{"id":1492,"date":"2012-08-21T18:27:32","date_gmt":"2012-08-21T18:27:32","guid":{"rendered":"http:\/\/eccv2012.unifi.it\/?page_id=1492"},"modified":"2012-10-03T07:51:05","modified_gmt":"2012-10-03T07:51:05","slug":"technical-program-sessions","status":"publish","type":"page","link":"http:\/\/eccv2012.unifi.it\/program\/main-conference\/technical-program-sessions\/","title":{"rendered":"Technical Program Sessions"},"content":{"rendered":"

8 October 2012<\/h1>\n

Morning<\/h2>\n

<\/a><\/p>\n

Oral Session 1: Geometry: Theory and application (10:05\u201410:35)<\/h3>\n\n\n\n\n
A QCQP Approach to Triangulation<\/td>\nChris Aholt, Sameer Agarwal, Rekha Thomas<\/td>\n<\/tr>\n
Reconstructing the World\u2019s Museums<\/td>\nJianxiong Xiao, Yasutaka Furukawa<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

<\/a><\/p>\n

Poster Session 1\u00a0(10:40\u201413:10)<\/h3>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Lie Bodies: A Manifold Representation of 3D Human Shape<\/td>\nOren Freifeld, Michael Black<\/td>\n<\/tr>\n
Worldwide Pose Estimation Using 3D Point Clouds<\/td>\nYunpeng Li, Noah Snavely, Daniel Huttenlocher, Pascal Fua<\/td>\n<\/tr>\n
Improved Reconstruction of Deforming Surfaces by Cancelling Ambient Occlusion<\/td>\nThabo Beeler, Derek Bradley, Henning Zimmer, Markus Gross<\/td>\n<\/tr>\n
On the Statistical Determination of Optimal Camera Configurations in Large Scale Surveillance networks<\/td>\nJunbin Liu, Clinton Fookes, Tim Wark, Sridha Sridharan<\/td>\n<\/tr>\n
The Scale of Geometric Texture<\/td>\nGeoffrey Oxholm, Prabin Bariya, Ko Nishino<\/td>\n<\/tr>\n
Efficient Articulated Trajectory Reconstruction Using Dynamic Programming and Filters<\/td>\nJack Valmadre, Yingying Zhu, Sridha Sridharan, Simon Lucey<\/td>\n<\/tr>\n
Object Co-detection<\/td>\nYinzge Bao, Yu Xiang, Silvio Savarese<\/td>\n<\/tr>\n
Morphable Displacement Field based Image Matching for Face Recognition Across Pose<\/td>\nShaoxin Li, Xin Liu, Xiujuan Chai, Haihong Zhang, Shihong Lao, Shiguang Shan<\/td>\n<\/tr>\n
Combining Per-Frame and Per-Track Cues for Multi-Person Action Recognition<\/td>\nSameh Khamis, Vlad I. Morariu, Larry S. Davis<\/td>\n<\/tr>\n
Joint Image and Word Sense Discrimination For Image Retrieval<\/td>\nAurelien Lucchi, Jason Weston<\/td>\n<\/tr>\n
Script Data for Attribute-based Recognition of Composite Activities<\/td>\nMarcus Rohrbach, Michaela Regneri, Mykhaylo Andriluka, Sikandar Amin, Manfred Pinkal, Bernt Schiele<\/td>\n<\/tr>\n
Undoing the Damage of Dataset Bias<\/td>\nAditya Khosla, Tinghui Zhou, Tomasz Malisiewicz, Alexei A. Efros, Antonio Torralba<\/td>\n<\/tr>\n
Dog Breed Classification Using Part Localization<\/td>\nJiongxin Liu, Angjoo Kanazawa, David Jacobs, Peter Belhumeur<\/td>\n<\/tr>\n
A Dictionary Learning Approach for Classification: Separating the Particularity and the Commonality<\/td>\nShu Kong, Donghui Wang<\/td>\n<\/tr>\n
Learning to Efficiently Detect Repeatable Interest Points in Depth Data<\/td>\nStefan Holzer, Jamie Shotton, Pushmeet Kohli<\/td>\n<\/tr>\n
Effective Use of Frequent Itemset Mining for Image Classification<\/td>\nBasura Fernando, Elisa Fromont, Tinne Tuytelaars<\/td>\n<\/tr>\n
Efficient Discriminative Projections for Compact Binary Descriptors<\/td>\nTomasz Trzcinski, Vincent Lepetit<\/td>\n<\/tr>\n
Descriptor Learning using Convex Optimisation<\/td>\nKaren Simonyan, Andrea Vedaldi, Andrew Zisserman<\/td>\n<\/tr>\n
Bottom-Up Perceptual Organization of Images into Object Part Hypotheses<\/td>\nMaruthi Narayanan, Benjamin Kimia<\/td>\n<\/tr>\n
Match Graph Construction for Large Image Databases<\/td>\nKwang In Kim, James Tompkin, Martin Theobald, Jan Kautz, Christian Theobalt<\/td>\n<\/tr>\n
Modeling Complex Temporal Composition of Actionlets for Activity Prediction<\/td>\nKang Li, Jie Hu, Yun Fu<\/td>\n<\/tr>\n
Learning Human Interaction by Interactive Phrases<\/td>\nYu Kong, Yunde Jia, Yun Fu<\/td>\n<\/tr>\n
Learning to Recognize Daily Actions using Gaze<\/td>\nAlireza Fathi, Yin Li, James M. Rehg<\/td>\n<\/tr>\n
Gait Recognition by Ranking<\/td>\nRa\u00fal Mart\u00edn F\u00e9lez, Tao Xiang<\/td>\n<\/tr>\n
Semi-Intrinsic Mean Shift on Riemannian Manifolds<\/td>\nRui Caseiro, Jo\u00e3o F. Henriques, Pedro Martins, Jorge Batista<\/td>\n<\/tr>\n
Efficient Nonlocal Regularization for Optical Flow<\/td>\nPhilipp Kr\u00e4henb\u00fchl, Vladlen Koltun<\/td>\n<\/tr>\n
Fast Fusion Moves for Multi-Model Estimation<\/td>\nAndrew Delong, Olga Veksler, Yuri Boykov<\/td>\n<\/tr>\n
Approximate MRF Inference Using Bounded Treewidth Subgraphs<\/td>\nAlex Fix, Joyce Chen, Endre Boros, Ramin Zabih<\/td>\n<\/tr>\n
Recursive Bilateral Filtering<\/td>\nQingxiong Yang<\/td>\n<\/tr>\n
Accelerated Large-Scale Optimization by Concomitant Hashing<\/td>\nYadong Mu, John Wright, Shih-Fu Chang<\/td>\n<\/tr>\n
Graph Degree Linkage: Agglomerative Clustering on a Directed Graph<\/td>\nWei Zhang, Xiaogang Wang, Deli Zhao, Xiaoou Tang<\/td>\n<\/tr>\n
Supervised Earth Mover’s Distance Learning and its Computer Vision Applications<\/td>\nFan Wang, Leonidas J. Guibas<\/td>\n<\/tr>\n
Global Optimization of Object Pose and Motion from a Single Rolling Shutter Image with Automatic 2D-3D Matching<\/td>\nLudovic Magerand, Adrien Bartoli, Omar Ait-Aider, Daniel Pizarro<\/td>\n<\/tr>\n
Online Learning of Linear Predictors for Real-Time Tracking<\/td>\nStefan Holzer, Marc Pollefeys, Slobodan Ilic, David Joseph Tan, Nassir Navab<\/td>\n<\/tr>\n
Online Learned Discriminative Part-Based Appearance Models for Multi-Human Tracking<\/td>\nBo Yang, Ram Nevatia<\/td>\n<\/tr>\n
Exposure Stacks of Live Scenes with Hand-held Cameras<\/td>\nJun Hu, Orazio Gallo, Kari Pulli<\/td>\n<\/tr>\n
Dual-Force Metric Learning for Robust Distracter-Resistant Tracker<\/td>\nZhibin Hong, Xue Mei, Dacheng Tao<\/td>\n<\/tr>\n
Shape and Reflectance from Natural Illumination<\/td>\nGeoffrey Oxholm, Ko Nishino<\/td>\n<\/tr>\n
Frequency Analysis of Transient Light Transport with Applications in Bare Sensor Imaging<\/td>\nDi Wu, Gordon Wetzstein, Christopher Barsi, Thomas Willwacher, Matthew O’Toole, Nikhil Naik, Qionghai Dai, Kyros Kutulakos, Ramesh Raskar<\/td>\n<\/tr>\n
Nonuniform Lattice Regression for Modeling the Camera Imaging Pipeline<\/td>\nHai Ting Lin, Zheng Lu, Seon Joo Kim, Michael S. Brown<\/td>\n<\/tr>\n
Context-Based Automatic Local Image Enhancement<\/td>\nSung Ju Hwang, Ashish Kapoor, Sing Bing Kang<\/td>\n<\/tr>\n
Segmentation with Non-Linear Regional Constraints Via Line-Search Cuts<\/td>\nLena Gorelick, Frank R. Schmidt, Yuri Boykov, Andrew Delong, Aaron Ward<\/td>\n<\/tr>\n
Hausdorff Distance Constraint for Multi-Surface Segmentation<\/td>\nFrank R. Schmidt, Yuri Boykov<\/td>\n<\/tr>\n
Background Subtraction Using Low Rank and Group Sparsity Constraints<\/td>\nXinyi Cui, Junzhou Huang, Shaoting Zhang , Dimitris N. Metaxas<\/td>\n<\/tr>\n
Free Hand-Drawn Sketch Segmentation<\/td>\nZhenbang Sun, Changhu Wang, Liqing Zhang, Lei Zhang<\/td>\n<\/tr>\n
Auto-grouped Sparse Representation for Visual Analysis<\/td>\nJiashi Feng, Xiaotong Yuan, Zilei Wang, Huan Xu, Shuicheng Yan<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Afternoon<\/h2>\n

