Pamitc


TUESDAY, June 25



08:30-09:45Orals (5) - 2 x parallel
Orals 1A - 3D Imaging and Reasoning Orals 1B - Statistics and Learning
3D-Based Reasoning with Blocks, Support, and Stability Rolling Riemannian Manifolds to Solve the Multi-class Classification Problem
Physically Plausible 3D Scene Tracking: The Single Actor Hypothesis Exploring Compositional High Order Pattern Potentials for Structured Output Learning
Intrinsic Scene Properties from a Single RGB-D Image Discrete MRF Inference of Marginal Densities for Non-uniformly Discretized Variable Space
Depth Acquisition from Density Modulated Binary Patterns GeoF: Geodesic Forests for Learning Coupled Predictors
Understanding Indoor Scenes Using 3D Geometric Phrases Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices
 
09:45-10:15Spotlights (30 posters) - 2 x parallel
Spotlights 1A - 3D and Stereo Spotlights 1B - Statistics and Learning
Manhattan Scene Understanding via XSlit Imaging Multi-class Video Co-segmentation with a Generative Multi-video Model
Discovering the Structure of a Planar Mirror System from Multiple Observations of a Single Point A Bayesian Approach to Multimodal Visual Dictionary Learning
Joint 3D Scene Reconstruction and Class Segmentation A Statistical Model for Recreational Trails in Aerial Images
Tensor-Based Human Body Modeling Beta Process Joint Dictionary Learning for Coupled Feature Spaces with Application to Single Image Super-Resolution
City-Scale Change Detection in Cadastral 3D Models Using Images Dictionary Learning from Ambiguously Labeled Data
Improving the Visual Comprehension of Point Sets Generalized Domain-Adaptive Dictionaries
Mirror Surface Reconstruction from a Single Image Tag Taxonomy Aware Dictionary Learning for Region Tagging
Detecting Changes in 3D Structure of a Scene from Multi-view Images Captured by a Vehicle-Mounted Camera Block and Group Regularized Sparse Modeling for Dictionary Learning
Templateless Quasi-rigid Shape Modeling with Implicit Loop-Closure Multi-level Discriminative Dictionary Learning towards Hierarchical Visual Categorization
Understanding Bayesian Rooms Using Composite 3D Object Models Fast Convolutional Sparse Coding
Shape from Silhouette Probability Maps: Reconstruction of Thin Objects in the Presence of Silhouette Extraction and Calibration Error In Defense of Sparsity Based Face Recognition
Joint Geodesic Upsampling of Depth Images Transfer Sparse Coding for Robust Image Representation
Relative Volume Constraints for Single View 3D Reconstruction Online Robust Dictionary Learning
Is There a Procedural Logic to Architecture? Multi-task Sparse Learning with Beta Process Prior for Action Recognition
Category Modeling from Just a Single Labeling: Use Depth Information to Guide the Learning of 2D Models Scalable Sparse Subspace Clustering
Bayesian Grammar Learning for Inverse Procedural Modeling Separable Dictionary Learning
Fusing Depth from Defocus and Stereo with Coded Apertures Compressed Hashing
Bayesian Depth-from-Defocus with Shading Constraints Improved Image Set Classification via Joint Sparse Approximated Nearest Subspaces
Multi-scale Curve Detection on Surfaces Optimizing 1-Nearest Prototype Classifiers
Intrinsic Characterization of Dynamic Surfaces Sparse Subspace Denoising for Image Manifolds
Pattern-Driven Colorization of 3D Surfaces Weakly Supervised Learning of Mid-Level Features with Beta-Bernoulli Process Restricted Boltzmann Machines
Three-Dimensional Bilateral Symmetry Plane Estimation in the Phase Domain Learning Binary Codes for High-Dimensional Data Using Bilinear Projections
Axially Symmetric 3D Pots Configuration System Using Axis of Symmetry and Break Curve Semi-supervised Node Splitting for Random Forest Construction
Wide-Baseline Hair Capture Using Strand-Based Refinement Capturing Layers in Image Collections with Componential Models: From the Layered Epitome to the Componential Counting Grid
Dense 3D Reconstruction from Severely Blurred Images Using a Single Moving Camera Alternating Decision Forests
Simultaneous Super-Resolution of Depth and Images Using a Single Camera Exploring Implicit Image Statistics for Visual Representativeness Modeling
Recovering Stereo Pairs from Anaglyphs A Divide-and-Conquer Method for Scalable Low-Rank Latent Matrix Pursuit
Exploiting the Power of Stereo Confidences Supervised Descent Method and Its Applications to Face Alignment
Ensemble Learning for Confidence Measures in Stereo Vision Robust Canonical Time Warping for the Alignment of Grossly Corrupted Sequences
Segment-Tree Based Cost Aggregation for Stereo Matching Relative Hidden Markov Models for Evaluating Motion Skill
A Fast Approximate AIB Algorithm for Distributional Word Clustering
 
10:15-12:00Posters and refreshments (first 30 minutes)
Posters 1A - 3D and Stereo Posters 1B - Statistics and Learning
Manhattan Scene Understanding via XSlit Imaging Multi-class Video Co-segmentation with a Generative Multi-video Model
Discovering the Structure of a Planar Mirror System from Multiple Observations of a Single Point A Bayesian Approach to Multimodal Visual Dictionary Learning
Joint 3D Scene Reconstruction and Class Segmentation A Statistical Model for Recreational Trails in Aerial Images
Tensor-Based Human Body Modeling Beta Process Joint Dictionary Learning for Coupled Feature Spaces with Application to Single Image Super-Resolution
City-Scale Change Detection in Cadastral 3D Models Using Images Dictionary Learning from Ambiguously Labeled Data
Improving the Visual Comprehension of Point Sets Generalized Domain-Adaptive Dictionaries
Mirror Surface Reconstruction from a Single Image Tag Taxonomy Aware Dictionary Learning for Region Tagging
Detecting Changes in 3D Structure of a Scene from Multi-view Images Captured by a Vehicle-Mounted Camera Block and Group Regularized Sparse Modeling for Dictionary Learning
Templateless Quasi-rigid Shape Modeling with Implicit Loop-Closure Multi-level Discriminative Dictionary Learning towards Hierarchical Visual Categorization
Understanding Bayesian Rooms Using Composite 3D Object Models Fast Convolutional Sparse Coding
Shape from Silhouette Probability Maps: Reconstruction of Thin Objects in the Presence of Silhouette Extraction and Calibration Error In Defense of Sparsity Based Face Recognition
Joint Geodesic Upsampling of Depth Images Transfer Sparse Coding for Robust Image Representation
Relative Volume Constraints for Single View 3D Reconstruction Online Robust Dictionary Learning
Is There a Procedural Logic to Architecture? Multi-task Sparse Learning with Beta Process Prior for Action Recognition
Category Modeling from Just a Single Labeling: Use Depth Information to Guide the Learning of 2D Models Scalable Sparse Subspace Clustering
Bayesian Grammar Learning for Inverse Procedural Modeling Separable Dictionary Learning
Fusing Depth from Defocus and Stereo with Coded Apertures Compressed Hashing
Bayesian Depth-from-Defocus with Shading Constraints Improved Image Set Classification via Joint Sparse Approximated Nearest Subspaces
Multi-scale Curve Detection on Surfaces Optimizing 1-Nearest Prototype Classifiers
Intrinsic Characterization of Dynamic Surfaces Sparse Subspace Denoising for Image Manifolds
Pattern-Driven Colorization of 3D Surfaces Weakly Supervised Learning of Mid-Level Features with Beta-Bernoulli Process Restricted Boltzmann Machines
Three-Dimensional Bilateral Symmetry Plane Estimation in the Phase Domain Learning Binary Codes for High-Dimensional Data Using Bilinear Projections
Axially Symmetric 3D Pots Configuration System Using Axis of Symmetry and Break Curve Semi-supervised Node Splitting for Random Forest Construction
Wide-Baseline Hair Capture Using Strand-Based Refinement Capturing Layers in Image Collections with Componential Models: From the Layered Epitome to the Componential Counting Grid
Dense 3D Reconstruction from Severely Blurred Images Using a Single Moving Camera Alternating Decision Forests
Simultaneous Super-Resolution of Depth and Images Using a Single Camera Exploring Implicit Image Statistics for Visual Representativeness Modeling
Recovering Stereo Pairs from Anaglyphs A Divide-and-Conquer Method for Scalable Low-Rank Latent Matrix Pursuit
Exploiting the Power of Stereo Confidences Supervised Descent Method and Its Applications to Face Alignment
Ensemble Learning for Confidence Measures in Stereo Vision Robust Canonical Time Warping for the Alignment of Grossly Corrupted Sequences
Segment-Tree Based Cost Aggregation for Stereo Matching Relative Hidden Markov Models for Evaluating Motion Skill
A Fast Approximate AIB Algorithm for Distributional Word Clustering
 
