CVPR 2013 papers

Oral

Robust Multi-Resolution Pedestrian Detection in Traffic Scenes

Junjie Yan, Xucong Zhang, Zhen Lei, Dong Yi, Shengcai Liao, Stan Li

Megastereo: Constructing High-Resolution Stereo Panoramas ( project,  project)

Christian Richardt,  Yael Pritch,  Henning Zimmer,  Alexander Sorkine-Hornung

Understanding Indoor Scenes using 3D Geometric Phrases ( project,dataset)

Wongun Choi, Yu-Wei Chao, Caroline Pantofaru, Silvio Savarese

Detection Evolution with Multi-Order Contextual Co-occurrence

Chen Guang, Yuanyuan Ding, Jing Xiao, Tony Han

Reconstructing Gas Flows Using Light Paths Approximation

Yu Ji, Jinwei Ye, Jingyi Yu

Reconstructing Loopy Curvilinear Structures Using Integer Programming ( PDF,  project)

Engin Turetken, Fethallah Benmansour, Bjoern Andres, Hanspeter Pfister, Pascal Fua

Event retrieval in large video collections with circulant temporal encoding ( PDF,  project)

Jerome Revaud, Herve Jegou, Matthijs Douze, Cordelia Schmid

Fine-Grained Crowdsourcing for Fine-Grained Recognition

Jia Deng, Jonathan Krause, Li Fei-Fei

Finding Things: Image Parsing with Regions and Per-Exemplar Detectors ( PDF,  code)

Joseph Tighe,  Svetlana Lazebnik

Physically Plausible 3D Scene Tracking: The Single Actor Hypothesis ( project,  videos,  PDF)

Nikolaos Kyriazis,  Antonis Argyros

Social Role Discovery in Human Events

Vignesh Ramanathan, Bangpeng Yao, Li Fei-Fei

Jointly Aligning and Segmenting Multiple Web Photo Streams for the Inference of Collective Photo Storylines ( project)

Gunhee Kim,  Eric Xing

3D-Based Reasoning with Blocks, Support, and Stability ( PDF)

Zhaoyin Jia,  Andrew Gallagher,  Ashutosh Saxena,  Tsuhan Chen

Cumulative Attribute Space for Age and Crowd Density Estimation ( PDF)

Ke Chen,  Shaogang Gong,  Tao Xiang,  Chen Change Loy

Hallucinating Humans as the Hidden Context for Labeling 3D Scenes ( project,  videos,  PDF) - formely: Imagining People as the Hidden Context for Labeling 3D Scenes

Yun Jiang,  Hema Koppula,  Ashutosh Saxena

Measuring Crowd Collectiveness ( PDF,  videos,  project,  code,  dataset)

Bolei Zhou, Xiaogang Wang

Bringing Semantics Into Focus Using Visual Abstraction ( PDF)

Larry Zitnick,  Devi Parikh

Watching Unlabeled Video Helps Learn New Human Actions from Very Few Labeled Snapshots

Chao-Yeh Chen, Kristen Grauman

PatchMatch Filter: Efficient Edge-Aware Filtering Meets Randomized Search for Fast Correspondence Field Estimation

Jiangbo Lu, Hongsheng Yang, Dongbo Min, Minh Do

GeoF: Geodesic Forests for Learning Coupled Predictors ( PDF)

Peter Kontschieder,  Pushmeet Kohli,  Jamie Shotton,  Antonio Criminisi

Spatial Inference Machines ( PDF)

Roman Shapovalov,  Dmitry Vetrov,  Pushmeet Kohli

Discriminative Segment Annotation in Weakly Labeled Video

Kevin Tang, Rahul Sukthankar, Jay Yagnik, Li Fei-Fei

Efficient Large Scale Structured Learning

Steven Branson, Oscar Beijbom, Serge Belongie

Discriminative Non-blind Deblurring ( PDF)