<\/a><\/p>\n

Poster Session 2\u00a0(14:30\u201417:00)<\/h3>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Background Inpainting for Videos with Dynamic Objects and a Free-moving Camera<\/td>\nMiguel Granados, Kwang In Kim, James Tompkin, Jan Kautz, Christian Theobalt<\/td>\n<\/tr>\n
Optimal Templates for Nonrigid Surface Reconstruction<\/td>\nMarkus Moll, Luc Van Gool<\/td>\n<\/tr>\n
Learning Domain Knowledge for Facade Labelling<\/td>\nDengxin Dai, Mukta Prasad, Gerhard Schmitt, Luc Van Gool<\/td>\n<\/tr>\n
Simultaneous Shape and Pose Adaption of Articulated Models using Linear Optimization<\/td>\nMatthias Straka, Stefan Hauswiesner, Matthias R\u00fcther, Horst Bischof<\/td>\n<\/tr>\n
Robust Fitting for Multiple View Geometry<\/td>\nOlof Enqvist, Erik Ask, Fredrik Kahl, Kalle \u00c5str\u00f6m<\/td>\n<\/tr>\n
Improving Image-Based Localization by Active Correspondence Search<\/td>\nTorsten Sattler, Bastian Leibe, Leif Kobbelt<\/td>\n<\/tr>\n
From Meaningful Contours to Discriminative Object Shape<\/td>\nPradeep krishna Yarlagadda, Bjorn Ommer<\/td>\n<\/tr>\n
A Particle Filter Framework for Contour Detection<\/td>\nNicolas Widynski, Max Mignotte<\/td>\n<\/tr>\n
TriCoS: A Tri-level Class-Discriminative Co-Segmentation Method for Image Classification<\/td>\nYuning Chai, Esa Rahtu, Victor Lempitsky, Luc Van Gool, Andrew Zisserman<\/td>\n<\/tr>\n
Multi-view Discriminant Analysis<\/td>\nMeina Kan, Shiguang Shan, Haihong Zhang, Shihong Lao, Xilin Chen<\/td>\n<\/tr>\n
Multi-scale Patch based Collaborative Representation for Face Recognition with Margin Distribution Optimization<\/td>\nPengfei Zhu, Lei Zhang, Qinghua Hu, Simon C.K. Shiu<\/td>\n<\/tr>\n
Object detection using strongly-supervised deformable part models<\/td>\nHossein Azizpour, Ivan Laptev<\/td>\n<\/tr>\n
Efficient Misalignment-Robust Representation for Real-Time Face Recognition<\/td>\nMeng Yang, Lei Zhang, David Zhang<\/td>\n<\/tr>\n
Monocular Object Detection using 3D Geometric Primitives<\/td>\nPeter Carr, Yaser Sheikh, Iain Matthews<\/td>\n<\/tr>\n
Object-centric spatial pooling for image classification<\/td>\nOlga Russakovsky, Yuanqing Lin, Kai Yu, Li Fei-fei<\/td>\n<\/tr>\n
Statistics of Patch Offsets for Image Completion<\/td>\nKaiming He, Jian Sun<\/td>\n<\/tr>\n
Spectral Demons – Image Registration via Global Spectral Correspondence<\/td>\nHerve Lombaert, Leo Grady, Xavier Pennec, Nicholas Ayache, Farida Cheriet<\/td>\n<\/tr>\n
MatchMiner: Efficient Spanning Structure Mining in Large Image Collections<\/td>\nYin Lou, Noah Snavely, Johannes Gehrke<\/td>\n<\/tr>\n
V1-Inspired Features Induce a Weighted Margin in SVMs<\/td>\nHilton Bristow, Simon Lucey<\/td>\n<\/tr>\n
Unsupervised Discovery of Mid-Level Discriminative Patches<\/td>\nSaurabh Singh, Abhinav Gupta, Alexei A. Efros<\/td>\n<\/tr>\n
Self-Similar Sketch<\/td>\nAndrea Vedaldi, Andrew Zisserman<\/td>\n<\/tr>\n
Depth Matters: Influence of Depth Cues on Visual Saliency<\/td>\nLang Congyan, Tam V. Nguyen, Harish Katti, Karthik Yadati, Mohan Kankanhalli, Shuicheng Yan<\/td>\n<\/tr>\n
Quaternion-based Spectral Saliency Detection for Eye Fixation Prediction<\/td>\nBoris Schauerte, Rainer Stiefelhagen<\/td>\n<\/tr>\n
Human Activities as Stochastic Kronecker Graphs<\/td>\nSinisa Todorovic<\/td>\n<\/tr>\n
Facial Action Transfer with Personalized Bilinear Regression<\/td>\nDong Huang, Fernando De la Torre<\/td>\n<\/tr>\n
Point of Gaze Estimation through Corneal Surface Reflection in an Active Illumination Environment<\/td>\nAtsushi Nakazawa, Christian Nitschke<\/td>\n<\/tr>\n
Order-Preserving Sparse Coding For Sequence Classification<\/td>\nBingbing Ni, Pierre Moulin, Shuicheng Yan<\/td>\n<\/tr>\n
Min-Space Integral Histogram<\/td>\nS\u00e9verine Dubuisson, Christophe Gonzales<\/td>\n<\/tr>\n
On Learning Higher-Order Consistency Potentials for Multi-class Pixel Labeling<\/td>\nKyoungup Park, Stephen Gould<\/td>\n<\/tr>\n
Sparse Coding and Dictionary Learning for Symmetric Positive Definite Matrices: A Kernel Approach<\/td>\nMehrtash T. Harandi, Conrad Sanderson, Richard Hartley, Brian Lovell<\/td>\n<\/tr>\n
Learning Class-to-Image Distance via Large Margin and L1-norm Regularization<\/td>\nZhengxiang Wang, Shenghua Gao, Liang-Tien Chia<\/td>\n<\/tr>\n
Taxonomic Multi-class Prediction and Person Layout using Efficient Structured Ranking<\/td>\nArpit Mittal, Matthew Blaschko, Andrew Zisserman, Philip H.S. Torr<\/td>\n<\/tr>\n
Robust Point Matching Revisited: A Concave Optimization Approach<\/td>\nWei Lian, Lei Zhang<\/td>\n<\/tr>\n
Learning Discriminative Spatial Relations for Detector Dictionaries: an Application to Pedestrian Detection<\/td>\nEnver Sangineto, Marco Cristani, Alessio Del Bue, Vittorio Murino<\/td>\n<\/tr>\n
Learning Deformations with Parallel Transport<\/td>\nDonglai Wei, Dahua Lin, John Fisher III<\/td>\n<\/tr>\n
Multi-channel Shape-Flow Kernel Descriptors for Robust Video Event Detection and Retrieval<\/td>\nPradeep Natarajan, Shuang Wu, Shiv Vitaladevuni, Xiaodan Zhuang, Unsang Park, Rohit Prasad, Premkumar Natarajan<\/td>\n<\/tr>\n
Tracking Using Motion Patterns for Very Crowded Scenes<\/td>\nXuemei Zhao, Dian Gong, Gerard Medioni<\/td>\n<\/tr>\n
Long-Range Spatio-Temporal Modeling of Video with Application to Fire Detection<\/td>\nAvinash Ravichandran, Stefano Soatto<\/td>\n<\/tr>\n
GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs<\/td>\nAmir Roshan Zamir, Afshin Dehghan, Mubarak Shah<\/td>\n<\/tr>\n
Heliometric Stereo: Shape from Sun Position<\/td>\nAustin Abrams, Christopher Hawley, Robert Pless<\/td>\n<\/tr>\n
Shape from Single Scattering for Translucent Objects<\/td>\nChika Inoshita, Yasuhiro Mukaigawa, Yasu Matsushita, Yasushi Yagi<\/td>\n<\/tr>\n
Scale Invariant Optical Flow<\/td>\nLi Xu, Zhenlong Dai, Jiaya Jia<\/td>\n<\/tr>\n
Structured Image Segmentation using Kernelized Features<\/td>\nAurelien Lucchi, Yunpeng Li, Kevin Smith, Pascal Fua<\/td>\n<\/tr>\n
Salient Object Detection: A Benchmark<\/td>\nAli Borji, Dicky Sihite, Laurent Itti<\/td>\n<\/tr>\n
Automatic Segmentation of Unknown Objects, with Application to Baggage Security<\/td>\nLeo Grady, Vivek Singh, Timo Kohlberger, Christopher Alvino, Claus Bahlmann<\/td>\n<\/tr>\n
Multi-Scale Clustering of Frame-to-Frame Correspondences for Motion Segmentation<\/td>\nRalf Dragon, Bodo Rosenhahn, Joern Ostermann<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

<\/a><\/p>\n

Oral Session 2: Learning and large-scale recognition\u00a0(17:05\u201418:30)<\/h3>\n\n\n\n\n\n\n\n
Fourier Kernel Learning<\/td>\nEduard-Gabriel Bzvan, Fuxin Li, Cristian Sminchisescu<\/td>\n<\/tr>\n
Efficient Optimization For Low-Rank Integrated Bilinear Classifiers<\/td>\nTakumi Kobayashi, Nobuyuki Otsu<\/td>\n<\/tr>\n
Metric Learning for Large Scale Image Classification: Generalizing to New Classes at Near-Zero Cost<\/td>\nThomas Mensink, Jakob Verbeek, Florent Perronnin, Gabriela Csurka<\/td>\n<\/tr>\n
Leafsnap: A Computer Vision System for Automatic Plant Species Identification<\/td>\nNeeraj Kumar, David Jacobs, Peter Belhumeur, Arijit Biswas, Joao Soares<\/td>\n<\/tr>\n
Large Scale Visual Geo-Localization of Images in Mountainous Terrain<\/td>\nGeorges Baatz, Olivier Saurer, Kevin Koeser, Marc Pollefeys<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