12:00-13:30Lunch with free on-site option
 
13:30-14:45Orals (5) - 2 x parallel
Orals 1C - Recognition Orals 1D - Imaging and Segmentation
Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images Discriminative Non-blind Deblurring
Watching Unlabeled Video Helps Learn New Human Actions from Very Few Labeled Snapshots Handling Noise in Single Image Deblurring Using Directional Filters
Fine-Grained Crowdsourcing for Fine-Grained Recognition Jointly Aligning and Segmenting Multiple Web Photo Streams for the Inference of Collective Photo Storylines
Poselet Conditioned Pictorial Structures Video Object Segmentation through Spatially Accurate and Temporally Dense Extraction of Primary Object Regions
Beyond Physical Connections: Tree Models in Human Pose Estimation Improving Image Matting Using Comprehensive Sampling Sets
 
14:45-15:25Spotlights (40 posters) - 2 x parallel
Spotlights 1C - Recognition Spotlights 1D - Imaging
Simultaneous Active Learning of Classifiers - Attributes via Relative Feedback Non-parametric Filtering for Geometric Detail Extraction and Material Representation
Expanded Parts Model for Human Attribute and Action Recognition in Still Images Learning the Change for Automatic Image Cropping
Multipath Sparse Coding Using Hierarchical Matching Pursuit Statistical Textural Distinctiveness for Salient Region Detection in Natural Images
Semi-supervised Domain Adaptation with Instance Constraints Real-Time No-Reference Image Quality Assessment Based on Filter Learning
Learning Structured Low-Rank Representations for Image Classification Learning without Human Scores for Blind Image Quality Assessment
MKPLS: Manifold Kernel Partial Least Squares for Lipreading and Speaker Identification The Variational Structure of Disparity and Regularization of 4D Light Fields
Subspace Interpolation via Dictionary Learning for Unsupervised Domain Adaptation Globally Consistent Multi-label Assignment on the Ray Space of 4D Light Fields
Graph-Based Discriminative Learning for Location Recognition Principal Observation Ray Calibration for Tiled-Lens-Array Integral Imaging Display
Learning by Associating Ambiguously Labeled Images Decoding, Calibration and Rectification for Lenselet-Based Plenoptic Cameras
HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences Adherent Raindrop Detection and Removal in Video
3D R Transform on Spatio-temporal Interest Points for Action Recognition Stochastic Deconvolution
Learning Cross-Domain Information Transfer for Location Recognition and Clustering Multi-image Blind Deblurring Using a Coupled Adaptive Sparse Prior
Studying Relationships between Human Gaze, Description, and Computer Vision Fast Image Super-Resolution Based on In-Place Example Regression
BFO Meets HOG: Feature Extraction Based on Histograms of Oriented p.d.f. Gradients for Image Classification A Machine Learning Approach for Non-blind Image Deconvolution
Class Generative Models Based on Feature Regression for Pose Estimation of Object Categories Learning to Estimate and Remove Non-uniform Image Blur
Leveraging Structure from Motion to Learn Discriminative Codebooks for Scalable Landmark Classification On a Link Between Kernel Mean Maps and Fraunhofer Diffraction, with an Application to Super-Resolution Beyond the Diffraction Limit
Designing Category-Level Attributes for Discriminative Visual Recognition Blur Processing Using Double Discrete Wavelet Transform
Attribute-Based Detection of Unfamiliar Classes with Humans in the Loop Structured Face Hallucination
Object-Centric Anomaly Detection by Attribute-Based Reasoning Unnatural L0 Sparse Representation for Natural Image Deblurring
Learning Class-to-Image Distance with Object Matchings Non-uniform Motion Deblurring for Bilayer Scenes
Sample-Specific Late Fusion for Visual Category Recognition Depth Super Resolution by Rigid Body Self-Similarity in 3D
Efficient Object Detection and Segmentation for Fine-Grained Recognition Saliency Aggregation: A Data-Driven Approach
Label-Embedding for Attribute-Based Classification What Makes a Patch Distinct?
Subcategory-Aware Object Classification Learning Video Saliency from Human Gaze Using Candidate Selection
Vantage Feature Frames for Fine-Grained Categorization Hierarchical Saliency Detection
Probabilistic Label Trees for Efficient Large Scale Image Classification HDR Deghosting: How to Deal with Saturation?
Harvesting Mid-level Visual Concepts from Large-Scale Internet Images FrameBreak: Dramatic Image Extrapolation by Guided Shift-Maps
Adaptive Active Learning for Image Classification Video Enhancement of People Wearing Polarized Glasses: Darkening Reversal and Reflection Reduction
SCaLE: Supervised and Cascaded Laplacian Eigenmaps for Visual Object Recognition Based on Nearest Neighbors Layer Depth Denoising and Completion for Structured-Light RGB-D Cameras
Adding Unlabeled Samples to Categories by Learned Attributes Separating Signal from Noise Using Patch Recurrence across Scales
Visual Place Recognition with Repetitive Structures Texture Enhanced Image Denoising via Gradient Histogram Preservation
Cross-View Image Geolocalization Fast Patch-Based Denoising Using Approximated Patch Geodesic Paths
Efficient 2D-to-3D Correspondence Filtering for Scalable 3D Object Recognition A New Model and Simple Algorithms for Multi-label Mumford-Shah Problems
Learning and Calibrating Per-Location Classifiers for Visual Place Recognition Computing Diffeomorphic Paths for Large Motion Interpolation
An Approach to Pose-Based Action Recognition Rotation, Scaling and Deformation Invariant Scattering for Texture Discrimination
Blocks That Shout: Distinctive Parts for Scene Classification Sensing and Recognizing Surface Textures Using a GelSight Sensor
Part Discovery from Partial Correspondence Enriching Texture Analysis with Semantic Data
Learning Collections of Part Models for Object Recognition
Fast Multiple-Part Based Object Detection Using KD-Ferns
POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation
 
