.
Intel has produced an open source computer vision library with a substantial discussion group (details on the web page).

《Computer Vision》这本书也是经典之作，另外，比较新的一本还有《Computer Vision-Algorithms and Applications》，是微软的Richard Szeliski写的，所以是微软在研究领域可以说是相当牛，在图像和视觉领域近年来也取得了很大成就。

希望有所帮助。

[读书] Computer Vision: Algorithms and Applications

丕子 — Sun, 23 May 2010 13:25:29 +0000

Richard Szeliski

一本系统介绍计算机视觉算法和应用的书籍，作者为微软研究院的：Richard Szeliski 。

As humans, we perceive the three-dimensional structure of the world around us with apparent ease. However, despite all of the recent advances in computer vision research, the dream of having a computer interpret an image at the same level as a two-year old remains elusive. Why is computer vision such a challenging problem, and what is the current state of the art?

Computer Vision: Algorithms and Applications explores the variety of techniques commonly used to analyze and interpret images. It also describes challenging real-world applications where vision is being successfully used, both for specialized applications such as medical imaging and fun consumer-level tasks such as image editing and stitching, which students can apply to their own personal photos and videos.

More than just a source of "recipes", this text/reference also takes a scientific approach to basic vision problems, formulating physical models of the imaging process before inverting this process to produce the best possible descriptions of a scene. Exercises are presented throughout the book, with a heavy emphasis on testing algorithms.

Suitable for either an undergraduate or a graduate-level course in computer vision, this textbook focuses on basic techniques that work under real-world conditions and encourages students to push their creative boundaries.

Dr. Richard Szeliski has over twenty years’ experience in computer vision research, most notably at Digital Equipment Corporation and Microsoft. 书籍下载

[分享] 机器视觉工具箱-Machine Vision Toolbox for Matlab

丕子 — Sat, 24 Apr 2010 01:04:46 +0000

机器视觉

发现了一个机器视觉的Matlab工具箱，分享一下。

机器视觉工具箱（MVT的）规定，在机器视觉和基于视觉的控制有益的多种功能。这是一个有点折衷收集反映作者在光度学，摄影测量，色度学方面的个人利益。它包括文件的阅读和写作，采集，显示，过滤，一滴，点和线特征提取，数学形态学，homographies，视觉的Jacobian，摄像机校准和色彩空间转换遍及 90多个业务功能，如图像。工具箱，Matlab与现代计算机工作站相结合，是一个有益的环境和便利的机器视觉算法研究。温和的图像大小处理率可以得到充分的``实时''，以便闭环控制。如焦点动态窗口（未提供），可用于增加处理速度注意方法。

作者是大牛PeterCorke，其主页上还有关于机器人的工具箱等，相当有用。有兴趣的可以去看看。

以前还整理过机器视觉的牛人，来这里。

The Machine Vision Toolbox (MVT) provides many functions that are useful in machine vision and vision-based control. It is a somewhat eclectic collection reflecting the author's personal interest in areas of photometry, photogrammetry, colorimetry. It includes over 90 functions spanning operations such as image file reading and writing, acquisition, display, filtering, blob, point and line feature extraction, mathematical morphology, homographies, visual Jacobians, camera calibration and color space conversion. The Toolbox, combined with Matlab and a modern workstation computer, is a useful and convenient environment for investigation of machine vision algorithms. For modest image sizes the processing rate can be sufficiently ``real-time'' to allow for closed-loop control. Focus of attention methods such as dynamic windowing (not provided) can be used to increase the processing rate.

Single Image Haze Removal(图像去雾)-CVPR'09 Best Paper

丕子 — Fri, 23 Apr 2010 00:39:51 +0000

今天真正又详细的了解了一下CVPR’09上的一篇值得国人骄傲的文章，真是一篇由简至美的好文，link。

这篇文章的：原文PDF、数据集、幻灯片、视频。感兴趣的可以了解一下。不过有一个问题就是如果天空中有淡淡的云，会不会是真？

CVPR的中文名是计算机视觉与模式识别会议，是计算机视觉领域最顶尖的国际会议之一。09年的CVPR共收到约1450篇投稿，其中393篇文章被接收，接收率为26%。只有一篇文章被选为今年的最佳论文。这是CVPR创立25年以来首次由中国人获得这个奖项。

2010年的结果也已经出来了，一共1724篇文章，CVPR2010 Paper Acceptance Rates: 78 papers were accepted for ORAL Presentation (4.5%).384 papers were accepted for POSTER Presentation (22.3%).