9 October 2012<\/h1>\n

Morning<\/h2>\n

<\/a><\/p>\n

Poster Session 3\u00a0(08:45\u201411:15)<\/h3>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Covariance Propagation and Next Best View Planning for 3D Reconstruction<\/td>\nSebastian Haner, Anders Heyden<\/td>\n<\/tr>\n
Dilated Divergence based Scale-Space Representation for Curve Analysis<\/td>\nMax W.K. Law, Keng-Yeow Tay, Andrew Leung, Gregory J. Garvin, Shuo Li<\/td>\n<\/tr>\n
A Parameterless Line Segment and Elliptical Arc Detector with Enhanced Ellipse Fitting<\/td>\nViorica Patraucean, Pierre Gurdjos, Rafael Grompone von Gioi<\/td>\n<\/tr>\n
Detecting and Reconstructing 3D Mirror Symmetric Objects<\/td>\nSudipta Sinha, Krishnan Ramnath, Rick Szeliski<\/td>\n<\/tr>\n
3D Reconstruction of Dynamic Scenes with Multiple Handheld Cameras<\/td>\nHanqing Jiang, Haomin Liu, Ping Tan, Guofeng Zhang, Hujun Bao<\/td>\n<\/tr>\n
Joint Face Alignment: Rescue Bad Alignments with Good Ones by Regularized Re-fitting<\/td>\nXiaowei Zhao, Xiujuan Chai, Shiguang Shan<\/td>\n<\/tr>\n
Dynamic Facial Expression Recognition using Longitudinal Facial Expression Atlases<\/td>\nYimo Guo, Guoying Zhao, Matti Pietik\u00e4inen<\/td>\n<\/tr>\n
Crosstalk Cascades for Frame-Rate Pedestrian Detection<\/td>\nPiotr Dollar, Ron Appel, Wolf Kienzle<\/td>\n<\/tr>\n
Query Specific Fusion for Image Retrieval<\/td>\nShaoting Zhang, Ming Yang, Timothee Cour, Kai Yu, Dimitris N. Metaxas<\/td>\n<\/tr>\n
Size Matters: Exhaustive Geometric Verification for Image Retrieval<\/td>\nHenrik Stewenius, Steinar H. Gunderson, Julien Pilet<\/td>\n<\/tr>\n
Scene Aligned Pooling for Complex Video Recognition<\/td>\nLiangliang Cao, Yadong Mu, Apostol Natsev, Shih-Fu Chang, Gang Hua, John R. Smith<\/td>\n<\/tr>\n
Discovering Latent Domains for Multisource Domain Adaptation<\/td>\nJudy Hoffman, Brian Kulis, Trevor Darrell, Kate Saenko<\/td>\n<\/tr>\n
Visual Recognition using Local Quantized Patterns<\/td>\nSibt ul Hussain, Bill Triggs<\/td>\n<\/tr>\n
Randomized Spatial Partition for Scene Recognition<\/td>\nYuning Jiang, Junsong Yuan, Gang Yu<\/td>\n<\/tr>\n
Nested Sparse Quantization for Efficient Feature Coding<\/td>\nXavier Boix, Gemma Roig, Christian Leistner, Luc Van Gool<\/td>\n<\/tr>\n
Comparative Evaluation of Binary Features<\/td>\nJared Heinly, Enrique Dunn, Jan-Michael Frahm<\/td>\n<\/tr>\n
Negative evidences and co-occurences in image retrieval: the benefit of PCA and whitening<\/td>\nHerv\u00e9 J\u00e9gou, Ondrej Chum<\/td>\n<\/tr>\n
W\u03b1SH: Weighted \u03b1-Shapes for Local Feature Detection<\/td>\nChristos Varytimidis, Konstantinos Rapantzikos, Yannis Avrithis<\/td>\n<\/tr>\n
Sparselet Models for Efficient Multiclass Object Detection<\/td>\nHyun Oh Song, Stefan Zickler, Tim Althoff, Ross Girshick, Mario Fritz, Christopher Geyer, Pedro Felzenszwalb, Trevor Darrell<\/td>\n<\/tr>\n
Nested Pictorial Structures<\/td>\nSteve Gu, Ying Zheng, Carlo Tomasi<\/td>\n<\/tr>\n
Performance Capture of Interacting Characters with Handheld Kinects<\/td>\nGenzhi Ye, Yebin Liu, Nils Hasler, Xiangyang Ji, Qionghai Dai, Christian Theobalt<\/td>\n<\/tr>\n
Dynamic Eye Movement Datasets and Learnt Saliency Models for Visual Action Recognition<\/td>\nStefan Mathe, Cristian Sminchisescu<\/td>\n<\/tr>\n
Coherent Filtering: Detecting Coherent Motions from Crowd Clutters<\/td>\nBolei Zhou, Xiaoou Tang, Xiaogang Wang<\/td>\n<\/tr>\n
Robust 3D Action Recognition with Random Occupancy Patterns<\/td>\nJiang Wang, Zicheng Liu, Jan Chorowski, Zhuoyuan Chen, Ying Wu<\/td>\n<\/tr>\n
Directional Space-Time Oriented Gradients for 3D Visual Pattern Analysis*<\/a><\/td>\nEhsan Norouznezhad, Mehrtash Harandi, Abbas Bigdeli, Mahsa Baktash, Adam Postula, Brian Lovell<\/td>\n<\/tr>\n
Polynomial Regression on Riemannian Manifolds<\/td>\nJacob Hinkle, Prasanna Muralidharan, P. Thomas Fletcher, Sarang Joshi<\/td>\n<\/tr>\n
Geodesic Saliency Using Background Priors<\/td>\nYichen Wei, Fang Wen, Wangjiang Zhu, Jian Sun<\/td>\n<\/tr>\n
Joint Face Alignment with Non-Parametric Shape Models<\/td>\nBrandon M. Smith, Li Zhang<\/td>\n<\/tr>\n
Discriminative Bayesian Active Shape Models<\/td>\nPedro Martins, Rui Caseiro, Jo\u00e3o F. Henriques, Jorge Batista<\/td>\n<\/tr>\n
Patch Based Synthesis for Single Depth Image Super-Resolution<\/td>\nOisin Mac Aodha, Neill D.F. Campbell, Arun Nair, Gabriel J. Brostow<\/td>\n<\/tr>\n
Annotation Propagation in Large Image Databases via Dense Image Correspondence<\/td>\nMichael Rubinstein, Ce Liu, William T. Freeman<\/td>\n<\/tr>\n
Numerically Stable Optimization of Polynomial Solvers for Minimal Problems<\/td>\nYubin Kuang, Kalle \u00c5str\u00f6m<\/td>\n<\/tr>\n
Has My Algorithm Succeeded? An Evaluator for Human Pose Estimators<\/td>\nNataraj Jammalamadaka, Andrew Zisserman, Marcin Eichner, Vittorio Ferrari, C.V. Jawahar<\/td>\n<\/tr>\n
Group Tracking: Exploring Mutual Relations for Multiple Object Tracking<\/td>\nGenquan Dua, Haizhou Ai, Song Cao, Shihong Lao<\/td>\n<\/tr>\n
A Discrete Chain Graph Model for 3D+T Cell Tracking with High Misdetection Robustness<\/td>\nBernhard X. Kausler, Martin Schiegg, Bjoern Andres, Martin Lindner, Ullrich Koethe, Heike Leitte, Jochen Wittbrodt, Lars Hufnagel, Fred A. Hamprecht<\/td>\n<\/tr>\n
Robust Tracking with Weighted Online Structured Learning<\/td>\nRui Yao, Qinfeng Shi, Chunhua Shen, Yanning Zhang, Anton van den Hengel<\/td>\n<\/tr>\n
Fast Regularization of Matrix-Valued Images<\/td>\nGuy Rosman, Yu Wang, Xue-Cheng Tai, Ron Kimmel, Alfred M. Bruckstein<\/td>\n<\/tr>\n
Blind Correction of Optical Aberrations<\/td>\nChristian J. Schuler, Michael Hirsch, Stefan Harmeling, Bernhard Sch\u00f6lkopf<\/td>\n<\/tr>\n
Inverse Rendering of Faces on a Cloudy Day<\/td>\nOswald Aldrian, William A.P. Smith<\/td>\n<\/tr>\n
On Tensor-Based PDEs and their Corresponding Variational Formulations with Application to Color Image Denoising<\/td>\nFreddie \u00c5str\u00f6m, George Baravdish, Michael Felsberg<\/td>\n<\/tr>\n
Kernelized Temporal Cut for Online Temporal Segmentation and Recognition<\/td>\nDian Gong, Gerard Medioni, Sikai Zhu, Xuemei Zhao<\/td>\n<\/tr>\n
Grain Segmentation of 3D Superalloy Images Using Multichannel EWCVT under Human Annotation Constraints<\/td>\nYu Cao, Lili Ju, Song Wang<\/td>\n<\/tr>\n
Hough Regions for Joining Instance Localization and Segmentation<\/td>\nHayko Riemenschneider, Sabine Sternig, Michael Donoser, Peter M. Roth, Horst Bischof<\/td>\n<\/tr>\n
Learning to Segment a Video to Clips Based on Scene and Camera Motion<\/td>\nAdarsh Kowdle, Tsuhan Chen<\/td>\n<\/tr>\n
Evaluation of Image Segmentation Quality by Adaptive Ground Truth Composition<\/td>\nBo Peng, Lei Zhang<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

<\/a><\/p>\n

Oral Session 3: Detection and attributes\u00a0(11:20\u201413:00)<\/h3>\n\n\n\n\n\n\n\n\n
Exact Acceleration of Linear Object Detectors<\/td>\nCharles Dubout, Fran\u00e7ois Fleuret<\/td>\n<\/tr>\n
Latent Hough Transform for Object Detection<\/td>\nNima Razavi, Juergen Gall, Pushmeet Kohli, Luc Van Gool<\/td>\n<\/tr>\n
Using linking features in learning non-parametric part models<\/td>\nLeonid Karlinsky, Shimon Ullman<\/td>\n<\/tr>\n
Diagnosing Error in Object Detectors<\/td>\nDerek Hoiem, Yodsawalai Chodpathumwan, Qieyun Dai<\/td>\n<\/tr>\n
Attributes for classifier feedback<\/td>\nAmar Prakash, Devi Parikh<\/td>\n<\/tr>\n
Constrained Semi-Supervised Learning using Attributes and Comparative Attributes<\/td>\nAbhinav Shrivastava, Saurabh Singh, Abhinav Gupta<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Afternoon<\/h2>\n