15:25-18:00Posters and refreshments (first 30 minutes)
Posters 1C - Recognition Posters 1D - Imaging
Simultaneous Active Learning of Classifiers - Attributes via Relative Feedback Non-parametric Filtering for Geometric Detail Extraction and Material Representation
Expanded Parts Model for Human Attribute and Action Recognition in Still Images Learning the Change for Automatic Image Cropping
Multipath Sparse Coding Using Hierarchical Matching Pursuit Statistical Textural Distinctiveness for Salient Region Detection in Natural Images
Semi-supervised Domain Adaptation with Instance Constraints Real-Time No-Reference Image Quality Assessment Based on Filter Learning
Learning Structured Low-Rank Representations for Image Classification Learning without Human Scores for Blind Image Quality Assessment
MKPLS: Manifold Kernel Partial Least Squares for Lipreading and Speaker Identification The Variational Structure of Disparity and Regularization of 4D Light Fields
Subspace Interpolation via Dictionary Learning for Unsupervised Domain Adaptation Globally Consistent Multi-label Assignment on the Ray Space of 4D Light Fields
Graph-Based Discriminative Learning for Location Recognition Principal Observation Ray Calibration for Tiled-Lens-Array Integral Imaging Display
Learning by Associating Ambiguously Labeled Images Decoding, Calibration and Rectification for Lenselet-Based Plenoptic Cameras
HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences Adherent Raindrop Detection and Removal in Video
3D R Transform on Spatio-temporal Interest Points for Action Recognition Stochastic Deconvolution
Learning Cross-Domain Information Transfer for Location Recognition and Clustering Multi-image Blind Deblurring Using a Coupled Adaptive Sparse Prior
Studying Relationships between Human Gaze, Description, and Computer Vision Fast Image Super-Resolution Based on In-Place Example Regression
BFO Meets HOG: Feature Extraction Based on Histograms of Oriented p.d.f. Gradients for Image Classification A Machine Learning Approach for Non-blind Image Deconvolution
Class Generative Models Based on Feature Regression for Pose Estimation of Object Categories Learning to Estimate and Remove Non-uniform Image Blur
Leveraging Structure from Motion to Learn Discriminative Codebooks for Scalable Landmark Classification On a Link Between Kernel Mean Maps and Fraunhofer Diffraction, with an Application to Super-Resolution Beyond the Diffraction Limit
Designing Category-Level Attributes for Discriminative Visual Recognition Blur Processing Using Double Discrete Wavelet Transform
Attribute-Based Detection of Unfamiliar Classes with Humans in the Loop Structured Face Hallucination
Object-Centric Anomaly Detection by Attribute-Based Reasoning Unnatural L0 Sparse Representation for Natural Image Deblurring
Learning Class-to-Image Distance with Object Matchings Non-uniform Motion Deblurring for Bilayer Scenes
Sample-Specific Late Fusion for Visual Category Recognition Depth Super Resolution by Rigid Body Self-Similarity in 3D
Efficient Object Detection and Segmentation for Fine-Grained Recognition Saliency Aggregation: A Data-Driven Approach
Label-Embedding for Attribute-Based Classification What Makes a Patch Distinct?
Subcategory-Aware Object Classification Learning Video Saliency from Human Gaze Using Candidate Selection
Vantage Feature Frames for Fine-Grained Categorization Hierarchical Saliency Detection
Probabilistic Label Trees for Efficient Large Scale Image Classification HDR Deghosting: How to Deal with Saturation?
Harvesting Mid-level Visual Concepts from Large-Scale Internet Images FrameBreak: Dramatic Image Extrapolation by Guided Shift-Maps
Adaptive Active Learning for Image Classification Video Enhancement of People Wearing Polarized Glasses: Darkening Reversal and Reflection Reduction
SCaLE: Supervised and Cascaded Laplacian Eigenmaps for Visual Object Recognition Based on Nearest Neighbors Layer Depth Denoising and Completion for Structured-Light RGB-D Cameras
Adding Unlabeled Samples to Categories by Learned Attributes Separating Signal from Noise Using Patch Recurrence across Scales
Visual Place Recognition with Repetitive Structures Texture Enhanced Image Denoising via Gradient Histogram Preservation
Cross-View Image Geolocalization Fast Patch-Based Denoising Using Approximated Patch Geodesic Paths
Efficient 2D-to-3D Correspondence Filtering for Scalable 3D Object Recognition A New Model and Simple Algorithms for Multi-label Mumford-Shah Problems
Learning and Calibrating Per-Location Classifiers for Visual Place Recognition Computing Diffeomorphic Paths for Large Motion Interpolation
An Approach to Pose-Based Action Recognition Rotation, Scaling and Deformation Invariant Scattering for Texture Discrimination
Blocks That Shout: Distinctive Parts for Scene Classification Sensing and Recognizing Surface Textures Using a GelSight Sensor
Part Discovery from Partial Correspondence Enriching Texture Analysis with Semantic Data
Learning Collections of Part Models for Object Recognition
Fast Multiple-Part Based Object Detection Using KD-Ferns
POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation
 
17:30-19:00Light snacks / dinner
 
19:00-21:00PAMI-TC Meeting
 

WEDNESDAY, June 26



08:30-09:45Orals (5) - 2 x parallel
Orals 2A - Motion and Reconstruction Orals 2B - Optimization Methods
Megastereo: Constructing High-Resolution Stereo Panoramas Gauging Association Patterns of Chromosome Territories via Chromatic Median
Dense Object Reconstruction with Semantic Priors Auxiliary Cuts for General Classes of Higher Order Functionals
Dense Variational Reconstruction of Non-rigid Surfaces from Monocular Video A Fast Semidefinite Approach to Solving Binary Quadratic Problems
Procrustean Normal Distribution for Non-rigid Structure from Motion Diffusion Processes for Retrieval Revisited
Dense Reconstruction Using 3D Object Shape Priors A Comparative Study of Modern Inference Techniques for Discrete Energy Minimization Problems
 