Uwe Schmidt,  Carsten Rother,  Sebastian Nowozin,  Jeremy Jancsary,  Stefan Roth

Underwater Camera Calibration Using Wavelength Triangulation

Timothy Yau, Minglun Gong, Yee-Hong (or Herb) Yang

Diffusion Processes for Retrieval Revisited ( PDF,  project,  code)

Michael Donoser (TU Graz, Austria),  Horst Bischof (TU Graz, Austria)

Handling Noise in Single Image Deblurring using Directional Filters ( project,  PDF,  code)

Lin Zhong,  Sunghyun Cho,  Dimitris Metaxas,  Sylvain Paris,  Jue Wang

Photometric Ambient Occlusion ( project,  PDF)

Daniel Hauagge ( Cornell University),  Scott Wehrwein ( Cornell University),  Kavita Bala ( Cornell University),  Noah Snavely ( Cornell University)

Intrinsic Scene Properties from a Single RGB-D Image ( PDF,  supplementary material) - formely: Scene-SIRFS: Intrinsic Scene Properties from a Single RGB-D Image

Jonathan Barron, Jitendra Malik

Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images ( PDF,  supplementary material) - formely: Perceptual Organization and Recognition of Indoor Scenes from RGBD Images

Saurabh Gupta,  Pablo Arbelaez,  Jitendra Malik

Fast, Accurate Detection of 100,000 Object Classes on a Single Machine ( PDF)

Thomas Dean, Jay Yagnik, Mark Ruzon, Mark Segal, Jonathon` Shlens, Sudheendra Vijayanarasimhan

Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices ( PDF,  slides)

Sadeep Jayasumana, Richard Hartley, Mathieu Salzmann, Hongdong Li, Mehrtash Harandi

Higher is Better: High-dimensional Feature and Its Efficient Compression for Face Verification

Dong Chen, Xudong Cao, Fang Wen, Jian Sun

Dense Variational Reconstruction of Non-Rigid Surfaces from Monocular Video ( project,  PDF) - formely: A Variational Formulation for Dense Non Rigid Structure from Motion

Ravi Garg,  Anastasios Roussos,  Lourdes Agapito

A Comparative Study of Modern Inference Techniques for Discrete Energy Minimization Problems ( PDF,  code)

Joerg Kappes,  Bjoern Andres,  Fred Hamprecht,  Christoph Schnoerr,  Sebastian Nowozin,  Dhruv Batra,  Sungwoong Kim,  Bernhard Kausler,  Jan Lellmann,  Nikos Komodakis,  Carsten Rother

Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization ( project,  PDF,  supplementary material,  videos)

Marcus Brubaker (TTI Chicago),  Andreas Geiger (KIT & MPI Tubingen),  Raquel Urtasun (TTI Chicago)

Structure Preserving Object Tracking ( project)

Lu Zhang,  Laurens van der Maaten

Gauging Association Patterns of Chromosome Territories via Chromatic Median

Hu Ding, Branislav Stojkovic, Ronald Berezney, Jinhui Xu

What Motion Reveals About Shape With Unknown BRDF and Lighting

Manmohan Chandraker, Dikpal Reddy, Yizhou Wang, Ravi Ramamoorthi

Beyond Physical Connections: Tree Models in Human Pose Estimation

Yi Li, Fang Wang

Human Pose Estimation using Body Parts Dependent Joint Regressors ( project) - formely: Human Pose Estimation from Still Images using Body Parts Dependent Joint Regressors

Matthias Dantone,  Juergen Gall,  Christian Leistner,  Luc Van Gool

Video Object Segmentation through Spatially Accurate and Temporally Dense Extraction of Primary Object Regions ( PDF,  project)

Dong Zhang, Omar Javed,  Mubarak Shah

Robust Monocular Epipolar Flow Estimation ( PDF)

Koichiro Yamaguchi, David McAllester, Raquel Urtasun

Tracking Sports Players with Context-Conditioned Motion Models ( PDF)