<\/a><\/p>\n

Poster Session 4\u00a0(14:30\u201417:00)<\/h3>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Renormalization Returns: Hyper-renormalization and Its Applications<\/td>\nKenichi Kanatani, Ali Al-Sharadqah, Nikolai Chernov, Yasuyuki Sugaya<\/td>\n<\/tr>\n
Scale Robust Multi View Stereo<\/td>\nChristian Bailer, Manuel Finckh, Hendrik P.A. Lensch<\/td>\n<\/tr>\n
Laplacian Meshes for Monocular 3D Shape Recovery<\/td>\nJonas \u00d6stlund, Aydin Varol, Dat Tien Ngo, Pascal Fua<\/td>\n<\/tr>\n
Soft Inextensibility Constraints for Template-Free Non-rigid Reconstruction<\/td>\nSara Vicente, Lourdes Agapito<\/td>\n<\/tr>\n
Spatiotemporal Descriptor for Wide-Baseline Stereo Reconstruction of Non-Rigid and Ambiguous Scenes<\/td>\nEduard Trulls Fortuny, Alberto Sanfeliu, Francesc Moreno-Noguer<\/td>\n<\/tr>\n
Elevation Angle from Reflectance Monotonicity: Photometric Stereo for General Isotropic Reflectances<\/td>\nBoxin Shi, Ping Tan, Yasu Matsushita, Katsushi Ikeuchi<\/td>\n<\/tr>\n
Local Log-Euclidean Covariance Matrix (L2<\/sup>ECM) for Image Representation and Its Applications<\/td>\nPeihua Li, Qilong Wang<\/td>\n<\/tr>\n
Ensemble Partitioning for Unsupervised Image Categorization<\/td>\nDengxin Dai, Mukta Prasad, Christian Leistner, Luc Van Gool<\/td>\n<\/tr>\n
Set Based Discriminative Ranking for Recognition<\/td>\nYang Wu, Michihiko Minoh, Masayuki Mukunoki, Shihong Lao<\/td>\n<\/tr>\n
A Global Hypotheses Verification Method for 3D Object Recognition<\/td>\nAitor Aldoma, Federico Tombari, Luigi Di Stefano, Markus Vincze<\/td>\n<\/tr>\n
Are You Really Smiling at Me? Spontaneous versus Posed Enjoyment Smiles<\/td>\nHamdi Dibeklioglu, Albert Salah, Theo Gevers<\/td>\n<\/tr>\n
Efficient Monte Carlo sampler for detecting parametric objects in large scenes<\/td>\nYannick Verdi\u00e9, Florent Lafarge<\/td>\n<\/tr>\n
Supervised Geodesic Propagation for Semantic Label Transfer<\/td>\nXiaowu Chen, Qing Li, Yafei Song, Xin Jin, Qinping Zhao<\/td>\n<\/tr>\n
Bayesian Face Revisited: A Joint Formulation<\/td>\nDong Chen, Xudong Cao, Liwei Wang, Fang Wen, Jian Sun<\/td>\n<\/tr>\n
Beyond Bounding Boxes: Learning Object Shape by Model-driven Grouping<\/td>\nJuan Antonio Monroy, Bjorn Ommer<\/td>\n<\/tr>\n
In Defence of Negative Mining for Annotating Weakly Labelled Data<\/td>\nParthipan Siva, Chris Russell, Tao Xiang<\/td>\n<\/tr>\n
Describing Clothing by Semantic Attributes<\/td>\nHuizhong Chen, Andrew Gallagher, Bernd Girod<\/td>\n<\/tr>\n
Graph Matching via Sequential Monte Carlo<\/td>\nYumin Suh, Minsu Cho, Kyoung Mu Lee<\/td>\n<\/tr>\n
Jet-Based Local Image Descriptors<\/td>\nAnders Boesen Lindbo Larsen, Sune Darkner, Anders Dahl, Kim S. Pedersen<\/td>\n<\/tr>\n
Abnormal Object Detection by Canonical Scene-based Contextual Model<\/td>\nSangdon Park, Wonsik Kim, Kyoung Mu Lee<\/td>\n<\/tr>\n
Shapecollage: Occlusion-Aware, Example-Based Shape Interpretation<\/td>\nForrester Cole, Phillip Isola, William T. Freeman, Fredo Durand, Edward Adelson<\/td>\n<\/tr>\n
Interactive Facial Feature Localization<\/td>\nVuong Le, Jonathan Brandt, Zhe Lin, Lubomir Bourdev, Thomas S. Huang<\/td>\n<\/tr>\n
Propagative Hough Voting for Human Activity Recognition<\/td>\nGang Yu, Junsong Yuan, Zicheng Liu<\/td>\n<\/tr>\n
Spatio-Temporal Phrases for Activity Recognition<\/td>\nYimeng Zhang, Xiaoming Liu, Ming-Ching Chang, Weina Ge, Tsuhan Chen<\/td>\n<\/tr>\n
Complex Events Detection using Data-driven Concepts<\/td>\nYang Yang, Mubarak Shah<\/td>\n<\/tr>\n
Learning to Recognize Unsuccessful Activities Using a Two-Layer Latent Structural Model<\/td>\nQiang Zhou, Gang Wang<\/td>\n<\/tr>\n
Action Recognition Using Subtensor Constraint<\/td>\nQiguang Liu, Xiaochun Cao<\/td>\n<\/tr>\n
Approximate Gaussian Mixtures for Large Scale Vocabularies*<\/a><\/td>\nYannis Avrithis, Yannis Kalantidis<\/td>\n<\/tr>\n
Globally Optimal Closed-surface Segmentation for Connectomics<\/td>\nBjoern Andres, Thorben Kroeger, Kevin L. Briggman, Winfried Denk, Natalya Korogod, Graham Knott, Ullrich Koethe, Fred A. Hamprecht<\/td>\n<\/tr>\n
Reduced Analytical Dependency Modeling for Classifier Fusion<\/td>\nAndy Jinhua Ma, Pong Chi Yuen<\/td>\n<\/tr>\n
Learning to Match Appearances by Correlations in a Covariance Metric Space<\/td>\nSlawomir Bak, Guillaume Charpiat, Etienne Corvee, Francois Bremond, Monique Thonnat<\/td>\n<\/tr>\n
On the Convergence of Graph Matching: Graduated Assignment Revisited<\/td>\nYu Tian, Junchi Yan, Hequan Zhang, Ya Zhang, Xiaokang Yang, Hongyuan Zha<\/td>\n<\/tr>\n
Image Annotation Using Metric Learning in Semantic Neighbourhoods<\/td>\nYashaswi Verma, C.V.\u00a0Jawahar<\/td>\n<\/tr>\n
Dynamic Programming for Approximate Expansion Algorithm<\/td>\nOlga Veksler<\/td>\n<\/tr>\n
Real-time Compressive Tracking<\/td>\nKaihua Zhang, Lei Zhang, Ming-Hsuan Yang<\/td>\n<\/tr>\n
Tracking Feature Points in Uncalibrated Images with Radial Distortion<\/td>\nMiguel Louren\u00e7o, Jo\u00e3o Pedro Barreto<\/td>\n<\/tr>\n
Divergence-Free Motion Estimation<\/td>\nIsabelle Herlin, Dominique B\u00e9r\u00e9ziat, Nicolas Mercier, Sergiy Zhuk<\/td>\n<\/tr>\n
Visual Tracking via Adaptive Tracker Selection with Multiple Features<\/td>\nJu Hong Yoon, Du Yong Kim, Kuk-Jin Yoon<\/td>\n<\/tr>\n
Image Enhancement using Calibrated Lens Simulations<\/td>\nYiChang Shih, Brian Guenter, Neel Joshi<\/td>\n<\/tr>\n
Color Constancy, Intrinsic Images, and Shape Estimation<\/td>\nJonathan T. Barron, Jitendra Malik<\/td>\n<\/tr>\n
A Fast Illumination and Deformation Insensitive Image Comparison Algorithm Using Wavelet-Based Geodesics<\/td>\nAnne Jorstad, David Jacobs, Alain Trouv\u00e9<\/td>\n<\/tr>\n
Large-Scale Gaussian Process Classification with Flexible Adaptive Histogram Kernels<\/td>\nErik Rodner, Alexander Freytag, Paul Bodesheim, Joachim Denzler<\/td>\n<\/tr>\n
Background Subtraction with Dirichlet Processes<\/td>\nTom S.F. Haines, Tao Xiang<\/td>\n<\/tr>\n
Mobile Product Image Search by Automatic Query Object Extraction<\/td>\nXiaohui Shen, Zhe Lin, Jonathan Brandt, Ying Wu<\/td>\n<\/tr>\n
Analyzing the Subspace Structure of Related Images: Concurrent Segmentation of Image Sets<\/td>\nLopamudra Mukherjee, Vikas Singh, Jia Xu, Maxwell D. Collins<\/td>\n<\/tr>\n
Artistic Image Classification: an Analysis on the PRINTART Database<\/td>\nGustavo Carneiro, Nuno Pinho da Silva, Alessio Del Bue, Joao Costeira<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

<\/a><\/p>\n

Oral Session 4: Actions and activities\u00a0(17:05\u201418:30)<\/h3>\n\n\n\n\n\n\n\n
Detecting Actions, Poses, and Objects with Relational Phraselets<\/td>\nChaitanya Desai, Deva Ramanan<\/td>\n<\/tr>\n
Action Recognition with Exemplar Based 2.5D Graph Matching<\/td>\nBangpeng Yao, Li Fei-fei<\/td>\n<\/tr>\n
Cost-Sensitive Top-Down\/Bottom-Up Inference for Multiscale Activity Recognition<\/td>\nMohamed Amer, Dan Xie, Mingtian Zhao, Yaofei Feng, Behrooz Mahasseni, Sinisa Todorovic, Song-Chun Zhu<\/td>\n<\/tr>\n
Activity Forecasting<\/td>\nKris Kitani, Brian D. Ziebart,\u00a0James Andrew Bagnell, Martial Hebert<\/td>\n<\/tr>\n
A Unified Framework for Multi-Target Tracking and Collective Activity Recognition<\/td>\nWongun Choi, Silvio Savarese<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