09:45-10:15Spotlights (30 posters) - 2 x parallel
Spotlights 2A - Pose and Photometry Spotlights 2B - Methods and Retrieval
A Global Approach for the Detection of Vanishing Points and Mutually Orthogonal Vanishing Directions Inductive Hashing on Manifolds
Cloud Motion as a Calibration Cue Hash Bit Selection: A Unified Solution for Selection Problems in Hashing
SLAM++: Simultaneous Localisation and Mapping at the Level of Objects All about VLAD
Rolling Shutter Camera Calibration Binary Code Ranking with Weighted Hamming Distance
Radial Distortion Self-Calibration Consensus of k-NNs for Robust Neighborhood Selection on Graph-Based Manifolds
A Minimum Error Vanishing Point Detection Approach for Uncalibrated Monocular Images of Man-Made Environments Topical Video Object Discovery from Key Frames by Modeling Word Co-occurrence Prior
Five Shades of Grey for Fast and Reliable Camera Pose Estimation Query Adaptive Similarity for Large Scale Object Retrieval
Can a Fully Unconstrained Imaging Model Be Applied Effectively to Central Cameras? Image Tag Completion via Image-Specific and Tag-Specific Linear Sparse Reconstructions
Single Image Calibration of Multi-axial Imaging Systems Lp-Norm IDF for Large Scale Image Search
The Episolar Constraint: Monocular Shape from Shadow Correspondence Constraints as Features
Shading-Based Shape Refinement of RGB-D Images Learning a Manifold as an Atlas
Illumination Estimation Based on Bilayer Sparse Coding Semi-supervised Learning of Feature Hierarchies for Object Detection in a Video
Learning Discriminative Illumination and Filters for Raw Material Classification with Optimal Projections of Bidirectional Texture Functions Fully-Connected CRFs with Non-Parametric Pairwise Potential
A Theory of Refractive Photo-Light-Path Triangulation Discriminative Sub-categorization
Analytic Bilinear Appearance Subspace Construction for Modeling Image Irradiance under Natural Illumination and Non-Lambertian Reflectance Whitened Expectation Propagation: Non-Lambertian Shape from Shading and Shadow
Spectral Modeling and Relighting of Reflective-Fluorescent Scenes Fast Energy Minimization Using Learned State Filters
Specular Reflection Separation Using Dark Channel Prior Bilinear Programming for Human Activity Recognition with Unknown MRF Graphs
BRDF Slices: Accurate Adaptive Anisotropic Appearance Acquisition A Higher-Order CRF Model for Road Network Extraction
A New Perspective on Uncalibrated Photometric Stereo Nonlinearly Constrained MRFs: Exploring the Intrinsic Dimensions of Higher-Order Cliques
Multi-view Photometric Stereo with Spatially Varying Isotropic Materials Fast Trust Region for Segmentation
Uncalibrated Photometric Stereo for Unknown Isotropic Reflectances Optimal Geometric Fitting under the Truncated L2-Norm
Calibrating Photometric Stereo by Holistic Reflectance Symmetry Analysis In Defense of 3D-Label Stereo
Articulated and Restricted Motion Subspaces and Their Signatures Universality of the Local Marginal Polytope
Template-Based Isometric Deformable 3D Reconstruction with Sampling-Based Focal Length Self-Calibration Continuous Inference in Graphical Models with Polynomial Energies
Monocular Template-Based 3D Reconstruction of Extensible Surfaces with Local Linear Elasticity Towards Efficient and Exact MAP-Inference for Large Scale Discrete Computer Vision Problems via Combinatorial Optimization
Non-rigid Structure from Motion with Diffusion Maps Prior An Iterated L1 Algorithm for Non-smooth Non-convex Optimization in Computer Vision
Joint Detection, Tracking and Mapping by Semantic Bundle Adjustment A Genetic Algorithm-Based Solver for Very Large Jigsaw Puzzles
A Practical Rank-Constrained Eight-Point Algorithm for Fundamental Matrix Estimation A Convex Regularize for Reducing Color Artifact in Color Image Recovery
CLAM: Coupled Localization and Mapping with Efficient Outlier Handling Kernel Learning for Extrinsic Classification of Manifold Features
 
10:15-12:00Posters and refreshments (first 30 minutes)
Posters 2A - Pose and Photometry Posters 2B - Methods and Retrieval
A Global Approach for the Detection of Vanishing Points and Mutually Orthogonal Vanishing Directions Inductive Hashing on Manifolds
Cloud Motion as a Calibration Cue Hash Bit Selection: A Unified Solution for Selection Problems in Hashing
SLAM++: Simultaneous Localisation and Mapping at the Level of Objects All about VLAD
Rolling Shutter Camera Calibration Binary Code Ranking with Weighted Hamming Distance
Radial Distortion Self-Calibration Consensus of k-NNs for Robust Neighborhood Selection on Graph-Based Manifolds
A Minimum Error Vanishing Point Detection Approach for Uncalibrated Monocular Images of Man-Made Environments Topical Video Object Discovery from Key Frames by Modeling Word Co-occurrence Prior
Five Shades of Grey for Fast and Reliable Camera Pose Estimation Query Adaptive Similarity for Large Scale Object Retrieval
Can a Fully Unconstrained Imaging Model Be Applied Effectively to Central Cameras? Image Tag Completion via Image-Specific and Tag-Specific Linear Sparse Reconstructions
Single Image Calibration of Multi-axial Imaging Systems Lp-Norm IDF for Large Scale Image Search
The Episolar Constraint: Monocular Shape from Shadow Correspondence Constraints as Features
Shading-Based Shape Refinement of RGB-D Images Learning a Manifold as an Atlas
Illumination Estimation Based on Bilayer Sparse Coding Semi-supervised Learning of Feature Hierarchies for Object Detection in a Video
Learning Discriminative Illumination and Filters for Raw Material Classification with Optimal Projections of Bidirectional Texture Functions Fully-Connected CRFs with Non-Parametric Pairwise Potential
A Theory of Refractive Photo-Light-Path Triangulation Discriminative Sub-categorization
Analytic Bilinear Appearance Subspace Construction for Modeling Image Irradiance under Natural Illumination and Non-Lambertian Reflectance Whitened Expectation Propagation: Non-Lambertian Shape from Shading and Shadow
Spectral Modeling and Relighting of Reflective-Fluorescent Scenes Fast Energy Minimization Using Learned State Filters
Specular Reflection Separation Using Dark Channel Prior Bilinear Programming for Human Activity Recognition with Unknown MRF Graphs
BRDF Slices: Accurate Adaptive Anisotropic Appearance Acquisition A Higher-Order CRF Model for Road Network Extraction
A New Perspective on Uncalibrated Photometric Stereo Nonlinearly Constrained MRFs: Exploring the Intrinsic Dimensions of Higher-Order Cliques
Multi-view Photometric Stereo with Spatially Varying Isotropic Materials Fast Trust Region for Segmentation
Uncalibrated Photometric Stereo for Unknown Isotropic Reflectances Optimal Geometric Fitting under the Truncated L2-Norm
Calibrating Photometric Stereo by Holistic Reflectance Symmetry Analysis In Defense of 3D-Label Stereo
Articulated and Restricted Motion Subspaces and Their Signatures Universality of the Local Marginal Polytope
Template-Based Isometric Deformable 3D Reconstruction with Sampling-Based Focal Length Self-Calibration Continuous Inference in Graphical Models with Polynomial Energies
Monocular Template-Based 3D Reconstruction of Extensible Surfaces with Local Linear Elasticity Towards Efficient and Exact MAP-Inference for Large Scale Discrete Computer Vision Problems via Combinatorial Optimization
Non-rigid Structure from Motion with Diffusion Maps Prior An Iterated L1 Algorithm for Non-smooth Non-convex Optimization in Computer Vision
Joint Detection, Tracking and Mapping by Semantic Bundle Adjustment A Genetic Algorithm-Based Solver for Very Large Jigsaw Puzzles
A Practical Rank-Constrained Eight-Point Algorithm for Fundamental Matrix Estimation A Convex Regularize for Reducing Color Artifact in Color Image Recovery
CLAM: Coupled Localization and Mapping with Efficient Outlier Handling Kernel Learning for Extrinsic Classification of Manifold Features
 
12:00-13:30Lunch with free on-site option
 
13:30-14:45Orals (5) - 2 x parallel
Orals 2C - Detection (+Medical/Curves) Orals 2D - Tracking and Flow
Learning Structured Hough Voting for Joint Object Detection and Occlusion Reasoning Tracking Sports Players with Context-Conditioned Motion Models
Detection Evolution with Multi-order Contextual Co-occurrence Structure Preserving Object Tracking
Efficient Large-Scale Structured Learning Multi-target Tracking by Lagrangian Relaxation to Min-cost Network Flow
Fast, Accurate Detection of 100,000 Object Classes on a Single Machine Patch Match Filter: Efficient Edge-Aware Filtering Meets Randomized Search for Fast Correspondence Field Estimation
Reconstructing Loopy Curvilinear Structures Using Integer Programming Robust Monocular Epipolar Flow Estimation
 
