If you can read this text, your browser does not support Cascading Style Sheets. Although not essential for using this CD-ROM, you may wish to upgrade your browser to a more recent version.
08:30–09:45
Orals 1A: 3D Imaging and Reasoning (Oregon Ballroom 201-202)
Derek Hoiem (UIUC), Steve Seitz (Univ. of hington)
13D-Based Reasoning with Blocks, Support, and Stability
Authors:
9Physically Plausible 3D Scene Tracking: The Single Actor Hypothesis
Authors:
17Intrinsic Scene Properties from a Single RGB-D Image
Authors:
25Depth Acquisition from Density Modulated Binary Patterns
Authors:
33Understanding Indoor Scenes Using 3D Geometric Phrases
Authors:
08:30–09:45
Orals 1B: Statistics and Learning (Oregon Ballroom 203-204)
Ben Taskar (Univ. of Washington), Rene Vidal Johns Hopkins Univ.)
41Rolling Riemannian Manifolds to Solve the Multi-class Classification Problem
Authors:
49Exploring Compositional High Order Pattern Potentials for Structured Output Learning
Authors:
57Discrete MRF Inference of Marginal Densities for Non-uniformly Discretized Variable Space
Authors:
65GeoF: Geodesic Forests for Learning Coupled Predictors
Authors:
73Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices
Authors:
09:45–10:15
Posters 1A: 3D and Stereo (Oregon Ballroom 201-202)
Cornelia Fermüller (Univ. of Maryland), Claudia Nieuwenhuis (Technical Univ. of Munich)
81Manhattan Scene Understanding via XSlit Imaging
Authors:
89Discovering the Structure of a Planar Mirror System from Multiple Observations of a Single Point
Authors:
97Joint 3D Scene Reconstruction and Class Segmentation
Authors:
105Tensor-Based Human Body Modeling
Authors:
113City-Scale Change Detection in Cadastral 3D Models Using Images
Authors:
121Improving the Visual Comprehension of Point Sets
Authors:
129Mirror Surface Reconstruction from a Single Image
Authors:
Authors:
145Templateless Quasi-rigid Shape Modeling with Implicit Loop-Closure
Authors:
153Understanding Bayesian Rooms Using Composite 3D Object Models
Authors:
Authors:
169Joint Geodesic Upsampling of Depth Images
Authors:
177Relative Volume Constraints for Single View 3D Reconstruction
Authors:
185Is There a Procedural Logic to Architecture?
Authors:
Authors:
201Bayesian Grammar Learning for Inverse Procedural Modeling
Authors:
209Fusing Depth from Defocus and Stereo with Coded Apertures
Authors:
217Bayesian Depth-from-Defocus with Shading Constraints
Authors:
225Multi-scale Curve Detection on Surfaces
Authors:
233Intrinsic Characterization of Dynamic Surfaces
Authors:
241Pattern-Driven Colorization of 3D Surfaces
Authors:
249Three-Dimensional Bilateral Symmetry Plane Estimation in the Phase Domain
Authors:
257Axially Symmetric 3D Pots Configuration System Using Axis of Symmetry and Break Curve
Authors:
265Wide-Baseline Hair Capture Using Strand-Based Refinement
Authors:
273Dense 3D Reconstruction from Severely Blurred Images Using a Single Moving Camera
Authors:
281Simultaneous Super-Resolution of Depth and Images Using a Single Camera
Authors:
289Recovering Stereo Pairs from Anaglyphs
Authors:
297Exploiting the Power of Stereo Confidences
Authors:
305Ensemble Learning for Confidence Measures in Stereo Vision
Authors:
313Segment-Tree Based Cost Aggregation for Stereo Matching
Authors:
09:45–10:15
Posters 1B: Statistics and Learning (Oregon Ballroom 203-204)
Sebastian Nowozin (MS Research, Cambridge), Jean Ponce (Ecole Normale Supérieure)
321Multi-class Video Co-segmentation with a Generative Multi-video Model
Authors:
329A Bayesian Approach to Multimodal Visual Dictionary Learning
Authors:
337A Statistical Model for Recreational Trails in Aerial Images
Authors:
Authors:
353Dictionary Learning from Ambiguously Labeled Data
Authors:
361Generalized Domain-Adaptive Dictionaries
Authors:
369Tag Taxonomy Aware Dictionary Learning for Region Tagging
Authors:
377Block and Group Regularized Sparse Modeling for Dictionary Learning
Authors:
383Multi-level Discriminative Dictionary Learning towards Hierarchical Visual Categorization
Authors:
391Fast Convolutional Sparse Coding
Authors:
399In Defense of Sparsity Based Face Recognition
Authors:
407Transfer Sparse Coding for Robust Image Representation
Authors:
415Online Robust Dictionary Learning
Authors:
423Multi-task Sparse Learning with Beta Process Prior for Action Recognition
Authors:
430Scalable Sparse Subspace Clustering
Authors:
438Separable Dictionary Learning
Authors:
Authors:
452Improved Image Set Classification via Joint Sparse Approximated Nearest Subspaces
Authors:
460Optimizing 1-Nearest Prototype Classifiers
Authors:
468Sparse Subspace Denoising for Image Manifolds
Authors:
Authors:
484Learning Binary Codes for High-Dimensional Data Using Bilinear Projections
Authors:
492Semi-supervised Node Splitting for Random Forest Construction
Authors:
Authors:
508Alternating Decision Forests
Authors:
516Exploring Implicit Image Statistics for Visual Representativeness Modeling
Authors:
524A Divide-and-Conquer Method for Scalable Low-Rank Latent Matrix Pursuit
Authors:
532Supervised Descent Method and Its Applications to Face Alignment
Authors:
540Robust Canonical Time Warping for the Alignment of Grossly Corrupted Sequences
Authors:
548Relative Hidden Markov Models for Evaluating Motion Skill
Authors:
556A Fast Approximate AIB Algorithm for Distributional Word Clustering
Authors:
13:30–14:45
Orals 1C: Recognition (Oregon Ballroom 201-202)
Deva Ramanan (Univ. of California at Irvine), Jamie Shotton (Microsoft Research)
564Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images
Authors:
572Watching Unlabeled Video Helps Learn New Human Actions from Very Few Labeled Snapshots
Authors:
580Fine-Grained Crowdsourcing for Fine-Grained Recognition
Authors:
588Poselet Conditioned Pictorial Structures
Authors:
596Beyond Physical Connections: Tree Models in Human Pose Estimation
Authors:
13:30–14:45
Orals 1D: Imaging and Segmentation (Oregon Ballroom 203-204)
Michael Brown (National Univ. of Singapore), Josef Sivic (Ecole Normale Supérieure)
604Discriminative Non-blind Deblurring
Authors:
612Handling Noise in Single Image Deblurring Using Directional Filters
Authors:
Authors:
Authors:
636Improving Image Matting Using Comprehensive Sampling Sets
Authors:
14:45–15:25
Posters 1C: Recognition (Oregon Ballroom 201-202)
Kristen Grauman (Univ. of Texas at Austin), Devi Parikh (Virginia Tech)
644Simultaneous Active Learning of Classifiers & Attributes via Relative Feedback
Authors:
652Expanded Parts Model for Human Attribute and Action Recognition in Still Images
Authors:
660Multipath Sparse Coding Using Hierarchical Matching Pursuit
Authors:
668Semi-supervised Domain Adaptation with Instance Constraints
Authors:
676Learning Structured Low-Rank Representations for Image Classification
Authors:
684MKPLS: Manifold Kernel Partial Least Squares for Lipreading and Speaker Identification
Authors:
692Subspace Interpolation via Dictionary Learning for Unsupervised Domain Adaptation
Authors:
700Graph-Based Discriminative Learning for Location Recognition
Authors:
708Learning by Associating Ambiguously Labeled Images
Authors:
716HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences
Authors:
7243D R Transform on Spatio-temporal Interest Points for Action Recognition
Authors:
731Learning Cross-Domain Information Transfer for Location Recognition and Clustering
Authors:
739Studying Relationships between Human Gaze, Description, and Computer Vision
Authors:
Authors:
755Class Generative Models Based on Feature Regression for Pose Estimation of Object Categories
Authors:
Authors:
771Designing Category-Level Attributes for Discriminative Visual Recognition
Authors:
779Attribute-Based Detection of Unfamiliar Classes with Humans in the Loop
Authors:
787Object-Centric Anomaly Detection by Attribute-Based Reasoning
Authors:
795Learning Class-to-Image Distance with Object Matchings
Authors:
803Sample-Specific Late Fusion for Visual Category Recognition
Authors:
811Efficient Object Detection and Segmentation for Fine-Grained Recognition
Authors:
819Label-Embedding for Attribute-Based Classification
Authors:
827Subcategory-Aware Object Classification
Authors:
835Vantage Feature Frames for Fine-Grained Categorization
Authors:
843Probabilistic Label Trees for Efficient Large Scale Image Classification
Authors:
851Harvesting Mid-level Visual Concepts from Large-Scale Internet Images
Authors:
859Adaptive Active Learning for Image Classification
Authors:
Authors:
875Adding Unlabeled Samples to Categories by Learned Attributes
Authors:
883Visual Place Recognition with Repetitive Structures
Authors:
891Cross-View Image Geolocalization
Authors:
899Efficient 2D-to-3D Correspondence Filtering for Scalable 3D Object Recognition
Authors:
907Learning and Calibrating Per-Location Classifiers for Visual Place Recognition
Authors:
915An Approach to Pose-Based Action Recognition
Authors:
923Blocks That Shout: Distinctive Parts for Scene Classification
Authors:
931Part Discovery from Partial Correspondence
Authors:
939Learning Collections of Part Models for Object Recognition
Authors:
947Fast Multiple-Part Based Object Detection Using KD-Ferns
Authors:
Authors:
14:45–15:25
Posters 1D: Imaging (Oregon Ballroom 203-204)
James Hays (Brown Univ.), Kyoung Mu Lee (Seoul National Univ.)