10 October 2012<\/h1>\n

Morning<\/h2>\n

<\/a><\/p>\n

Poster Session 5\u00a0(08:45\u201411:15)<\/h3>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Camera Pose Estimation Using First-Order Curve Differential Geometry<\/td>\nRicardo Fabbri, Benjamin B. Kimia, Peter J. Giblin<\/td>\n<\/tr>\n
Beyond Feature Points: Structured Prediction for Monocular Non-rigid 3D Reconstruction<\/td>\nMathieu Salzmann, Raquel Urtasun<\/td>\n<\/tr>\n
Learning Spatially-Smooth Mappings in Non-Rigid Structure from Motion<\/td>\nOnur Hamsici, Paulo F.U. Gotardo, Aleix M. Martinez<\/td>\n<\/tr>\n
In Defence of RANSAC for Outlier Rejection in Deformable Registration<\/td>\nQuoc-Huy Tran, Tat-Jun Chin, Gustavo Carneiro, Michael S. Brown, David Suter<\/td>\n<\/tr>\n
A Tensor Voting Approach for Multi-View 3D Scene Flow Estimation and Refinement<\/td>\nJaesik Park, Tae Hyun Oh, Jiyoung Jung, Yu-Wing Tai, In So Kweon<\/td>\n<\/tr>\n
Two-view Underwater Structure and Motion for Cameras under Flat Refractive Interfaces<\/td>\nLai Kang, Lingda Wu, Yee-Hong Yang<\/td>\n<\/tr>\n
Reading Ancient Coins: Automatically Identifying Denarii using Obverse Legend Seeded Retrieval<\/td>\nOgnjen Arandjelovic<\/td>\n<\/tr>\n
Robust and Practical Face Recognition via Structured Sparsity<\/td>\nKui Jia, Tsung-Han Chan, Yi Ma<\/td>\n<\/tr>\n
Recognizing Materials from Virtual Examples<\/td>\nWenbin Li, Mario Fritz<\/td>\n<\/tr>\n
Scene Recognition on the Semantic Manifold<\/td>\nRoland Kwitt, Nuno Vasconcelos, Nikhil Rasiwasia<\/td>\n<\/tr>\n
Unsupervised Temporal Commonality Discovery<\/td>\nWen-Sheng Chu, Feng Zhou, Fernando De la Torre<\/td>\n<\/tr>\n
Finding People Using Scale, Rotation and Articulation Invariant Matching<\/td>\nHao Jiang<\/td>\n<\/tr>\n
Measuring Image Distances via Embedding in a Semantic Manifold<\/td>\nChen Fang, Lorenzo Torresani<\/td>\n<\/tr>\n
Efficient Point-to-Subspace Query in L1 with Application to Robust Face Recognition<\/td>\nJu Sun, Yuqian Zhang, John Wright<\/td>\n<\/tr>\n
Recognizing Complex Events using Large Margin Joint Low-Level Event Model<\/td>\nHamid Izadinia, Mubarak Shah<\/td>\n<\/tr>\n
Multi-Component Models for Object Detection<\/td>\nChunhui Gu, Pablo Arbelaez, Yuanqing Lin, Kai Yu, Jitendra Malik<\/td>\n<\/tr>\n
Discriminative Decorrelation for Clustering and Classification<\/td>\nBharath Hariharan, Jitendra Malik, Deva Ramanan<\/td>\n<\/tr>\n
Beyond Spatial Pyramids: A New Feature Extraction Framework with Dense Spatial Sampling for Image Classification<\/td>\nShengye Yan, Xinxing Xu, Dong Xu, Stephen Lin, Xuelong Li<\/td>\n<\/tr>\n
Subspace Learning in Krein Spaces: Complete Kernel Fisher Discriminant Analysis with Indefinite Kernels<\/td>\nStefanos Zafeiriou<\/td>\n<\/tr>\n
A Novel Material-aware Feature Descriptor for Volumetric Image Registration in Diffusion Tensor Space<\/td>\nShuai Li, Qinping Zhao, Shengfa Wang, Tingbo Hou, Aimin Hao, Hong Qin<\/td>\n<\/tr>\n
Efficient Closed-Form Solution to Generalized Boundary Detection<\/td>\nMarius Leordeanu, Rahul Sukthankar, Cristian Sminchisescu<\/td>\n<\/tr>\n
Attribute Learning for Understanding Unstructured Social Activity<\/td>\nYanwei Fu, Timothy M. Hospedales, Tao\u00a0 Xiang, Shaogang Gong<\/td>\n<\/tr>\n
Statistical Inference of Motion in the Invisible<\/td>\nHaroon Idrees, Imran Saleemi, Mubarak Shah<\/td>\n<\/tr>\n
Going With the Flow: Pedestrian Efficiency in Crowded Scenes<\/td>\nLouis Kratz, Ko Nishino<\/td>\n<\/tr>\n
Reconstructing 3D Human Pose from 2D Image Landmarks.<\/td>\nVarun Ramakrishna, Takeo Kanade, Yaser Sheikh<\/td>\n<\/tr>\n
Fast Tiered Labeling with Topological Priors<\/td>\nYing Zheng, Steve Gu, Carlo Tomasi<\/td>\n<\/tr>\n
TreeCANN – k-d tree Coherence Approximate Nearest Neighbor algorithm<\/td>\nIgor Olonetsky, Shai Avidan<\/td>\n<\/tr>\n
Robust Regression<\/td>\nDong Huang, Ricardo\u00a0 Cabral, Fernando De la Torre<\/td>\n<\/tr>\n
Domain Adaptive Dictionary Learning<\/td>\nQiang Qiu, Vishal M. Patel, Pavan Turaga, Rama Chellappa<\/td>\n<\/tr>\n
A Robust and Efficient Doubly Regularized Metric Learning Approach<\/td>\nMeizhu Liu, Baba C. Vemuri<\/td>\n<\/tr>\n
A Discriminative Data-dependent Mixture-Model Approach for Multiple Instance Learning in Image Classification<\/td>\nQifan Wang, Luo Si, Dan Zhang<\/td>\n<\/tr>\n
No Bias Left Behind: Covariate Shift Adaptation for Discriminative 3D Pose Estimation<\/td>\nMakoto Yamada, Leonid Sigal, Michalis Raptis<\/td>\n<\/tr>\n
Labeling Images by Integrating Sparse Multiple Distance Learning and Semantic Context Modeling<\/td>\nChuanjun Ji, Xiangdong Zhou, Lan Lin, Weidong Yang<\/td>\n<\/tr>\n
Exploiting the Circulant Structure of Tracking-by-detection with Kernels<\/td>\nJo\u00e3o F. Henriques, Rui Caseiro, Pedro Martins, Jorge Batista<\/td>\n<\/tr>\n
Online Spatio-Temporal Structural Context Learning for Visual Tracking<\/td>\nLongyin Wen, Zhaowei Cai, Zhen Lei, Dong Yi, Stan Z. Li<\/td>\n<\/tr>\n
Automatic Tracking of a Large Number of Moving Targets in 3D<\/td>\nYe Liu, Hui Li, Yan Qiu Chen<\/td>\n<\/tr>\n
Towards optimal non-rigid surface tracking<\/td>\nMartin Klaudiny, Chris Budd, Adrian Hilton<\/td>\n<\/tr>\n
Full Body Performance Capture under Uncontrolled and Varying Illumination: A Shading-based Approach<\/td>\nChenglei Wu, Kiran Varanasi, Christian Theobalt<\/td>\n<\/tr>\n
Automatic Exposure Correction of Consumer Photographs<\/td>\nLu Yuan, Jian Sun<\/td>\n<\/tr>\n
Image Guided Tone Mapping with Locally Nonlinear Model<\/td>\nHuxiang Gu, Ying Wang, Shiming Xiang, Gaofeng Meng, Chunhong Pan<\/td>\n<\/tr>\n
A comparison of the statistical properties of IQA databases relative to a set of newly captured high-definition images<\/td>\nJavier Silvestre-Blanes, Ian Van Der Linde, Rub\u00e9n P\u00e9rez-Llor\u00e9ns<\/td>\n<\/tr>\n
Supervised Assessment of Segmentation Hierarchies<\/td>\nJordi Pont-Tuset, Ferran Marques<\/td>\n<\/tr>\n
Image Labeling on a Network: Using Social-Network Metadata for Image Classification<\/td>\nJulian McAuley, Jure Leskovec<\/td>\n<\/tr>\n
Segmentation Based Particle Filtering for Real-Time 2D Object Tracking<\/td>\nVasileios Belagiannis, Falk Schubert, Nassir Navab, Slobodan Ilic<\/td>\n<\/tr>\n
Online Video Segmentation by Bayesian Split-Merge Clustering<\/td>\nJuho Lee, Suha Kwak, Bohyung Han, Seungjin Choi<\/td>\n<\/tr>\n
Joint Classification-Regression Forests for Spatially Structured Multi-Object Segmentation<\/td>\nBen Glocker, Olivier Pauly, Ender Konukoglu, Antonio Criminisi<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

<\/a><\/p>\n

Oral Session 5: MRFs and early vision\u00a0(11:20\u201413:00)<\/h3>\n\n\n\n\n\n\n\n\n
Diverse M-Best Solutions in Markov Random Fields<\/td>\nDhruv Batra, Payman Yadollahpour, Abner Guzman-Rivera, Greg Shakhnarovich<\/td>\n<\/tr>\n
Generic Cuts: An Efficient Algorithm for Optimal Inference in Higher Order MRF-MAP<\/td>\nChetan Arora, Subhashis Banerjee, Prem Kalra, S.N. Maheshwari<\/td>\n<\/tr>\n
Filter-based Mean-Field Inference for Random Fields with Higher Order Terms and Product Label-Spaces<\/td>\nJonathan Warrell, Vibhav Vineet, Phil Torr<\/td>\n<\/tr>\n
Continuous Markov Random Fields for Robust Stereo Estimation<\/td>\nKoichiro Yamaguchi, Tamir Hazan, David McAllester, Raquel Urtasun<\/td>\n<\/tr>\n
Good Regions to Deblur<\/td>\nZhe Hu, Ming-Hsuan Yang<\/td>\n<\/tr>\n
Patch Complexity, Finite Pixel Correlations and Optimal Denoising<\/td>\nAnat Levin, Boaz Nadler, Fredo Durand, William T. Freeman<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Afternoon<\/h2>\n