14:45-15:25Spotlights (40 posters) - 2 x parallel
Spotlights 2C - Segmentation and Shape Spotlights 2D - Motion and Medical Imaging
Deep Learning Shape Priors for Object Segmentation Blind Deconvolution of Widefield Fluorescence Microscopic Data by Regularization of the Optical Transfer Function (OTF)
PDM-ENLOR: Learning Ensemble of Local PDM-Based Regressions Image Understanding from Experts’ Eyes by Modeling Perceptual Skill of Diagnostic Reasoning Processes
Incorporating User Interaction and Topological Constraints within Contour Completion via Discrete Calculus Adaptive Compressed Tomography Sensing
Recovering Line-Networks in Images by Junction-Point Processes Classification of Tumor Histology via Morphometric Context
Image Matting with Local and Nonlocal Smooth Priors Efficient 3D Endfiring TRUS Prostate Segmentation with Globally Optimized Rotational Symmetry
Probabilistic Graphlet Cut: Exploiting Spatial Structure Cue for Weakly Supervised Image Segmentation Graph-Based Optimization with Tubularity Markov Tree for 3D Vessel Segmentation
Towards Fast and Accurate Segmentation Prostate Segmentation in CT Images via Spatial-Constrained Transductive Lasso
Discriminative Re-ranking of Diverse Segmentations Area Preserving Brain Mapping
Robust Region Grouping via Internal Patch Statistics Discriminative Brain Effective Connectivity Analysis for Alzheimer’s Disease: A Kernel Learning Approach upon Sparse Gaussian Bayesian Network
Unsupervised Joint Object Discovery and Segmentation in Internet Images Compressible Motion Fields
Ensemble Video Object Cut in Highly Dynamic Scenes Fast Rigid Motion Segmentation via Incrementally-Complex Local Models
Graph Transduction Learning with Connectivity Constraints with Application to Multiple Foreground Cosegmentation Determining Motion Directly from Normal Flows Upon the Use of a Spherical Eye Platform
Top-Down Segmentation of Non-rigid Visual Objects Using Derivative-Based Search on Sparse Manifolds Correspondence-Less Non-rigid Registration of Triangular Surface Meshes
A Principled Deep Random Field Model for Image Segmentation Video Editing with Temporal, Spatial and Appearance Consistency
Background Modeling Based on Bidirectional Analysis Correlation Filters for Object Alignment
Learning for Structured Prediction Using Approximate Subgradient Descent with Working Sets Plane-Based Content Preserving Warps for Video Stabilization
A Sentence Is Worth a Thousand Pixels Deformable Spatial Pyramid Matching for Fast Dense Correspondences
GRASP Recurring Patterns from a Single View The Generalized Laplacian Distance and Its Applications for Visual Matching
Image Segmentation by Cascaded Region Agglomeration Groupwise Registration via Graph Shrinkage on the Image Manifold
Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling FasT-Match: Fast Affine Template Matching
Voxel Cloud Connectivity Segmentation - Supervoxels for Point Clouds As-Projective-As-Possible Image Stitching with Moving DLT
SCALPEL: Segmentation Cascades with Localized Priors and Efficient Learning Real-Time Model-Based Rigid Object Pose Estimation and Tracking Combining Dense and Sparse Visual Cues
Submodular Salient Region Detection Minimum Uncertainty Gap for Robust Visual Tracking
A Video Representation Using Temporal Superpixels Part-Based Visual Tracking with Online Latent Structural Learning
Pose from Flow and Flow from Pose Least Soft-Threshold Squares Tracking
Mesh Based Semantic Modelling for Indoor and Outdoor Scenes Self-Paced Learning for Long-Term Tracking
Weakly-Supervised Dual Clustering for Image Semantic Segmentation Multi-target Tracking by Rank-1 Tensor Approximation
Salient Object Detection: A Discriminative Regional Feature Integration Approach Robust Real-Time Tracking of Multiple Objects by Volumetric Mass Densities
Revisiting Depth Layers from Occlusions Information Consensus for Distributed Multi-target Tracking
Hierarchical Video Representation with Trajectory Binary Partition Tree Online Object Tracking: A Benchmark
Discriminative Subspace Clustering Learning Compact Binary Codes for Visual Tracking
PISA: Pixelwise Image Saliency by Aggregating Complementary Appearance Contrast Measures with Spatial Priors Visual Tracking via Locality Sensitive Histograms
Boundary Detection Benchmarking: Beyond F-Measures Optical Flow Estimation Using Laplacian Mesh Energy
Measures and Meta-Measures for the Supervised Evaluation of Image Segmentation Large Displacement Optical Flow from Nearest Neighbor Fields
Multi-resolution Shape Analysis via Non-Euclidean Wavelets: Applications to Mesh Segmentation and Surface Alignment Problems A Fully-Connected Layered Model of Foreground and Background Flow
Robust Estimation of Nonrigid Transformation for Point Set Registration
Efficient Computation of Shortest Path-Concavity for 3D Meshes
Boundary Cues for 3D Object Shape Recovery
A Linear Approach to Matching Cuboids in RGBD Images
 