下面是作者的感想摘录，值得借鉴：

这篇论文研究的问题是图像的去雾技术，它可以还原图像的颜色和能见度，同时也能利用雾的浓度来估计物体的距离，这些在计算机视觉上都有重要应用（例如三维重建，物体识别）。但是之前人们还没找到简单有效的方法来达到这个目的。在这篇论文里，我们找到了一个非常简单的，甚至说令人惊讶统计规律，并提出了有效的去雾方法。

与之前的方法不同，我们把注意力放到了无雾图像的统计特征上。我们发现，在无雾图像中，每一个局部区域都很有可能会有阴影，或者是纯颜色的东西，又或者是黑色的东西。因此，每一个局部区域都很有可能有至少一个颜色通道会有很低的值。我们把这个统计规律叫做Dark Channel Prior。直观来说，Dark Channel Prior认为每一个局部区域都总有一些很暗的东西。这个规律很简单，但在我们研究的去雾问题上却是本质的基本规律。

由于雾总是灰白色的，因此一旦图像受到雾的影响，那么这些本来应该很暗的东西就会变得灰白。不仅如此，根据物理上雾的形成公式，我们还能根据这些东西的灰白程度来判断雾的浓度。因此，我们提出的Dark Channel Prior能很有效地去除雾的影响，同时利用物的浓度来估算物体的距离。

大道之行在于简

我们这篇文章的三个审稿人都给出了最高的评分。他们认为我们的方法简单而有效。其中一位评委说，Dark Channel Prior的想法听起来很不可思议，但我们却证明了其真实性。另一位评委认为很少有文章能够用如此简单的方法使实验结果获得如此大的提升。还有一位评委甚至亲自实现了我们的方法并确认其可行。孙剑说阅读这样的评审结果是一件让人快乐的事情。而汤老师认为，这篇文章的成功在于三个方面。第一，方法非常简单；第二，对于一个很困难的问题，给出了很好的结果；第三，发现了一个基本的自然规律并且应用在实际的问题中。在迈阿密的演讲结束后，观众也给予了很高的评价。他们跟我说，这是这次CVPR上最有趣的一个演讲。

一位与会的研究员说，最好的idea，往往就是那些看起来很简单，但说出来大家都会觉得怎么没有人想到过的idea。而我们的idea正好就符合了这一点。我们论文摘要的第一句话是这么说的，“我们提出了一个简单而有效的方法”。或许，这就是对我们这次工作最好的概括——简单的，就是美的。

您可能也喜欢：
ICCV 2011的一篇Oral： Relative Attributes	K. Grauman的7篇CVPR2011的paper	CVPR2011录取结果	Computer Vision-计算机视觉的几个链接库和几本书	CVPR 2011 的Oral：用Multi-Attribute Queries改善Image Ranking and Retrieval
无觅

您可能也喜欢：
IJCAI 2011 accepted papers 出来了	CVPR2011录取结果	Tomasz：cvpr 2011: highlights from day 1	CVPR 2011 Best Paper-优秀论文	Single Image Haze Removal(图像去雾)-CVPR’09 Best Paper
无觅

您可能也喜欢：
CVPR 2011 Best Paper-优秀论文	Tomasz：cvpr 2011: highlights from day 1	Jingen Liu一人独中两篇CVPR2011的Oral	K. Grauman的7篇CVPR2011的paper	SIGGRAPH2011和IJCAI2011关于CV的Paper
无觅

您可能也喜欢：
有价值的paper(By Dahua Lin@MIT)	介绍几本数学书(By Dahua Lin@MIT)	漫话距离(By Dahua Lin@MIT)	深入问题本身(By Dahua Lin@MIT)	MIT Dahua Lin：推荐两个东西
无觅

您可能也喜欢：
[读书] Computer Vision: Algorithms and Applications	[分享] 机器视觉工具箱-Machine Vision Toolbox for Matlab	Computer Vision-计算机视觉的几个链接库和几本书	CVPR2010一篇论文的读书笔记：关于Action Classification	Single Image Haze Removal(图像去雾)-CVPR’09 Best Paper
无觅

丕子 » Computer Vision

关于Attribute(s)和Pattern Recognition

相关文章

SIGGRAPH2011和IJCAI2011关于CV的Paper

Robotics and Vision

State-of-the-Art Reports

Session: Quality and Scalability

Session: Non-Photorealistic Rendering

Session: Image and Video

相关文章

CVPR2011录取结果

相关文章

Is computer vision as good as thought?(By Dahua Lin@MIT)

相关文章

现在Computer Vision基本要用的几个图像特征和方法

Average Precision (AP %)

相关文章

今天？今天: 关于Phone Interview以及一些琐事

相关文章

Computer Vision-计算机视觉的几个链接库和几本书

相关文章

[读书] Computer Vision: Algorithms and Applications

相关文章

[分享] 机器视觉工具箱-Machine Vision Toolbox for Matlab

相关文章

Single Image Haze Removal(图像去雾)-CVPR'09 Best Paper

大道之行在于简

相关文章

您可能也喜欢：
The Spider：一个“面向对象”的机器学习Matlab工具箱	现在Computer Vision基本要用的几个图像特征和方法	[读书] Computer Vision: Algorithms and Applications	Computer Vision-计算机视觉的几个链接库和几本书	机器视觉工程师招聘&机器学习博士后招生
无觅