<\/a><\/p>\n

Poster Session 6\u00a0(14:30\u201417:00)<\/h3>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Guaranteed Ellipse Fitting with the Sampson Distance<\/td>\nZygmunt L. Szpak, Wojciech Chojnacki, Anton van den hengel<\/td>\n<\/tr>\n
A Locally Linear Regression Model for Boundary Preserving Regularization in Stereo Matching<\/td>\nShengqi Zhu, Li Zhang, Hailin Jin<\/td>\n<\/tr>\n
A Novel Fast Method for L\u221e<\/sub> Problems in Multiview Geometry<\/td>\nZhijun Dai, Yihong Wu, Fengjun Zhang, Hongan Wang<\/td>\n<\/tr>\n
Visibility Probability Structure from SfM Datasets and Applications<\/td>\nSiddharth Choudhary, P.J. Narayanan<\/td>\n<\/tr>\n
A Generative Model for Online Depth Fusion<\/td>\nOliver J. Woodford, George Vogiatzis<\/td>\n<\/tr>\n
Depth Recovery Using an Adaptive Color-Guided Auto-Regressive Model<\/td>\nJingyu Yang, Xinchen Ye, Kun Li, Chunping Hou<\/td>\n<\/tr>\n
Learning Hybrid Part Filters for Scene Recognition<\/td>\nYingbin Zheng, Yu-Gang Jiang, Xiangyang Xue<\/td>\n<\/tr>\n
Parametric Manifold of an Object under Different Viewing Directions<\/td>\nXiaozheng Zhang, Yongsheng Gao, Terry Caelli<\/td>\n<\/tr>\n
Fast approximations to structured sparse coding and applications to object classification<\/td>\nArthur Szlam, Karol Gregor, Yann LeCun<\/td>\n<\/tr>\n
Displacement Template with Divide-& -Conquer Algorithm for Significantly Improving Descriptor based Face Recognition Approaches<\/td>\nLiang Chen, Ling Yan, Yonghuai Liu, Lixin Gao, Xiaoqin Zhang<\/td>\n<\/tr>\n
Latent Pyramidal Regions for Recognizing Scenes<\/td>\nFereshteh Sadeghi, Marshall F. Tappen<\/td>\n<\/tr>\n
Augmented Attribute Representations<\/td>\nViktoriia Sharmanska, Novi Quadrianto, Christoph H. Lampert<\/td>\n<\/tr>\n
Exploring the Spatial Hierarchy of Mixture Models for Human Pose Estimation<\/td>\nYuandong Tian, C. Lawrence Zitnick, Srinivasa G. Narasimhan<\/td>\n<\/tr>\n
People Orientation Recognition by Mixtures of Wrapped Distributions on Random Trees<\/td>\nDavide Baltieri, Roberto Vezzani, Rita Cucchiara<\/td>\n<\/tr>\n
Hybrid Classifiers for Object Classification with a Rich Background<\/td>\nMargarita Osadchy, Daniel Keren, Bella Specktor<\/td>\n<\/tr>\n
Unsupervised and Supervised Visual Codes with Restricted Boltzmann Machines<\/td>\nHanlin Goh, Nicolas Thome, Matthieu Cord, Joo-Hwee Lim<\/td>\n<\/tr>\n
A New Biologically Inspired Color Image Descriptor<\/td>\nJun Zhang, Youssef Barhomi, Thomas Serre<\/td>\n<\/tr>\n
Finding Correspondence from Multiple Images via Sparse and Low-rank Decomposition<\/td>\nZinan Zeng, Tsung-Han\u00a0 Chan, Kui Jia, Dong Xu<\/td>\n<\/tr>\n
Multidimensional Spectral Hashing<\/td>\nYair Weiss, Rob Fergus, Antonio Torralba<\/td>\n<\/tr>\n
What Makes a Good Detector? – Structured Priors for Learning From Few Examples<\/td>\nTianshi Gao, Michael Stark, Daphne Koller<\/td>\n<\/tr>\n
A Convolutional Treelets Binary Feature Approach to Fast Keypoint Recognition<\/td>\nChenxia Wu, Jianke Zhu, Jiemi Zhang, Chun Chen, Deng Cai<\/td>\n<\/tr>\n
Categorizing Turn-Taking Interactions<\/td>\nKarthir Prabhakar, James M. Rehg<\/td>\n<\/tr>\n
Local Expert Forest of Score Fusion for Video Event Classification<\/td>\nJingchen Liu, Scott McCloskey, Yanxi Liu<\/td>\n<\/tr>\n
View-Invariant Action Recognition using Latent Kernelized Structural SVM<\/td>\nXinxiao Wu, Yunde Jia<\/td>\n<\/tr>\n
Trajectory-Based Modeling of Human Actions with Motion Reference Points<\/td>\nYu-Gang Jiang, Qi Dai, Xiangyang Xue, Wei Liu, Chong-Wah Ngo<\/td>\n<\/tr>\n
PatchMatchGraph: Building a Graph of Dense Patch Correspondences for Label Transfer<\/td>\nStephen Gould, Yuhang Zhang<\/td>\n<\/tr>\n
A Unifying Theory of Active Discovery and Learning<\/td>\nTimothy M. Hospedales, Shaogang Gong, Tao\u00a0 Xiang<\/td>\n<\/tr>\n
Extracting 3D Scene-consistent Object Proposals and Depth from Stereo Images<\/td>\nMichael Bleyer, Christoph Rhemann, Carsten Rother<\/td>\n<\/tr>\n
Repairing Sparse Low-Rank Texture<\/td>\nXiao Liang, Xiang Ren, Zhengdong Zhang, Yi Ma<\/td>\n<\/tr>\n
Active Frame Selection for Label Propagation in Videos<\/td>\nSudheendra Vijayanarasimhan, Kristen Grauman<\/td>\n<\/tr>\n
Non-causal Temporal Prior for Video Deblocking<\/td>\nDeqing Sun, Ce Liu<\/td>\n<\/tr>\n
Text Image Deblurring Using Text-specific Properties<\/td>\nHojin Cho, Jue Wang, Seungyong Lee<\/td>\n<\/tr>\n
Sequential Spectral Learning to Hash with Multiple Representations<\/td>\nSaehoon Kim, Yoonseop Kang, Seungjin Choi<\/td>\n<\/tr>\n
Two-Granularity Tracking: Mediating Trajectory and Detection Graphs for Tracking through Persistent Occlusions<\/td>\nKaterina Fragkiadaki, Weiyu Zhang,\u00a0Geng Zhang, Jianbo Shi<\/td>\n<\/tr>\n
Taking Mobile Multi-Object Tracking to the Next Level: People, Unknown Objects, and Carried Items<\/td>\nDennis Mitzel, Bastian Leibe<\/td>\n<\/tr>\n
Dynamic Context for Tracking Behind Occlusions<\/td>\nFei Xiong, Octavia I. Camps, Mario Sznaier<\/td>\n<\/tr>\n
To Track or To Detect? An Ensemble Framework for Optimal Selection<\/td>\nXu Yan, Xuqing Wu, Ioannis A. Kakadiaris, Shishir Shah<\/td>\n<\/tr>\n
Spatial and Angular Variational Super-resolution of 4D Light Fields<\/td>\nSven Wanner, Bastian Goldluecke<\/td>\n<\/tr>\n
Blur-Kernel Estimation from Spectral Irregularities<\/td>\nAmit Goldstein, Raanan Fattal<\/td>\n<\/tr>\n
Deconvolving PSFs for A Better Motion Deblurring using Multiple Images<\/td>\nXiang Zhu, Filip Sroubek, Peyman Milanfar<\/td>\n<\/tr>\n
Depth and Deblurring from a Spectrally-varying Depth-of-Field<\/td>\nAyan Chakrabarti, Todd Zickler<\/td>\n<\/tr>\n
Segmentation over Detection by Coupled Global and Local Sparse Representations<\/td>\nWei Xia, Zheng Song, Jiashi Feng, Loong Fah Cheong, Shuicheng Yan<\/td>\n<\/tr>\n
Moving Object Segmentation Using Motor Signals<\/td>\nChanghai Xu, Jingen Liu, Benjamin Kuipers<\/td>\n<\/tr>\n
Block-sparse RPCA for Consistent Foreground Detection<\/td>\nZhi Gao, Loong Fah Cheong, Mo Shan<\/td>\n<\/tr>\n
A Generative Model for Simultaneous Estimation of Human Body Shape and Pixel-level Segmentation<\/td>\nIngmar Rauschert, Robert T. Collins<\/td>\n<\/tr>\n
Visual Dictionary Learning for Joint Object Categorization and Segmentation<\/td>\nAastha Jain, Luca Zappella, Patrick McClure, Rene Vidal<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

<\/a><\/p>\n

Oral Session 6: Geometry and recognition\u00a0(17:05\u201418:30)<\/h3>\n\n\n\n\n\n\n\n
People Watching: Human Actions as a Cue for Single View Geometry<\/td>\nDavid Fouhey, Vincent Delaitre, Abhinav Gupta, Alexei A. Efros, Ivan Laptev, Josef Sivic<\/td>\n<\/tr>\n
Indoor Segmentation and Support Inference from RGBD Images<\/td>\nNathan Silberman, Derek Hoiem, Pushmeet Kohli, Rob Fergus<\/td>\n<\/tr>\n
Beyond the line of sight: labeling the underlying surfaces<\/td>\nRuiqi Guo, Derek Hoiem<\/td>\n<\/tr>\n
Depth Extraction from Video Using Non-parametric Sampling<\/td>\nKevin Karsch, Ce Liu, Sing Bing Kang<\/td>\n<\/tr>\n
Multiple View Object Cosegmentation using Appearance and Stereo Cues<\/td>\nAdarsh Kowdle, Sudipta Sinha, Rick Szeliski<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