15:25-15:40Awards
 
15:40-18:00Posters and refreshments (first 30 minutes)
Posters 2C - Segmentation and Shape Posters 2D - Motion and Medical Imaging
Deep Learning Shape Priors for Object Segmentation Blind Deconvolution of Widefield Fluorescence Microscopic Data by Regularization of the Optical Transfer Function (OTF)
PDM-ENLOR: Learning Ensemble of Local PDM-Based Regressions Image Understanding from Experts’ Eyes by Modeling Perceptual Skill of Diagnostic Reasoning Processes
Incorporating User Interaction and Topological Constraints within Contour Completion via Discrete Calculus Adaptive Compressed Tomography Sensing
Recovering Line-Networks in Images by Junction-Point Processes Classification of Tumor Histology via Morphometric Context
Image Matting with Local and Nonlocal Smooth Priors Efficient 3D Endfiring TRUS Prostate Segmentation with Globally Optimized Rotational Symmetry
Probabilistic Graphlet Cut: Exploiting Spatial Structure Cue for Weakly Supervised Image Segmentation Graph-Based Optimization with Tubularity Markov Tree for 3D Vessel Segmentation
Towards Fast and Accurate Segmentation Prostate Segmentation in CT Images via Spatial-Constrained Transductive Lasso
Discriminative Re-ranking of Diverse Segmentations Area Preserving Brain Mapping
Robust Region Grouping via Internal Patch Statistics Discriminative Brain Effective Connectivity Analysis for Alzheimer’s Disease: A Kernel Learning Approach upon Sparse Gaussian Bayesian Network
Unsupervised Joint Object Discovery and Segmentation in Internet Images Compressible Motion Fields
Ensemble Video Object Cut in Highly Dynamic Scenes Fast Rigid Motion Segmentation via Incrementally-Complex Local Models
Graph Transduction Learning with Connectivity Constraints with Application to Multiple Foreground Cosegmentation Determining Motion Directly from Normal Flows Upon the Use of a Spherical Eye Platform
Top-Down Segmentation of Non-rigid Visual Objects Using Derivative-Based Search on Sparse Manifolds Correspondence-Less Non-rigid Registration of Triangular Surface Meshes
A Principled Deep Random Field Model for Image Segmentation Video Editing with Temporal, Spatial and Appearance Consistency
Background Modeling Based on Bidirectional Analysis Correlation Filters for Object Alignment
Learning for Structured Prediction Using Approximate Subgradient Descent with Working Sets Plane-Based Content Preserving Warps for Video Stabilization
A Sentence Is Worth a Thousand Pixels Deformable Spatial Pyramid Matching for Fast Dense Correspondences
GRASP Recurring Patterns from a Single View The Generalized Laplacian Distance and Its Applications for Visual Matching
Image Segmentation by Cascaded Region Agglomeration Groupwise Registration via Graph Shrinkage on the Image Manifold
Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling FasT-Match: Fast Affine Template Matching
Voxel Cloud Connectivity Segmentation - Supervoxels for Point Clouds As-Projective-As-Possible Image Stitching with Moving DLT
SCALPEL: Segmentation Cascades with Localized Priors and Efficient Learning Real-Time Model-Based Rigid Object Pose Estimation and Tracking Combining Dense and Sparse Visual Cues
Submodular Salient Region Detection Minimum Uncertainty Gap for Robust Visual Tracking
A Video Representation Using Temporal Superpixels Part-Based Visual Tracking with Online Latent Structural Learning
Pose from Flow and Flow from Pose Least Soft-Threshold Squares Tracking
Mesh Based Semantic Modelling for Indoor and Outdoor Scenes Self-Paced Learning for Long-Term Tracking
Weakly-Supervised Dual Clustering for Image Semantic Segmentation Multi-target Tracking by Rank-1 Tensor Approximation
Salient Object Detection: A Discriminative Regional Feature Integration Approach Robust Real-Time Tracking of Multiple Objects by Volumetric Mass Densities
Revisiting Depth Layers from Occlusions Information Consensus for Distributed Multi-target Tracking
Hierarchical Video Representation with Trajectory Binary Partition Tree Online Object Tracking: A Benchmark
Discriminative Subspace Clustering Learning Compact Binary Codes for Visual Tracking
PISA: Pixelwise Image Saliency by Aggregating Complementary Appearance Contrast Measures with Spatial Priors Visual Tracking via Locality Sensitive Histograms
Boundary Detection Benchmarking: Beyond F-Measures Optical Flow Estimation Using Laplacian Mesh Energy
Measures and Meta-Measures for the Supervised Evaluation of Image Segmentation Large Displacement Optical Flow from Nearest Neighbor Fields
Multi-resolution Shape Analysis via Non-Euclidean Wavelets: Applications to Mesh Segmentation and Surface Alignment Problems A Fully-Connected Layered Model of Foreground and Background Flow
Robust Estimation of Nonrigid Transformation for Point Set Registration
Efficient Computation of Shortest Path-Concavity for 3D Meshes
Boundary Cues for 3D Object Shape Recovery
A Linear Approach to Matching Cuboids in RGBD Images
 
17:30-19:00Light snacks / dinner
 

THURSDAY, June 27



08:30-09:45Orals (5) - 2 x parallel
Orals 3A - Video Orals 3B - Geometry and Physics (+Medical)
Event Retrieval in Large Video Collections with Circulant Temporal Encoding Underwater Camera Calibration Using Wavelength Triangulation
Cumulative Attribute Space for Age and Crowd Density Estimation Reconstructing Gas Flows Using Light-Path Approximation
Social Role Discovery in Human Events Photometric Ambient Occlusion
Discriminative Segment Annotation in Weakly Labeled Video What Object Motion Reveals about Shape with Unknown BRDF and Lighting
Context-Aware Modeling and Recognition of Activities in Video Hyperbolic Harmonic Mapping for Constrained Brain Surface Registration
 
09:45-10:15Spotlights (30 posters) - 2 x parallel
Spotlights 3A - Video Analysis Spotlights 3B - Features and Contours
Crossing the Line: Crowd Counting by Integer Programming with Local Features Learning Separable Filters
Multi-source Multi-scale Counting in Extremely Dense Crowd Images Robust Feature Matching with Alternate Hough and Inverted Hough Transforms
Better Exploiting Motion for Better Action Recognition SWIGS: A Swift Guided Sampling Method
Detection of Manipulation Action Consequences (MAC) Learning Multiple Non-linear Sub-spaces Using K-RBMs
Representing Videos Using Mid-level Discriminative Patches Light Field Distortion Feature for Transparent Object Recognition
Modeling Actions through State Changes From Local Similarity to Global Coding: An Application to Image Classification
Recognizing Activities via Bag of Words for Attribute Dynamics Joint Spectral Correspondence for Disparate Image Matching
Sampling Strategies for Real-Time Action Recognition Efficient Color Boundary Detection with Color-Opponent Mechanisms
Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis Winding Number for Region-Boundary Consistent Salient Contour Extraction
Online Dominant and Anomalous Behavior Detection in Videos Supervised Semantic Gradient Extraction Using Linear-Time Optimization
Augmenting Bag-of-Words: Data-Driven Discovery of Temporal and Structural Information for Activity Recognition Spatio-temporal Depth Cuboid Similarity Feature for Activity Recognition Using Depth Camera
Complex Event Detection via Multi-source Video Attributes Sparse Quantization for Patch Description
A Thousand Frames in Just a Few Words: Lingual Description of Videos through Latent Topics and Sparse Object Stitching Evaluation of Color STIPs for Human Action Recognition
Spatiotemporal Deformable Part Models for Action Detection Supervised Kernel Descriptors for Visual Recognition
Poselet Key-Framing: A Model for Human Activity Recognition Discriminative Color Descriptors
Recognize Human Activities from Partially Observed Videos Boosting Binary Keypoint Descriptors
Event Recognition in Videos by Learning from Heterogeneous Web Sources Exploring Weak Stabilization for Motion Feature Extraction
Motionlets: Mid-level 3D Parts for Human Motion Recognition Dense Segmentation-Aware Descriptors
Multi-agent Event Detection: Localization and Role Assignment Keypoints from Symmetries by Wave Propagation
Cross-View Action Recognition via a Continuous Virtual Path Graph Matching with Anchor Nodes: A Learning Approach
Large-Scale Video Summarization Using Web-Image Priors Dense Non-rigid Point-Matching Using Random Projections
Representing and Discovering Adversarial Team Behaviors Using Player Roles Deformable Graph Matching
Story-Driven Summarization for Egocentric Video Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images
Finding Group Interactions in Social Clutter K-Means Hashing: An Affinity-Preserving Quantization Method for Learning Binary Compact Codes
First-Person Activity Recognition: What Are They Doing to Me? Optimized Product Quantization for Approximate Nearest Neighbor Search
Joint Sparsity-Based Representation and Analysis of Unconstrained Activities A Non-parametric Framework for Document Bleed-through Removal
Motion Estimation for Self-Driving Cars with a Generalized Camera Scene Text Recognition Using Part-Based Tree-Structured Character Detection
Active Contours with Group Similarity
Accurate and Robust Registration of Nonrigid Surface Using Hierarchical Statistical Shape Model
 