963Non-parametric Filtering for Geometric Detail Extraction and Material Representation
Authors:
971Learning the Change for Automatic Image Cropping
Authors:
979Statistical Textural Distinctiveness for Salient Region Detection in Natural Images
Authors:
987Real-Time No-Reference Image Quality Assessment Based on Filter Learning
Authors:
995Learning without Human Scores for Blind Image Quality Assessment
Authors:
1003The Variational Structure of Disparity and Regularization of 4D Light Fields
Authors:
1011Globally Consistent Multi-label Assignment on the Ray Space of 4D Light Fields
Authors:
1019Principal Observation Ray Calibration for Tiled-Lens-Array Integral Imaging Display
Authors:
1027Decoding, Calibration and Rectification for Lenselet-Based Plenoptic Cameras
Authors:
1035Adherent Raindrop Detection and Removal in Video
Authors:
Authors:
1051Multi-image Blind Deblurring Using a Coupled Adaptive Sparse Prior
Authors:
1059Fast Image Super-Resolution Based on In-Place Example Regression
Authors:
1067A Machine Learning Approach for Non-blind Image Deconvolution
Authors:
1075Learning to Estimate and Remove Non-uniform Image Blur
Authors:
Authors:
1091Blur Processing Using Double Discrete Wavelet Transform
Authors:
1099Structured Face Hallucination
Authors:
1107Unnatural L0 Sparse Representation for Natural Image Deblurring
Authors:
1115Non-uniform Motion Deblurring for Bilayer Scenes
Authors:
1123Depth Super Resolution by Rigid Body Self-Similarity in 3D
Authors:
1131Saliency Aggregation: A Data-Driven Approach
Authors:
1139What Makes a Patch Distinct?
Authors:
1147Learning Video Saliency from Human Gaze Using Candidate Selection
Authors:
1155Hierarchical Saliency Detection
Authors:
1163HDR Deghosting: How to Deal with Saturation?
Authors:
1171FrameBreak: Dramatic Image Extrapolation by Guided Shift-Maps
Authors:
1179Video Enhancement of People Wearing Polarized Glasses: Darkening Reversal and Reflection Reduction
Authors:
1187Layer Depth Denoising and Completion for Structured-Light RGB-D Cameras
Authors:
1195Separating Signal from Noise Using Patch Recurrence across Scales
Authors:
1203Texture Enhanced Image Denoising via Gradient Histogram Preservation
Authors:
1211Fast Patch-Based Denoising Using Approximated Patch Geodesic Paths
Authors:
1219A New Model and Simple Algorithms for Multi-label Mumford-Shah Problems
Authors:
1227Computing Diffeomorphic Paths for Large Motion Interpolation
Authors:
1233Rotation, Scaling and Deformation Invariant Scattering for Texture Discrimination
Authors:
1241Sensing and Recognizing Surface Textures Using a GelSight Sensor
Authors:
1248Enriching Texture Analysis with Semantic Data
Authors:
08:30–09:45
Orals 2A: Motion and Reconstruction (Oregon Ballroom 201-202)
Marc Pollefeys (ETH Zurich), Noah Snavely (Cornell Univ.)
1256Megastereo: Constructing High-Resolution Stereo Panoramas
Authors:
1264Dense Object Reconstruction with Semantic Priors
Authors:
1272Dense Variational Reconstruction of Non-rigid Surfaces from Monocular Video
Authors:
1280Procrustean Normal Distribution for Non-rigid Structure from Motion
Authors:
1288Dense Reconstruction Using 3D Object Shape Priors
Authors:
08:30–09:45
Orals 2B: Optimization Methods (Oregon Ballroom 203-204)
Sameer Agarwal (Google), Pushmeet Kohli (Microsoft Research Cambridge)
1296Gauging Association Patterns of Chromosome Territories via Chromatic Median
Authors:
1304Auxiliary Cuts for General Classes of Higher Order Functionals
Authors:
1312A Fast Semidefinite Approach to Solving Binary Quadratic Problems
Authors:
1320Diffusion Processes for Retrieval Revisited
Authors:
1328A Comparative Study of Modern Inference Techniques for Discrete Energy Minimization Problems
Authors:
09:45–10:15
Posters 2A: Pose and Photometry (Oregon Ballroom 201-202)
Katsushi Ikeuchi (Univ. of Tokyo), Yasuyuki Matsushita (Microsoft Research Asia)
1336A Global Approach for the Detection of Vanishing Points and Mutually Orthogonal Vanishing Directions
Authors:
1344Cloud Motion as a Calibration Cue
Authors:
1352SLAM++: Simultaneous Localisation and Mapping at the Level of Objects
Authors:
1360Rolling Shutter Camera Calibration
Authors:
1368Radial Distortion Self-Calibration
Authors:
Authors:
1384Five Shades of Grey for Fast and Reliable Camera Pose Estimation
Authors:
1391Can a Fully Unconstrained Imaging Model Be Applied Effectively to Central Cameras?