11 October 2012<\/h1>\n

Morning<\/h2>\n

<\/a><\/p>\n

Poster Session 7\u00a0(08:45\u201411:15)<\/h3>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Manifold Statistics for Essential Matrices*<\/a><\/td>\nGijs Dubbelman, Leo Dorst, Henk Pijls<\/td>\n<\/tr>\n
Elastic Shape Matching of Parameterized Surfaces Using Square Root Normal Fields<\/td>\nIan H. Jermyn, Sebastian Kurtek, Eric Klassen, Anuj Srivastava<\/td>\n<\/tr>\n
N-tuple Color Segmentation for Multi-View Silhouette Extraction<\/td>\nAbdelaziz Djelouah, Jean-Sebastien Franco, Edmond Boyer, Fran\u00e7ois Le Clerc, Patrick Perez<\/td>\n<\/tr>\n
Motion-Aware Structured Light Using Spatio-Temporal Decodable Patterns<\/td>\nYuichi Taguchi, Amit Agrawal, Oncel Tuzel<\/td>\n<\/tr>\n
Refractive Calibration of Underwater Cameras<\/td>\nAnne Jordt-Sedlazeck, Reinhard Koch<\/td>\n<\/tr>\n
Detection of Independently Moving Objects in Non-planar Scenes via Multi-Frame Monocular Epipolar Constraint<\/td>\nSoumyabrata Dey, Vladimir Reilly, Imran Saleemi, Mubarak Shah<\/td>\n<\/tr>\n
Shape from Angle Regularity<\/td>\nAamer Zaheer, Maheen Rashid, Sohaib Khan<\/td>\n<\/tr>\n
Pose Invariant Approach for Face Recognition At Distance<\/td>\nEslam Mostafa, Asem Ali, Naif Alajlan, Aly Farag<\/td>\n<\/tr>\n
Minimal Correlation Classification<\/td>\nNoga Levy, Lior Wolf<\/td>\n<\/tr>\n
Contextual Object Detection using Set-based Classification<\/td>\nRamazan Gokberk Cinbis, Stan Sclaroff<\/td>\n<\/tr>\n
Age Invariant Face Verification with Relative Craniofacial Growth Model<\/td>\nTao Wu, Rama Chellappa<\/td>\n<\/tr>\n
Inferring Gene Interaction Networks from ISH Images via Kernelized Graphical Models<\/td>\nKriti Puniyani, Eric P. Xing<\/td>\n<\/tr>\n
Random Forest for Image Annotation<\/td>\nHao Fu, Qian Zhang, Guoping Qiu<\/td>\n<\/tr>\n
(MP)2<\/sup>T: Multiple People Multiple Parts Tracker<\/td>\nHamid Izadinia, Imran Saleemi, Wenhui Li, Mubarak Shah<\/td>\n<\/tr>\n
Mixture Component Identification and Learning for Visual Recognition<\/td>\nOmid Aghazadeh, Hossein Azizpour, Josephine Sullivan, Stefan Carlsson<\/td>\n<\/tr>\n
Image Retrieval with Structured Object Queries Using Latent Ranking SVM<\/td>\nTian Lan, Weilong Yang, Yang Wang, Greg Mori<\/td>\n<\/tr>\n
A probabilistic derivative measure based on the distribution of intensity difference<\/td>\nYoungbae Hwang, In So Kweon<\/td>\n<\/tr>\n
Pairwise Rotation Invariant Co-occurrence Local Binary Pattern<\/td>\nXianbiao Qi, Rong Xiao, Jun Guo,\u00a0Lei Zhang<\/td>\n<\/tr>\n
Per-patch Descriptor Selection using Surface and Scene Properties<\/td>\nIvo Everts, Jan C. van Gemert, Theo Gevers<\/td>\n<\/tr>\n
Mixed-Resolution Patch-Matching<\/td>\nHarshit Sureka, P J Narayanan<\/td>\n<\/tr>\n
Exploiting Sparse Representations for Robust Analysis of Noisy Complex Video Scenes<\/td>\nGloria Zen, Elisa Ricci, Nicu Sebe<\/td>\n<\/tr>\n
KAZE Features<\/td>\nPablo Fern\u00e1ndez Alcantarilla, Adrien Bartoli, Andrew J. Davison<\/td>\n<\/tr>\n
Online Moving Camera Background Subtraction<\/td>\nAli Elqursh, Ahmed Elgammal<\/td>\n<\/tr>\n
Coregistration: Simultaneous Alignment and Modeling of Articulated 3D Shape<\/td>\nDavid A. Hirshberg, Matthew Loper, Eric Rachlin, Michael J. Black<\/td>\n<\/tr>\n
Motion Interchange Patterns for Action Recognition in Unconstrained Videos<\/td>\nOrit Kliper-Gross, Yaron Gurovich, Tal Hassner, Lior Wolf<\/td>\n<\/tr>\n
A Non-parametric Hierarchical Model to Discover Behavior Dynamics from Tracks<\/td>\nJulian F.P. Kooij, Gwenn Englebienne, Dariu M. Gavrila<\/td>\n<\/tr>\n
Scene semantics from long-term observation of people<\/td>\nVincent Delaitre, David F. Fouhey, Ivan Laptev, Josef Sivic, Abhinav Gupta, Alexei A. Efros<\/td>\n<\/tr>\n
Efficient Exact Inference for 3D Indoor Scene Understanding<\/td>\nAlexander G. Schwing, Raquel Urtasun<\/td>\n<\/tr>\n
Seam Segment Carving: Retargeting Images to Irregularly-Shaped Image Domains<\/td>\nShaoyu Qi, Jeffrey Ho<\/td>\n<\/tr>\n
Estimation of Intrinsic Image Sequences from Image+Depth Video<\/td>\nKyong Joon Lee, Qi Zhao, Xin Tong, Minmin Gong, Shahram Izadi, Sang Uk Lee,\u00a0Ping Tan, Stephen Lin\u00a0National University); Ping Tan (); Stephen Lin ()<\/span><\/td>\n<\/tr>\n
Bayesian Blind Deconvolution with General Sparse Image Priors<\/td>\nS. Derin Babacan, Rafael Molina, Minh N. Do, Aggelos K. Katsaggelos<\/td>\n<\/tr>\n
3D2<\/sup>PM – 3D Deformable Part Models<\/td>\nBojan Pepik, Peter Gehler, Michael Stark, Bernt Schiele<\/td>\n<\/tr>\n
Efficient Similarity Derived From Kernel-based Transition Probability<\/td>\nTakumi Kobayashi, Nobuyuki Otsu<\/td>\n<\/tr>\n
A Convex Discrete-Continuous Approach for Markov Random Fields<\/td>\nChristopher Zach, Pushmeet Kohli<\/td>\n<\/tr>\n
Generalized Roof Duality for Multi-Label Optimization: Optimal Lower Bounds and Persistency<\/td>\nThomas Windheuser, Hiroshi Ishikawa, Daniel Cremers<\/td>\n<\/tr>\n
Sparse Embedding: A Framework For Sparsity Promoting Dimensionality Reduction<\/td>\nHien V. Nguyen, Vishal M. Patel, Nasser Nasrabadi, Rama Chellappa<\/td>\n<\/tr>\n
Automatic Localization of Balloon Markers and Guidewire in Rotational Fluoroscopy with Application to 3D Stent Reconstructionon to 3D stent reconstruction<\/span><\/td>\nYu Wang, Terrence Chen, Peng Wang, Christopher Rohkohl, Dorin Comaniciu<\/td>\n<\/tr>\n
Improving NCC-based Direct Visual Tracking<\/td>\nGlauco Scandaroli, Maxime Meilland,\u00a0Rogerio Richa<\/td>\n<\/tr>\n
Simultaneous Compaction and Factorization of Sparse Image Motion Matrices<\/td>\nSusanna Ricco, Carlo Tomasi<\/td>\n<\/tr>\n
Low-Rank\u00a0 Sparse Learning\u00a0 for Robust Visual Tracking<\/td>\nTianzhu Zhang, Bernard Ghanem, Si Liu, Narendra Ahuja<\/td>\n<\/tr>\n
Towards Optimal Design of Time and Color Multiplexing Codes<\/td>\nTsung-Han\u00a0 Chan, Kui Jia, Eliot Wycoff, Chong-Yung Chi, Yi Ma<\/td>\n<\/tr>\n
Dating Historical Color Images<\/td>\nFrank Palermo, James Hays,\u00a0Alexei A. Efros<\/td>\n<\/tr>\n
Rainbow Flash Camera: Depth Edge Extraction Using Complementary Colors<\/td>\nYuichi Taguchi<\/td>\n<\/tr>\n
Stixels Motion Estimation Without Optical Flow Computation<\/td>\nBertan G\u00fcnyel, Rodrigo Benenson, Radu Timofte, Luc Van Gool<\/td>\n<\/tr>\n
Video Matting Using Multi-Frame Nonlocal Matting Laplacain<\/td>\nInchang Choi, Minhaeng Lee, Yu-Wing Tai<\/td>\n<\/tr>\n
Super-Resolution-based inpainting<\/td>\nOlivier Le Meur, Christine Guillemot<\/td>\n<\/tr>\n
Fast Planar Correlation Clustering for Image Segmentation<\/td>\nJulian Yarkony, Alexander Ihler, Charless C. Fowlkes<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

<\/a><\/p>\n

Oral Session 7: Lights, action!\u00a0(11:20\u201413:00)<\/h3>\n\n\n\n\n\n\n\n\n
Reflectance and Natural Illumination from a Single Image<\/td>\nStephen Lombardi, Ko Nishino<\/td>\n<\/tr>\n
Frequency-Space Decomposition and Acquisition of Light Transport under Spatially Varying Illumination<\/td>\nDikpal Reddy, Ravi Ramamoorthi, Brian Curless<\/td>\n<\/tr>\n
A Naturalistic Open Source Movie for Optical Flow Evaluation<\/td>\nDaniel J. Butler, Jonas Wulff, Garrett B. Stanley, Michael J. Black<\/td>\n<\/tr>\n
Streaming Hierarchical Video Segmentation<\/td>\nChenliang Xu, Caiming Xiong, Jason Corso<\/td>\n<\/tr>\n
Motion Capture of Hands in Action using Discriminative Salient Points<\/td>\nLuca Ballan, Aparna Taneja, Juergen Gall, Luc Van Gool, Marc Pollefeys<\/td>\n<\/tr>\n
Photo-Sequencing<\/td>\nTali Basha,\u00a0Yael Moses, Shai Avidan<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Afternoon<\/h2>\n