10:15-12:00Posters and refreshments (first 30 minutes)
Posters 3A - Video Analysis Posters 3B - Features and Contours
Crossing the Line: Crowd Counting by Integer Programming with Local Features Learning Separable Filters
Multi-source Multi-scale Counting in Extremely Dense Crowd Images Robust Feature Matching with Alternate Hough and Inverted Hough Transforms
Better Exploiting Motion for Better Action Recognition SWIGS: A Swift Guided Sampling Method
Detection of Manipulation Action Consequences (MAC) Learning Multiple Non-linear Sub-spaces Using K-RBMs
Representing Videos Using Mid-level Discriminative Patches Light Field Distortion Feature for Transparent Object Recognition
Modeling Actions through State Changes From Local Similarity to Global Coding: An Application to Image Classification
Recognizing Activities via Bag of Words for Attribute Dynamics Joint Spectral Correspondence for Disparate Image Matching
Sampling Strategies for Real-Time Action Recognition Efficient Color Boundary Detection with Color-Opponent Mechanisms
Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis Winding Number for Region-Boundary Consistent Salient Contour Extraction
Online Dominant and Anomalous Behavior Detection in Videos Supervised Semantic Gradient Extraction Using Linear-Time Optimization
Augmenting Bag-of-Words: Data-Driven Discovery of Temporal and Structural Information for Activity Recognition Spatio-temporal Depth Cuboid Similarity Feature for Activity Recognition Using Depth Camera
Complex Event Detection via Multi-source Video Attributes Sparse Quantization for Patch Description
A Thousand Frames in Just a Few Words: Lingual Description of Videos through Latent Topics and Sparse Object Stitching Evaluation of Color STIPs for Human Action Recognition
Spatiotemporal Deformable Part Models for Action Detection Supervised Kernel Descriptors for Visual Recognition
Poselet Key-Framing: A Model for Human Activity Recognition Discriminative Color Descriptors
Recognize Human Activities from Partially Observed Videos Boosting Binary Keypoint Descriptors
Event Recognition in Videos by Learning from Heterogeneous Web Sources Exploring Weak Stabilization for Motion Feature Extraction
Motionlets: Mid-level 3D Parts for Human Motion Recognition Dense Segmentation-Aware Descriptors
Multi-agent Event Detection: Localization and Role Assignment Keypoints from Symmetries by Wave Propagation
Cross-View Action Recognition via a Continuous Virtual Path Graph Matching with Anchor Nodes: A Learning Approach
Large-Scale Video Summarization Using Web-Image Priors Dense Non-rigid Point-Matching Using Random Projections
Representing and Discovering Adversarial Team Behaviors Using Player Roles Deformable Graph Matching
Story-Driven Summarization for Egocentric Video Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images
Finding Group Interactions in Social Clutter K-Means Hashing: An Affinity-Preserving Quantization Method for Learning Binary Compact Codes
First-Person Activity Recognition: What Are They Doing to Me? Optimized Product Quantization for Approximate Nearest Neighbor Search
Joint Sparsity-Based Representation and Analysis of Unconstrained Activities A Non-parametric Framework for Document Bleed-through Removal
Motion Estimation for Self-Driving Cars with a Generalized Camera Scene Text Recognition Using Part-Based Tree-Structured Character Detection
Active Contours with Group Similarity
Accurate and Robust Registration of Nonrigid Surface Using Hierarchical Statistical Shape Model
 
12:00-13:30Lunch with free on-site option
 
13:30-14:45Orals (5) - 2 x parallel
Orals 3C - Context and Scenes (+ANN) Orals 3D - Faces, People, and Crowds
Spatial Inference Machines Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification
Hallucinated Humans as the Hidden Context for Labeling 3D Scenes Robust Multi-resolution Pedestrian Detection in Traffic Scenes
Finding Things: Image Parsing with Regions and Per-Exemplar Detectors Human Pose Estimation Using Body Parts Dependent Joint Regressors
Bringing Semantics into Focus Using Visual Abstraction Measuring Crowd Collectiveness
Cartesian K-Means Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization
 
14:45-15:25Spotlights (40 posters) - 2 x parallel
Spotlights 3C - Objects and Scenes Spotlights 3D - People and Faces
Manhattan Junction Catalogue for Spatial Reasoning of Indoor Scenes Expressive Visual Text-to-Speech Using Active Appearance Models
Tensor-Based High-Order Semantic Relation Transfer for Semantic Scene Segmentation Computationally Efficient Regression on a Dependency Graph for Human Pose Estimation
Geometric Context from Videos Hollywood 3D: Recognizing Actions in 3D Natural Scenes
It’s Not Polite to Point: Describing People with Uncertain Attributes 3D Visual Proxemics: Recognizing Human Interactions in 3D from a Single Image
Heterogeneous Visual Features Fusion via Sparse Multimodal Machine Decoding Children’s Social Behavior
A Max-Margin Riffled Independence Model for Image Tag Ranking Capturing Complex Spatio-temporal Relations among Facial Muscles for Facial Expression Recognition
Weakly Supervised Learning for Attribute Localization in Outdoor Scenes Detecting Pulse from Head Motions in Video
Scene Parsing by Integrating Function, Geometry and Appearance Models Towards Contactless, Low-Cost and Accurate 3D Fingerprint Identification
Beyond Point Clouds: Scene Understanding by Reasoning Geometry and Physics Robust Discriminative Response Map Fitting with Constrained Local Models
Label Propagation from ImageNet to 3D Point Clouds Facial Feature Tracking Under Varying Facial Expressions and Face Poses Based on Restricted Boltzmann Machines
Analyzing Semantic Segmentation Using Hybrid Human-Machine CRFs Detecting and Aligning Faces by Image Retrieval
Nonparametric Scene Parsing with Adaptive Feature Relevance and Semantic Context Learning SURF Cascade for Fast and Accurate Object Detection
Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection Deep Convolutional Network Cascade for Facial Point Detection
Saliency Detection via Graph-Based Manifold Ranking Exemplar-Based Face Parsing
Maximum Cohesive Grid of Superpixels for Fast Object Localization Graph-Laplacian PCA: Closed-Form Solution and Robustness
Accurate Localization of 3D Objects from RGB-D Data Using Segmentation Hypotheses Probabilistic Elastic Matching for Pose Variant Face Verification
Efficient Maximum Appearance Search for Large-Scale Object Detection Constrained Clustering and Its Application to Face Clustering in Videos
Single-Pedestrian Detection Aided by Multi-pedestrian Detection Selective Transfer Machine for Personalized Facial Action Unit Detection
Robust Object Co-detection The SVM-Minus Similarity Score for Video Face Recognition
Integrating Grammar and Segmentation for Human Pose Estimation Face Recognition in Movie Trailers via Mean Sequence Sparse Representation-Based Classification
Modeling Mutual Visibility Relationship in Pedestrian Detection Towards Pose Robust Face Recognition
Learning to Detect Partially Overlapping Instances Single-Sample Face Recognition with Image Corruption and Misalignment via Sparse Illumination Transfer
Looking Beyond the Image: Unsupervised Learning for Object Saliency and Detection Fusing Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild
Histograms of Sparse Codes for Object Detection Action Recognition by Hierarchical Sequence Summarization
Efficient Detector Adaptation for Object Detection in a Video Pixel-Level Hand Detection in Ego-centric Videos
A Lazy Man’s Approach to Benchmarking: Semisupervised Classifier Evaluation and Recalibration Human Pose Estimation Using a Joint Pixel-wise and Part-wise Formulation
Fast Object Detection with Entropy-Driven Evaluation Unsupervised Salience Learning for Person Re-identification
Discriminatively Trained And-Or Tree Models for Object Detection Locally Aligned Feature Transforms across Views
Occlusion Patterns for Object Class Detection Semi-supervised Learning with Constraints for Person Identification in Multimedia Data
Bottom-Up Segmentation for Top-Down Detection Learning Locally-Adaptive Decision Functions for Person Verification
Composite Statistical Inference for Semantic Segmentation 3D Pictorial Structures for Multiple View Articulated Pose Estimation
Multi-attribute Queries: To Merge or Not to Merge? Pedestrian Detection with Unsupervised Multi-stage Feature Learning
Local Fisher Discriminant Analysis for Pedestrian Re-identification A Joint Model for 2D and 3D Pose Estimation from a Single Image
Explicit Occlusion Modeling for 3D Object Class Representations Unconstrained Monocular 3D Human Pose Estimation by Action Detection and Cross-Modality Regression Forest
Incorporating Structural Alternatives and Sharing into Hierarchy for Multiclass Object Recognition and Detection Hypergraphs for Joint Multi-view Reconstruction and Multi-object Tracking
Articulated Pose Estimation Using Discriminative Armlet Classifiers Tracking People and Their Objects
Sparse Output Coding for Large-Scale Visual Recognition Seeking the Strongest Rigid Detector
From N to N+1: Multiclass Transfer Incremental Learning MODEC: Multimodal Decomposable Models for Human Pose Estimation
What’s in a Name? First Names as Facial Attributes Detection- and Trajectory-Level Exclusion in Multiple Object Tracking
Kernel Null Space Methods for Novelty Detection Optimized Pedestrian Detection for Multiple and Occluded People
Long-Term Occupancy Analysis Using Graph-Based Optimisation in Thermal Imagery
Detecting and Naming Actors in Movies Using Generative Appearance Models
Harry Potter’s Marauder’s Map: Localizing and Tracking Multiple Persons-of-Interest by Nonnegative Discretization
Improving an Object Detector and Extracting Regions Using Superpixels
Tracking Human Pose by Tracking Symmetric Parts
 