Authors:
1399Single Image Calibration of Multi-axial Imaging Systems
Authors:
1407The Episolar Constraint: Monocular Shape from Shadow Correspondence
Authors:
1415Shading-Based Shape Refinement of RGB-D Images
Authors:
1423Illumination Estimation Based on Bilayer Sparse Coding
Authors:
Authors:
1438A Theory of Refractive Photo-Light-Path Triangulation
Authors:
Authors:
1452Spectral Modeling and Relighting of Reflective-Fluorescent Scenes
Authors:
1460Specular Reflection Separation Using Dark Channel Prior
Authors:
1468BRDF Slices: Accurate Adaptive Anisotropic Appearance Acquisition
Authors:
1474A New Perspective on Uncalibrated Photometric Stereo
Authors:
1482Multi-view Photometric Stereo with Spatially Varying Isotropic Materials
Authors:
1490Uncalibrated Photometric Stereo for Unknown Isotropic Reflectances
Authors:
1498Calibrating Photometric Stereo by Holistic Reflectance Symmetry Analysis
Authors:
1506Articulated and Restricted Motion Subspaces and Their Signatures
Authors:
Authors:
1522Monocular Template-Based 3D Reconstruction of Extensible Surfaces with Local Linear Elasticity
Authors:
1530Non-rigid Structure from Motion with Diffusion Maps Prior
Authors:
1538Joint Detection, Tracking and Mapping by Semantic Bundle Adjustment
Authors:
1546A Practical Rank-Constrained Eight-Point Algorithm for Fundamental Matrix Estimation
Authors:
1554CLAM: Coupled Localization and Mapping with Efficient Outlier Handling
Authors:
09:45–10:15
Posters 2B: Methods and Retrieval (Oregon Ballroom 203-204)
Yuri Boykov (Univ. of Western Ontario), Fredrik Kahl (Lund Univ.)
1562Inductive Hashing on Manifolds
Authors:
1570Hash Bit Selection: A Unified Solution for Selection Problems in Hashing
Authors:
1578All About VLAD
Authors:
1586Binary Code Ranking with Weighted Hamming Distance
Authors:
1594Consensus of k-NNs for Robust Neighborhood Selection on Graph-Based Manifolds
Authors:
1602Topical Video Object Discovery from Key Frames by Modeling Word Co-occurrence Prior
Authors:
1610Query Adaptive Similarity for Large Scale Object Retrieval
Authors:
1618Image Tag Completion via Image-Specific and Tag-Specific Linear Sparse Reconstructions
Authors:
1626Lp-Norm IDF for Large Scale Image Search
Authors:
Authors:
1642Learning a Manifold as an Atlas
Authors:
1650Semi-supervised Learning of Feature Hierarchies for Object Detection in a Video
Authors:
1658Fully-Connected CRFs with Non-Parametric Pairwise Potential
Authors:
1666Discriminative Sub-categorization
Authors:
1674Whitened Expectation Propagation: Non-Lambertian Shape from Shading and Shadow
Authors:
1682Fast Energy Minimization Using Learned State Filters
Authors:
1690Bilinear Programming for Human Activity Recognition with Unknown MRF Graphs
Authors:
1698A Higher-Order CRF Model for Road Network Extraction
Authors:
1706Nonlinearly Constrained MRFs: Exploring the Intrinsic Dimensions of Higher-Order Cliques
Authors:
1714Fast Trust Region for Segmentation
Authors:
1722Optimal Geometric Fitting under the Truncated L2-Norm
Authors:
1730In Defense of 3D-Label Stereo
Authors:
1738Universality of the Local Marginal Polytope
Authors:
1744Continuous Inference in Graphical Models with Polynomial Energies
Authors:
Authors:
1759An Iterated L1 Algorithm for Non-smooth Non-convex Optimization in Computer Vision
Authors:
1767A Genetic Algorithm-Based Solver for Very Large Jigsaw Puzzles
Authors:
1775A Convex Regularize for Reducing Color Artifact in Color Image Recovery
Authors:
1782Kernel Learning for Extrinsic Classification of Manifold Features
Authors:
13:30–14:45
Orals 2C: Detection (+Medical/Curves) (Oregon Ballroom 201-202)
Jason Corso (SUNY at Buffalo), Larry Zitnick (Microsoft Research)
1790Learning Structured Hough Voting for Joint Object Detection and Occlusion Reasoning
Authors:
1798Detection Evolution with Multi-order Contextual Co-occurrence
Authors:
1806Efficient Large-Scale Structured Learning
Authors:
1814Fast, Accurate Detection of 100,000 Object Classes on a Single Machine
Authors:
1822Reconstructing Loopy Curvilinear Structures Using Integer Programming
Authors:
13:30–14:45
Orals 2D: Tracking and Flow (Oregon Ballroom 203-204)
David Forsyth (UIUC), Stefan Roth (Technishe Universität Darmstadt)
1830Tracking Sports Players with Context-Conditioned Motion Models
Authors:
1838Structure Preserving Object Tracking
Authors:
1846Multi-target Tracking by Lagrangian Relaxation to Min-cost Network Flow
Authors:
Authors:
1862Robust Monocular Epipolar Flow Estimation
Authors:
14:45–15:25
Posters 2C: Segmentation and Shape (Oregon Ballroom 201-202)
Jitendra Malik (Univ. of California at Berkeley), Andrea Vedaldi (Univ. of Oxford)
1870Deep Learning Shape Priors for Object Segmentation
Authors:
1878PDM-ENLOR: Learning Ensemble of Local PDM-Based Regressions
Authors:
Authors:
1894Recovering Line-Networks in Images by Junction-Point Processes
Authors:
1902Image Matting with Local and Nonlocal Smooth Priors
Authors:
Authors:
1916Towards Fast and Accurate Segmentation
Authors:
1923Discriminative Re-ranking of Diverse Segmentations
Authors:
1931Robust Region Grouping via Internal Patch Statistics
Authors:
1939Unsupervised Joint Object Discovery and Segmentation in Internet Images
Authors:
1947Ensemble Video Object Cut in Highly Dynamic Scenes
Authors:
Authors:
1963Top-Down Segmentation of Non-rigid Visual Objects Using Derivative-Based Search on Sparse Manifolds
Authors:
1971A Principled Deep Random Field Model for Image Segmentation
Authors:
1979Background Modeling Based on Bidirectional Analysis
Authors:
1987Learning for Structured Prediction Using Approximate Subgradient Descent with Working Sets
Authors:
1995A Sentence Is Worth a Thousand Pixels
Authors:
2003GRASP Recurring Patterns from a Single View
Authors:
2011Image Segmentation by Cascaded Region Agglomeration
Authors:
2019Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling
Authors:
2027Voxel Cloud Connectivity Segmentation - Supervoxels for Point Clouds
Authors:
2035SCALPEL: Segmentation Cascades with Localized Priors and Efficient Learning
Authors:
2043Submodular Salient Region Detection
Authors:
2051A Video Representation Using Temporal Superpixels
Authors:
2059Pose from Flow and Flow from Pose
Authors:
2067Mesh Based Semantic Modelling for Indoor and Outdoor Scenes
Authors:
2075Weakly-Supervised Dual Clustering for Image Semantic Segmentation
Authors:
2083Salient Object Detection: A Discriminative Regional Feature Integration Approach
Authors:
2091Revisiting Depth Layers from Occlusions
Authors:
2099Hierarchical Video Representation with Trajectory Binary Partition Tree
Authors:
2107Discriminative Subspace Clustering
Authors:
Authors:
2123Boundary Detection Benchmarking: Beyond F-Measures
Authors:
2131Measures and Meta-Measures for the Supervised Evaluation of Image Segmentation
Authors:
Authors:
2147Robust Estimation of Nonrigid Transformation for Point Set Registration
Authors:
2155Efficient Computation of Shortest Path-Concavity for 3D Meshes
Authors:
2163Boundary Cues for 3D Object Shape Recovery
Authors:
2171A Linear Approach to Matching Cuboids in RGBD Images
Authors:
14:45–15:25
Posters 2D: Motion and Medical Imaging (Oregon Ballroom 203-204)
Leo Grady (HeartFlow, Inc.), Vincent Lepetit (EPFL)
Authors:
Authors:
2195Adaptive Compressed Tomography Sensing
Authors:
2203Classification of Tumor Histology via Morphometric Context
Authors:
2211Efficient 3D Endfiring TRUS Prostate Segmentation with Globally Optimized Rotational Symmetry
Authors:
2219Graph-Based Optimization with Tubularity Markov Tree for 3D Vessel Segmentation
Authors:
2227Prostate Segmentation in CT Images via Spatial-Constrained Transductive Lasso
Authors:
2235Area Preserving Brain Mapping
Authors:
Authors:
2251Compressible Motion Fields
Authors:
2259Fast Rigid Motion Segmentation via Incrementally-Complex Local Models
Authors:
2267Determining Motion Directly from Normal Flows Upon the Use of a Spherical Eye Platform
Authors:
2275Correspondence-Less Non-rigid Registration of Triangular Surface Meshes
Authors:
2283Video Editing with Temporal, Spatial and Appearance Consistency
Authors:
2291Correlation Filters for Object Alignment
Authors:
2299Plane-Based Content Preserving Warps for Video Stabilization
Authors:
2307Deformable Spatial Pyramid Matching for Fast Dense Correspondences
Authors:
2315The Generalized Laplacian Distance and Its Applications for Visual Matching
Authors:
2323Groupwise Registration via Graph Shrinkage on the Image Manifold
Authors:
2331FasT-Match: Fast Affine Template Matching
Authors:
2339As-Projective-As-Possible Image Stitching with Moving DLT
Authors:
Authors:
2355Minimum Uncertainty Gap for Robust Visual Tracking
Authors:
2363Part-Based Visual Tracking with Online Latent Structural Learning
Authors:
2371Least Soft-Threshold Squares Tracking
Authors:
2379Self-Paced Learning for Long-Term Tracking
Authors:
2387Multi-target Tracking by Rank-1 Tensor Approximation
Authors:
2395Robust Real-Time Tracking of Multiple Objects by Volumetric Mass Densities
Authors:
2403Information Consensus for Distributed Multi-target Tracking
Authors:
2411Online Object Tracking: A Benchmark
Authors:
2419Learning Compact Binary Codes for Visual Tracking
Authors:
2427Visual Tracking via Locality Sensitive Histograms
Authors:
2435Optical Flow Estimation Using Laplacian Mesh Energy
Authors:
2443Large Displacement Optical Flow from Nearest Neighbor Fields
Authors:
2451A Fully-Connected Layered Model of Foreground and Background Flow
Authors:
08:30–09:45
Orals 3A: Video (Oregon Ballroom 201-202)
Irfan Essa (Georgia Tech), Ivan Laptev (INRIA)
2459Event Retrieval in Large Video Collections with Circulant Temporal Encoding
Authors:
2467Cumulative Attribute Space for Age and Crowd Density Estimation
Authors:
2475Social Role Discovery in Human Events
Authors:
2483Discriminative Segment Annotation in Weakly Labeled Video
Authors:
2491Context-Aware Modeling and Recognition of Activities in Video
Authors:
08:30–09:45
Orals 3B: Geometry and Physics (+Medical) (Oregon Ballroom 203-204)
Kyros Kutulakos (Univ. of Toronto), Ko Nishino (Drexel Univ.)
2499Underwater Camera Calibration Using Wavelength Triangulation
Authors:
2507Reconstructing Gas Flows Using Light-Path Approximation
Authors:
2515Photometric Ambient Occlusion
Authors:
2523What Object Motion Reveals about Shape with Unknown BRDF and Lighting
Authors:
2531Hyperbolic Harmonic Mapping for Constrained Brain Surface Registration
Authors:
09:45–10:15
Posters 3A: Video Analysis (Oregon Ballroom 201-202)
Silvio Savarese (Univ. of Michigan), Cordelia Schmid (INRIA)
2539Crossing the Line: Crowd Counting by Integer Programming with Local Features
Authors:
2547Multi-source Multi-scale Counting in Extremely Dense Crowd Images
Authors:
2555Better Exploiting Motion for Better Action Recognition
Authors:
2563Detection of Manipulation Action Consequences (MAC)
Authors:
2571Representing Videos Using Mid-level Discriminative Patches
Authors:
2579Modeling Actions through State Changes
Authors:
2587Recognizing Activities via Bag of Words for Attribute Dynamics
Authors:
2595Sampling Strategies for Real-Time Action Recognition
Authors:
2603Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis
Authors:
2611Online Dominant and Anomalous Behavior Detection in Videos
Authors:
Authors:
2627Complex Event Detection via Multi-source Video Attributes
Authors:
Authors:
2642Spatiotemporal Deformable Part Models for Action Detection
Authors:
2650Poselet Key-Framing: A Model for Human Activity Recognition
Authors:
2658Recognize Human Activities from Partially Observed Videos
Authors:
2666Event Recognition in Videos by Learning from Heterogeneous Web Sources
Authors:
2674Motionlets: Mid-level 3D Parts for Human Motion Recognition
Authors:
2682Multi-agent Event Detection: Localization and Role Assignment
Authors:
2690Cross-View Action Recognition via a Continuous Virtual Path
Authors:
2698Large-Scale Video Summarization Using Web-Image Priors
Authors:
2706Representing and Discovering Adversarial Team Behaviors Using Player Roles
Authors:
2714Story-Driven Summarization for Egocentric Video
Authors:
2722Finding Group Interactions in Social Clutter
Authors:
2730First-Person Activity Recognition: What Are They Doing to Me?