Jingchen Liu, Peter Carr, Robert Collins, Yanxi Liu

Multi-target Tracking by Lagrangian Relaxation to Min-Cost Network Flow ( PDF)

Asad Butt,  Robert Collins

Cartesian k-means ( PDF)

Mohammad Norouzi, David J Fleet

Improving Image Matting using Comprehensive Sampling Sets

Ehsan Shahrian, Deepu Rajan, Brian Price, Scott Cohen

Hyperbolic Harmonic Mapping for Constrained Brain Surface Registration

Rui Shi, Wei Zeng, Zhengyu Su, Hanna Damasio, Zhonglin Lu, Yalin Wang, Shing-Tung Yau, Xianfeng Gu

Context-Aware Modeling and Recognition of Activities in Video

Yingying Zhu, Nandita Nayak, Amit Roy-Chowdhury

A Fast Semidefinite Approach to Solving Binary Quadratic Problems

PENG WANG, Chunhua Shen, Anton van den Hengel

Dense Reconstruction Using 3D Object Shape Priors

Amaury Dame, Victor Prisacariu, Carl Ren, Ian Reid

Dense Object Reconstruction with Semantic Priors ( PDF)

Yingze Bao, Manmohan Chandraker, Yuanqing Lin, Silvio Savarese

Poselet Conditioned Pictorial Structures ( PDF)

Leonid Pishchulin,  Mykhaylo Andriluka,  Peter Gehler,  Bernt Schiele

Procrustean Normal Distribution for Non-Rigid Structure from Motion ( project)

Minsik Lee,  Jungchan Cho, Chong-Ho Choi,  Songhwai Oh

Discrete MRF Inference of Marginal Densities for Non-uniformly Discretized Variable Space ( PDF,  supplementary material) - formely: Discrete Maximum Posterior Marginal Inference for Non-uniformly Discretized Variable Space

Masaki Saito, Takayuki Okatani, Koichiro Deguchi

Depth Acquisition from Density Modulated Binary Patterns ( PDF)

Zhe Yang,  Zhiwei Xiong, Yueyi Zhang, Jiao Wang,  Feng Wu

Learning Structured Hough Voting for Joint Object Detection and Occlusion Reasoning

Tao Wang, Xuming He, Nick Barnes

Auxiliary Cuts for General Classes of Non-Linear Constraints

Ismail BenAyed, Lena Gorelick, Yuri Boykov

Exploring Compositional High Order Pattern Potentials for Structured Output Learning ( PDF)

Yujia Li, Daniel Tarlow, Richard Zemel

Rolling Riemannian Manifolds to Solve the Multi-class Classification Problem

Rui Caseiro, Pedro Martins, João F. Henriques, Fátima Silva Leite, Jorge Batista

Posters

Transfer Sparse Coding for Robust Image Representation ( PDF)

Mingsheng Long, Guiguang Ding, Jianmin Wang, Yuchen Guo, Philip Yu

Boosting Binary Keypoint Descriptors

Tomasz Trzcinski, Mario Christoudias, Pascal Fua, Vincent Lepetit

Optical Flow Estimation using Laplacian Mesh Energy ( project)

Wenbin Li,  Darren Cosker,  Matthew Brown,  Rui Tang

Computationally Efficient Regression on a Dependency Graph for Human Pose Estimation ( PDF,  poster)

Kota Hara (UMD), Rama Chellappa (UMD)

Consensus of k-NNs for Robust Neighborhood Selection on Graph-Based Manifolds ( PDF)

Vittal Premachandran, Ramakrishna Kakarala

Learning Separable Filters ( PDF)

Roberto Rigamonti,  Amos Sironi,  Vincent Lepetit,  Pascal Fua

Five Shades of Grey for Fast and Reliable Camera Pose Estimation ( PDF)

Adam Herout, István Szentandrási, Michal Zachariás, Markéta Dubská, Rudolf Kajan

Learning for Structured Prediction Using Approximate Subgradient Descent with Working Sets ( PDF)