<\/a><\/p>\n

Poster Session 8\u00a0(14:30\u201417:00)<\/h3>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Co-inference for Multi-modal Scene Analysis<\/td>\nDaniel Munoz, James Bagnell, Martial Hebert<\/td>\n<\/tr>\n
A Unified View on Deformable Shape Factorizations<\/td>\nRoland Angst, Marc Pollefeys<\/td>\n<\/tr>\n
Finding the Exact Rotation Between Two Images Independently of the Translation<\/td>\nLaurent Kneip, Roland Siegwart, Marc Pollefeys<\/td>\n<\/tr>\n
A New set of Quartic Trivariate Polynomial Equations for Stratified Camera Self-Calibration Under Zero-Skew and Constant Parameters Assumptions<\/td>\nAdlane Habed, Kassem Al Ismaeil, David Fofi<\/td>\n<\/tr>\n
A Minimal Solution for Camera Calibration Using Independent Pairwise Correspondences<\/td>\nFrancisco Vasconcelos, Jo\u00e3o Pedro Barreto, Edmond Boyer<\/td>\n<\/tr>\n
Real-Time Human Pose Tracking from Range Data<\/td>\nVarun Ganapathi, Christian Plagemann, Daphne Koller, Sebastian Thrun<\/td>\n<\/tr>\n
Large-lexicon attribute-consistent text recognition in natural images<\/td>\nTatiana Novikova, Olga Barinova, Pushmeet Kohli, Victor Lempitsky<\/td>\n<\/tr>\n
Dictionary-based Face Recognition from Video<\/td>\nYi-Chen Chen, Vishal M. Patel, P. Jonathon Phillips, Rama Chellappa<\/td>\n<\/tr>\n
Relaxed Pairwise Learned Metric for Person Re-Identification<\/td>\nMartin Hirzer, Peter M. Roth, Martin K\u00f6stinger, Horst Bischof<\/td>\n<\/tr>\n
Connecting Missing Links: Object Discovery from Sparse Observations Using 5 Million Product Images<\/td>\nHongwen Kang, Martial Hebert, Alexei A. Efros, Takeo Kanade<\/td>\n<\/tr>\n
Disentangling Factors of Variation for Facial Expression Recognition<\/td>\nSalah Rifai, Yoshua Bengio, Aaron Courville, Pascal Vincent, Mehdi Mirza<\/td>\n<\/tr>\n
Simultaneous Image Classification and Annotation via Biased Random Walk on Tri-relational Graph<\/td>\nXiao Cai, Hua Wang, Heng Huang, Chris Ding<\/td>\n<\/tr>\n
Spring Lattice Counting Grids: Scene recognition using deformable positional constraints<\/td>\nAlessandro Perina, Nebojsa Jojic<\/td>\n<\/tr>\n
Hand Pose Estimation and Hand Shape Classification using Multi-layered Randomized Decision Forests<\/td>\nCem Keskin, Furkan K\u0131ra\u00e7, Yunus Emre Kara, Lale Akarun<\/td>\n<\/tr>\n
Information Theoretic Learning for Pixel-based Visual Agents<\/td>\nMarco Gori, Stefano Melacci, Marco Lippi, Marco Maggini<\/td>\n<\/tr>\n
Attribute Discovery via Predictable Discriminative Binary Codes<\/td>\nMohammad Rastegari, Ali Farhadi, David Forsyth<\/td>\n<\/tr>\n
Local Higher-Order Statistics (LHS) for Texture Categorization and Facial Analysis<\/td>\nGaurav Sharma, Sibt ul Hussain, Frederic Jurie<\/td>\n<\/tr>\n
SEEDS: Superpixels Extracted via Energy-Driven Sampling<\/td>\nMichael Van den Bergh, Xavier Boix, Gemma Roig, Benjamin de Capitani, Luc Van Gool<\/td>\n<\/tr>\n
Recording and Playback of Camera Shake:\u00a0Benchmarking Blind Deconvolution with a Real-World Database<\/td>\nRolf Koehler, Michael Hirsch, Betty Mohler, Bernhard Sch\u00f6lkopf, Stefan Harmeling<\/td>\n<\/tr>\n
Learning-Based Symmetry Detection in Natural Images<\/td>\nStavros Tsogkas, Iasonas Kokkinos<\/td>\n<\/tr>\n
Similarity Constrained Latent Support Vector Machine: An Application to Weakly Supervised Action Classification<\/td>\nNataliya Shapovalova, Arash Vahdat, Kevin Cannons, Tian Lan, Greg Mori<\/td>\n<\/tr>\n
Team Activity Recognition in Sports<\/td>\nCem Direkoglu, Noel E. O’Connor<\/td>\n<\/tr>\n
Space-Variant Descriptor Sampling for Action Recognition Based on Saliency and Eye Movements<\/td>\nEleonora Vig, Michael Dorr, David Cox<\/td>\n<\/tr>\n
Dynamic Probabilistic CCA for Analysis of Affective Behaviour<\/td>\nMihalis A. Nicolaou, Vladimir Pavlovic, Maja Pantic<\/td>\n<\/tr>\n
Loss-Specific Training of Non-Parametric Image Restoration Models: A New State of the Art<\/td>\nJeremy Jancsary, Sebastian Nowozin, Carsten Rother<\/td>\n<\/tr>\n
A Probabilistic Approach to Robust Matrix Factorization<\/td>\nNaiyan Wang, Tiansheng Yao, Jingdong Wang, Dit-Yan Yeung<\/td>\n<\/tr>\n
Fast Parameter Sensitivity Analysis of PDE-based Image Processing Methods<\/td>\nTorben P\u00e4tz, Tobias Preusser<\/td>\n<\/tr>\n
The Lazy Flipper: Efficient Depth-limited Exhaustive Search in Discrete Graphical Models<\/td>\nBjoern Andres, J\u00f6rg H. Kappes, Thorsten Beier, Ullrich Koethe, Fred A. Hamprecht<\/td>\n<\/tr>\n
Face Association Across Unconstrained Video Frames Using Conditional Random Fields<\/td>\nMing Du, Rama Chellappa<\/td>\n<\/tr>\n
Contraction Moves for Geometric Model Fitting<\/td>\nOliver J. Woodford, Minh-Tri Pham, Atsuto Maki, Riccardo Gherardi, Frank Perbet, Bjorn Stenger<\/td>\n<\/tr>\n
General and Nested Wiberg Minimization: L2<\/sub> and Maximum Likelihood<\/td>\nDennis Strelow<\/td>\n<\/tr>\n
Nonmetric Priors for Continuous Multilabel Optimization<\/td>\nEvgeny Strekalovskiy, Claudia Nieuwenhuis, Daniel Cremers<\/td>\n<\/tr>\n
Real-Time Camera Tracking: When is High Frame-Rate Best?<\/td>\nAnkur Handa, Richard A. Newcombe, Adrien Angeli, Andrew J. Davison<\/td>\n<\/tr>\n
A Bayesian Approach to Alignment-based Image Hallucination<\/td>\nMarshall F. Tappen, Ce Liu<\/td>\n<\/tr>\n
Continuous Regression for Non-Rigid Image Alignment<\/td>\nEnrique Sanchez Lozano, Fernando De la Torre, Daniel Gonzalez Jimenez<\/td>\n<\/tr>\n
Non-Rigid Shape Registration: A Single Linear Least Squares Framework<\/td>\nMohammad Rouhani, Angel D. Sappa<\/td>\n<\/tr>\n
Robust and Accurate Shape Model Fitting using Random Forest Regression Voting<\/td>\nTim F. Cootes, Mircea C. Ionita, Claudia Lindner, Patrick Sauer<\/td>\n<\/tr>\n
Shape From Fluorescence<\/td>\nTali Treibitz, Zack Murez, B. Greg Mitchell, David Kriegman<\/td>\n<\/tr>\n
Separability Oriented Preprocessing for Illumination-insensitive Face Recognition<\/td>\nHu Han, Shiguang Shan, Xilin Chen, Shihong Lao, Wen Gao<\/td>\n<\/tr>\n
Saliency Modeling from Image Histograms<\/td>\nShijian Lu, Joo-Hwee Lim<\/td>\n<\/tr>\n
A Theoretical Analysis of Camera Response Functions in Image Deblurring<\/td>\nXiaogang Chen, Feng Li, Jie Yang, Jingyi Yu<\/td>\n<\/tr>\n
Robust and Efficient Subspace Segmentation via Least Squares Regression<\/td>\nCan-Yi Lu, Hai Min, Zhong-Qiu Zhao, Lin Zhu, De-Shuang Huang, Shuicheng Yan<\/td>\n<\/tr>\n
Local Label Descriptor for Example based Semantic Image Labeling<\/td>\nYiqing Yang, Zhouyuan Li, Li Zhang, Christopher Murphy, Jim Hoeve, Hongrui Jiang<\/td>\n<\/tr>\n
Road Scene Segmentation from a Single Image<\/td>\nJose \u00a0M. Alvarez, Theo Gevers, Yann LeCun, Antonio Lopez<\/td>\n<\/tr>\n
Efficient Recursive Algorithms for Computing the Mean Diffusion Tensor and\u00a0 Applications to DTI Segmentation<\/td>\nGuang Cheng, Hesamoddin Salehian, Baba Vemuri<\/td>\n<\/tr>\n
Semi-Nonnegative Matrix Factorization for Motion Segmentation with Missing Data<\/td>\nQuanyi Mo, Bruce A. Draper<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

<\/a><\/p>\n

Oral Session 8: Semantic seGMENTATION and object discovery\u00a0(17:05\u201418:30)<\/h3>\n\n\n\n\n\n\n\n
A Three-Layered Approach to Facade Parsing<\/td>\nAnelo Martinovi, Markus Mathias, Julien Weissenberg, Luc Van Gool<\/td>\n<\/tr>\n
Semantic Segmentation with Second-Order Pooling<\/td>\nJoao Carreira, Rui Caseiro, Jorge Batista, Cristian Sminchisescu<\/td>\n<\/tr>\n
Shape Sharing for Object Segmentation<\/td>\nJaechul Kim, Kristen Grauman<\/td>\n<\/tr>\n
Segmentation Propagation in ImageNet<\/td>\nDaniel Kuettel,Matthieu Guillaumin, Vittorio Ferrari<\/td>\n<\/tr>\n
\u201cClustering by Composition\u201d for Unsupervised Discovery of Image Categories<\/td>\nAlon Faktor,\u00a0Michal Irani<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n","protected":false},"excerpt":{"rendered":"

8 October 2012 Morning Oral Session 1: Geometry: Theory and application (10:05\u201410:35) A QCQP Approach to Triangulation Chris Aholt, Sameer Agarwal, Rekha Thomas Reconstructing the World\u2019s Museums Jianxiong Xiao, Yasutaka Furukawa Poster Session 1\u00a0(10:40\u201413:10) Lie Bodies: A Manifold Representation of … Continue reading →<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"parent":1254,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"sidebar-page.php","meta":{"ngg_post_thumbnail":0},"_links":{"self":[{"href":"http:\/\/eccv2012.unifi.it\/wp-json\/wp\/v2\/pages\/1492"}],"collection":[{"href":"http:\/\/eccv2012.unifi.it\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"http:\/\/eccv2012.unifi.it\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"http:\/\/eccv2012.unifi.it\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/eccv2012.unifi.it\/wp-json\/wp\/v2\/comments?post=1492"}],"version-history":[{"count":76,"href":"http:\/\/eccv2012.unifi.it\/wp-json\/wp\/v2\/pages\/1492\/revisions"}],"predecessor-version":[{"id":1521,"href":"http:\/\/eccv2012.unifi.it\/wp-json\/wp\/v2\/pages\/1492\/revisions\/1521"}],"up":[{"embeddable":true,"href":"http:\/\/eccv2012.unifi.it\/wp-json\/wp\/v2\/pages\/1254"}],"wp:attachment":[{"href":"http:\/\/eccv2012.unifi.it\/wp-json\/wp\/v2\/media?parent=1492"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}