Authors:
2738Joint Sparsity-Based Representation and Analysis of Unconstrained Activities
Authors:
2746Motion Estimation for Self-Driving Cars with a Generalized Camera
Authors:
09:45–10:15
Posters 3B: Features and Contours (Oregon Ballroom 203-204)
Svetlana Lazebnik (UIUC), Yoichi Sato (Univ. of Tokyo)
2754Learning Separable Filters
Authors:
2762Robust Feature Matching with Alternate Hough and Inverted Hough Transforms
Authors:
2770SWIGS: A Swift Guided Sampling Method
Authors:
2778Learning Multiple Non-linear Sub-spaces Using K-RBMs
Authors:
2786Light Field Distortion Feature for Transparent Object Recognition
Authors:
2794From Local Similarity to Global Coding: An Application to Image Classification
Authors:
2802Joint Spectral Correspondence for Disparate Image Matching
Authors:
2810Efficient Color Boundary Detection with Color-Opponent Mechanisms
Authors:
2818Winding Number for Region-Boundary Consistent Salient Contour Extraction
Authors:
2826Supervised Semantic Gradient Extraction Using Linear-Time Optimization
Authors:
2834Spatio-temporal Depth Cuboid Similarity Feature for Activity Recognition Using Depth Camera
Authors:
2842Sparse Quantization for Patch Description
Authors:
2850Evaluation of Color STIPs for Human Action Recognition
Authors:
2858Supervised Kernel Descriptors for Visual Recognition
Authors:
2866Discriminative Color Descriptors
Authors:
2874Boosting Binary Keypoint Descriptors
Authors:
2882Exploring Weak Stabilization for Motion Feature Extraction
Authors:
2890Dense Segmentation-Aware Descriptors
Authors:
2898Keypoints from Symmetries by Wave Propagation
Authors:
2906Graph Matching with Anchor Nodes: A Learning Approach
Authors:
2914Dense Non-rigid Point-Matching Using Random Projections
Authors:
Authors:
2930Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images
Authors:
2938K-Means Hashing: An Affinity-Preserving Quantization Method for Learning Binary Compact Codes
Authors:
2946Optimized Product Quantization for Approximate Nearest Neighbor Search
Authors:
2954A Non-parametric Framework for Document Bleed-through Removal
Authors:
2961Scene Text Recognition Using Part-Based Tree-Structured Character Detection
Authors:
2969Active Contours with Group Similarity
Authors:
2977Accurate and Robust Registration of Nonrigid Surface Using Hierarchical Statistical Shape Model
Authors:
13:30–14:45
Orals 3C: Context and Scenes (+ANN) (Oregon Ballroom 201-202)
Tamara Berg (Stony Brook Univ.), Fei-Fei Li (Stanford Univ.)
2985Spatial Inference Machines
Authors:
2993Hallucinated Humans as the Hidden Context for Labeling 3D Scenes
Authors:
3001Finding Things: Image Parsing with Regions and Per-Exemplar Detectors
Authors:
3009Bringing Semantics into Focus Using Visual Abstraction
Authors:
Authors:
13:30–14:45
Orals 3D: Faces, People, and Crowds (Oregon Ballroom 203-204)
Erik Learned-Miller (Univ. of Massachusetts), Bernt Schiele (Max Planck Institute)
Authors:
3033Robust Multi-resolution Pedestrian Detection in Traffic Scenes
Authors:
3041Human Pose Estimation Using Body Parts Dependent Joint Regressors
Authors:
3049Measuring Crowd Collectiveness
Authors:
3057Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization
Authors:
14:45–15:25
Posters 3C: Objects and Scenes (Oregon Ballroom 201-202)
Alexander Berg (Stony Brook Univ.), Vittorio Ferrari (Univ. of Edinburgh)
3065Manhattan Junction Catalogue for Spatial Reasoning of Indoor Scenes
Authors:
3073Tensor-Based High-Order Semantic Relation Transfer for Semantic Scene Segmentation
Authors:
3081Geometric Context from Videos
Authors:
3089It's Not Polite to Point: Describing People with Uncertain Attributes
Authors:
3097Heterogeneous Visual Features Fusion via Sparse Multimodal Machine
Authors:
3103A Max-Margin Riffled Independence Model for Image Tag Ranking
Authors:
3111Weakly Supervised Learning for Attribute Localization in Outdoor Scenes
Authors:
3119Scene Parsing by Integrating Function, Geometry and Appearance Models
Authors:
3127Beyond Point Clouds: Scene Understanding by Reasoning Geometry and Physics
Authors:
3135Label Propagation from ImageNet to 3D Point Clouds
Authors:
3143Analyzing Semantic Segmentation Using Hybrid Human-Machine CRFs
Authors:
3151Nonparametric Scene Parsing with Adaptive Feature Relevance and Semantic Context
Authors:
3158Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection
Authors:
3166Saliency Detection via Graph-Based Manifold Ranking
Authors:
3174Maximum Cohesive Grid of Superpixels for Fast Object Localization
Authors:
3182Accurate Localization of 3D Objects from RGB-D Data Using Segmentation Hypotheses
Authors:
3190Efficient Maximum Appearance Search for Large-Scale Object Detection
Authors:
3198Single-Pedestrian Detection Aided by Multi-pedestrian Detection
Authors:
3206Robust Object Co-detection
Authors:
3214Integrating Grammar and Segmentation for Human Pose Estimation
Authors:
3222Modeling Mutual Visibility Relationship in Pedestrian Detection
Authors:
3230Learning to Detect Partially Overlapping Instances
Authors:
3238Looking Beyond the Image: Unsupervised Learning for Object Saliency and Detection
Authors:
3246Histograms of Sparse Codes for Object Detection
Authors:
3254Efficient Detector Adaptation for Object Detection in a Video
Authors:
3262A Lazy Man's Approach to Benchmarking: Semisupervised Classifier Evaluation and Recalibration
Authors:
3270Fast Object Detection with Entropy-Driven Evaluation
Authors:
3278Discriminatively Trained And-Or Tree Models for Object Detection
Authors:
3286Occlusion Patterns for Object Class Detection
Authors:
3294Bottom-Up Segmentation for Top-Down Detection
Authors:
3302Composite Statistical Inference for Semantic Segmentation
Authors:
3310Multi-attribute Queries: To Merge or Not to Merge?