15:25-18:00Posters and refreshments (first 30 minutes)
Posters 3C - Objects and Scenes Posters 3D - People and Faces
Manhattan Junction Catalogue for Spatial Reasoning of Indoor Scenes Expressive Visual Text-to-Speech Using Active Appearance Models
Tensor-Based High-Order Semantic Relation Transfer for Semantic Scene Segmentation Computationally Efficient Regression on a Dependency Graph for Human Pose Estimation
Geometric Context from Videos Hollywood 3D: Recognizing Actions in 3D Natural Scenes
It’s Not Polite to Point: Describing People with Uncertain Attributes 3D Visual Proxemics: Recognizing Human Interactions in 3D from a Single Image
Heterogeneous Visual Features Fusion via Sparse Multimodal Machine Decoding Children’s Social Behavior
A Max-Margin Riffled Independence Model for Image Tag Ranking Capturing Complex Spatio-temporal Relations among Facial Muscles for Facial Expression Recognition
Weakly Supervised Learning for Attribute Localization in Outdoor Scenes Detecting Pulse from Head Motions in Video
Scene Parsing by Integrating Function, Geometry and Appearance Models Towards Contactless, Low-Cost and Accurate 3D Fingerprint Identification
Beyond Point Clouds: Scene Understanding by Reasoning Geometry and Physics Robust Discriminative Response Map Fitting with Constrained Local Models
Label Propagation from ImageNet to 3D Point Clouds Facial Feature Tracking Under Varying Facial Expressions and Face Poses Based on Restricted Boltzmann Machines
Analyzing Semantic Segmentation Using Hybrid Human-Machine CRFs Detecting and Aligning Faces by Image Retrieval
Nonparametric Scene Parsing with Adaptive Feature Relevance and Semantic Context Learning SURF Cascade for Fast and Accurate Object Detection
Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection Deep Convolutional Network Cascade for Facial Point Detection
Saliency Detection via Graph-Based Manifold Ranking Exemplar-Based Face Parsing
Maximum Cohesive Grid of Superpixels for Fast Object Localization Graph-Laplacian PCA: Closed-Form Solution and Robustness
Accurate Localization of 3D Objects from RGB-D Data Using Segmentation Hypotheses Probabilistic Elastic Matching for Pose Variant Face Verification
Efficient Maximum Appearance Search for Large-Scale Object Detection Constrained Clustering and Its Application to Face Clustering in Videos
Single-Pedestrian Detection Aided by Multi-pedestrian Detection Selective Transfer Machine for Personalized Facial Action Unit Detection
Robust Object Co-detection The SVM-Minus Similarity Score for Video Face Recognition
Integrating Grammar and Segmentation for Human Pose Estimation Face Recognition in Movie Trailers via Mean Sequence Sparse Representation-Based Classification
Modeling Mutual Visibility Relationship in Pedestrian Detection Towards Pose Robust Face Recognition
Learning to Detect Partially Overlapping Instances Single-Sample Face Recognition with Image Corruption and Misalignment via Sparse Illumination Transfer
Looking Beyond the Image: Unsupervised Learning for Object Saliency and Detection Fusing Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild
Histograms of Sparse Codes for Object Detection Action Recognition by Hierarchical Sequence Summarization
Efficient Detector Adaptation for Object Detection in a Video Pixel-Level Hand Detection in Ego-centric Videos
A Lazy Man’s Approach to Benchmarking: Semisupervised Classifier Evaluation and Recalibration Human Pose Estimation Using a Joint Pixel-wise and Part-wise Formulation
Fast Object Detection with Entropy-Driven Evaluation Unsupervised Salience Learning for Person Re-identification
Discriminatively Trained And-Or Tree Models for Object Detection Locally Aligned Feature Transforms across Views
Occlusion Patterns for Object Class Detection Semi-supervised Learning with Constraints for Person Identification in Multimedia Data
Bottom-Up Segmentation for Top-Down Detection Learning Locally-Adaptive Decision Functions for Person Verification
Composite Statistical Inference for Semantic Segmentation 3D Pictorial Structures for Multiple View Articulated Pose Estimation
Multi-attribute Queries: To Merge or Not to Merge? Pedestrian Detection with Unsupervised Multi-stage Feature Learning
Local Fisher Discriminant Analysis for Pedestrian Re-identification A Joint Model for 2D and 3D Pose Estimation from a Single Image
Explicit Occlusion Modeling for 3D Object Class Representations Unconstrained Monocular 3D Human Pose Estimation by Action Detection and Cross-Modality Regression Forest
Incorporating Structural Alternatives and Sharing into Hierarchy for Multiclass Object Recognition and Detection Hypergraphs for Joint Multi-view Reconstruction and Multi-object Tracking
Articulated Pose Estimation Using Discriminative Armlet Classifiers Tracking People and Their Objects
Sparse Output Coding for Large-Scale Visual Recognition Seeking the Strongest Rigid Detector
From N to N+1: Multiclass Transfer Incremental Learning MODEC: Multimodal Decomposable Models for Human Pose Estimation
What’s in a Name? First Names as Facial Attributes Detection- and Trajectory-Level Exclusion in Multiple Object Tracking
Kernel Null Space Methods for Novelty Detection Optimized Pedestrian Detection for Multiple and Occluded People
Long-Term Occupancy Analysis Using Graph-Based Optimisation in Thermal Imagery
Detecting and Naming Actors in Movies Using Generative Appearance Models
Harry Potter’s Marauder’s Map: Localizing and Tracking Multiple Persons-of-Interest by Nonnegative Discretization
Improving an Object Detector and Extracting Regions Using Superpixels
Tracking Human Pose by Tracking Symmetric Parts
 

Towers