Authors:
3318Local Fisher Discriminant Analysis for Pedestrian Re-identification
Authors:
3326Explicit Occlusion Modeling for 3D Object Class Representations
Authors:
Authors:
3342Articulated Pose Estimation Using Discriminative Armlet Classifiers
Authors:
3350Sparse Output Coding for Large-Scale Visual Recognition
Authors:
3358From N to N+1: Multiclass Transfer Incremental Learning
Authors:
3366What's in a Name? First Names as Facial Attributes
Authors:
3374Kernel Null Space Methods for Novelty Detection
Authors:
14:45–15:25
Posters 3D: People and Faces (Oregon Ballroom 203-204)
Terry Boult (Univ. of Colorado, Colorado Springs), Lihi Zelnik-Manor (Technion)
3382Expressive Visual Text-to-Speech Using Active Appearance Models
Authors:
3390Computationally Efficient Regression on a Dependency Graph for Human Pose Estimation
Authors:
3398Hollywood 3D: Recognizing Actions in 3D Natural Scenes
Authors:
34063D Visual Proxemics: Recognizing Human Interactions in 3D from a Single Image
Authors:
3414Decoding Children's Social Behavior
Authors:
3422Capturing Complex Spatio-temporal Relations among Facial Muscles for Facial Expression Recognition
Authors:
3430Detecting Pulse from Head Motions in Video
Authors:
3438Towards Contactless, Low-Cost and Accurate 3D Fingerprint Identification
Authors:
3444Robust Discriminative Response Map Fitting with Constrained Local Models
Authors:
Authors:
3460Detecting and Aligning Faces by Image Retrieval
Authors:
3468Learning SURF Cascade for Fast and Accurate Object Detection
Authors:
3476Deep Convolutional Network Cascade for Facial Point Detection
Authors:
3484Exemplar-Based Face Parsing
Authors:
3492Graph-Laplacian PCA: Closed-Form Solution and Robustness
Authors:
3499Probabilistic Elastic Matching for Pose Variant Face Verification
Authors:
3507Constrained Clustering and Its Application to Face Clustering in Videos
Authors:
3515Selective Transfer Machine for Personalized Facial Action Unit Detection
Authors:
3523The SVM-Minus Similarity Score for Video Face Recognition
Authors:
3531Face Recognition in Movie Trailers via Mean Sequence Sparse Representation-Based Classification
Authors:
3539Towards Pose Robust Face Recognition
Authors:
Authors:
3554Fusing Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild
Authors:
3562Action Recognition by Hierarchical Sequence Summarization
Authors:
3570Pixel-Level Hand Detection in Ego-centric Videos
Authors:
3578Human Pose Estimation Using a Joint Pixel-wise and Part-wise Formulation
Authors:
3586Unsupervised Salience Learning for Person Re-identification
Authors:
3594Locally Aligned Feature Transforms across Views
Authors:
3602Semi-supervised Learning with Constraints for Person Identification in Multimedia Data
Authors:
3610Learning Locally-Adaptive Decision Functions for Person Verification
Authors:
36183D Pictorial Structures for Multiple View Articulated Pose Estimation
Authors:
3626Pedestrian Detection with Unsupervised Multi-stage Feature Learning
Authors:
3634A Joint Model for 2D and 3D Pose Estimation from a Single Image
Authors:
Authors:
3650Hypergraphs for Joint Multi-view Reconstruction and Multi-object Tracking
Authors:
3658Tracking People and Their Objects
Authors:
3666Seeking the Strongest Rigid Detector
Authors:
3674MODEC: Multimodal Decomposable Models for Human Pose Estimation
Authors:
3682Detection- and Trajectory-Level Exclusion in Multiple Object Tracking
Authors:
3690Optimized Pedestrian Detection for Multiple and Occluded People
Authors:
3698Long-Term Occupancy Analysis Using Graph-Based Optimisation in Thermal Imagery
Authors:
3706Detecting and Naming Actors in Movies Using Generative Appearance Models
Authors:
Authors:
3721Improving an Object Detector and Extracting Regions Using Superpixels
Authors:
3728Tracking Human Pose by Tracking Symmetric Parts
Authors: