Official Program for CVPR14

TUESDAY, June 24

08:30-10:00Parallel Oral Sessions (6 papers each)
Orals 1A - Matching and Reconstruction Orals 1B - Segmentation and Grouping
Fast and Accurate Image Matching with Cascade Hashing for 3D Reconstruction
Spectral Graph Reduction for Efficient Image and Streaming Video Segmentation
Predicting Matchability
Nearest Neighbor-based Label Transfer for Weakly Supervised Multiclass Video Segmentation
Trinocular Geometry Revisited
Video Motion Segmentation Using New Adaptive Manifold Denoising Model
Critical Configurations For Radial Distortion Self-Calibration
Cut, Glue & Cut: A Fast, Approximate Solver for Multicut Partitioning
Minimal Solvers for Relative Pose with a Single Unknown Radial Distortion
Neural Decision Forests for Semantic Image Labelling
Reconstructing PASCAL VOC
Pulling Things out of Perspective
10:00-12:00Poster Session (56 posters)
Posters P1 - Poster Session (Recognition, Segmentation, Stereo and SFM)
Event Detection using Multi-Level Relevance Labels and Multiple Features
Robust and Efficient Full-Angle Quaternions for Matching Arrays of 3D Rotations
Compuer vision vs. human vision: What can be learned?
Semi-supervised Spectral Clustering for Image Set Classification
Look at the Driver, Look at the Road: No Distraction! No Accident!
Measuring Distance Between Unordered Sets of Different Sizes
Learning Mid-level Filters for Person Re-identification
Filter Pairing Neural Network for Person Re-identification
Lacunarity Analysis on Image Patterns for Texture Classification
Superpixel-grounded Deformable Part Models
From Categories to Individuals in Real Time --- A Unified Boosting Approach
NMF-KNN: Image Annotation using Weighted Multi-view Non-Negative Matrix Factorization
Fine-Grained Visual Comparisons with Local Learning
Inferring Analogous Attributes
Beyond Comparing Image Pairs: Setwise Active Learning for Relative Attributes
Visual Persuasion: Inferring Communicative Intents of Images
Histograms of Pattern Sets for Image Classification and Object Recognition
Incorporating Scene Context and Object Layout into Appearance Modeling
Co-Segmentation of Textured 3D Shapes with Sparse Annotations
How to Evaluate Foreground Maps?
MILCut: A Sweeping Line Multiple Instance Learning Paradigm for Interactive Image Segmentation
SCAMS: Simultaneous Clustering and Model Selection
The Shape-Time Random Field for Semantic Video Labeling
The Secrets of Salient Object Segmentation
Non-rigid Segmentation using Sparse Low Dimensional Manifolds and Deep Belief Networks
An Exemplar-based CRF for Multi-instance Object Segmentation
Object Partitioning using Local Convexity
Bayesian Active Contours with Affine-Invariant, Elastic Shape Prior
Max-Margin Boltzmann Machines for Object Segmentation
Multiscale Combinatorial Grouping
RIGOR: Reusing Inference in Graph Cuts for generating Object Regions
Efficient Hierarchical Graph-Based Segmentation of RBGD Videos
Point Matching in the Presence of Outliers in Both Point Sets: A Concave Optimization Approach
Multiple Structured-Instance Learning for Semantic Segmentation with Uncertain Training Data
Joint Motion Segmentation and Background Subtraction in Dynamic Scenes
SeamSeg: Video Object Segmentation using Patch Seams
Laplacian Coordinates for Seeded Image Segmentation
Error-tolerant Scribbles Based Interactive Image Segmentation
Reliable Multi-view Stereopsis Evaluation
Timing-Based Local Descriptor for Dynamic Surfaces
A Minimal Solution to the Generalized Pose-and-Scale Problem
A General and Simple Method for Camera Pose and Focal Length Determination
Partial Symmetry in Polynomial Systems and Its Application in Computer Vision
Efficient Computation of Relative Pose for Multi-Camera Systems
Simultaneous Localization and Calibration: Self-Calibration of Consumer Depth Cameras
Minimal Scene Descriptions from Structure from Motion Models
Fast, Approximate Piecewise-Planar Modeling Based on Sparse Structure-from-Motion and Dense Superpixels
On Projective Reconstruction In Arbitrary Dimensions
Stereo under Sequential Optimal Sampling: A Statistical Analysis Framework for Search Space Reduction
Efficient pruning LMI conditions for Branch-and-Prune Rank and Chirality-Constrained Estimation of the Dual Absolute Quadric
Very Fast Solution to the PnP Problem with Algebraic Outlier Rejection
Finding Vanishing Points via Point Alignments in Image Primal and Dual Domains
Discriminative Feature-to-Point Matching in Image-Based Localization
Two-View Camera Calibration for Multi-Layer Flat Refractive Interface
Accurate Localization and Pose Estimation for Large 3D Models
Relative Pose Estimation for a Multi-Camera System with Known Vertical Direction
Iterative Multilevel MRF Leveraging Context and Voxel Information for Brain Tumour Segmentation in MRI
13:30-14:45Parallel Oral Sessions (5 papers each)
Orals 2A - Statistical Methods and Learning I Orals 2B - Action Recognition
Optimal Decisions from Probabilistic Models: the Intersection-over-Union Case
Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group
Covariance Trees for 2D and 3D Processing
Multi-View Super Vector for Action Recognition
Hierarchical Subquery Evaluation for Active Learning on a Graph
Unsupervised Spectral Dual Assignment Clustering of Human Actions in Context
Anytime Recognition of Objects and Scenes
Parsing videos of actions with segmental grammars
Rich feature hierarchies for accurate object detection and semantic segmentation
Rate-Invariant Analysis of Trajectories on Riemannian Manifolds with Application in Visual Speech Recognition
15:15-16:30Awards / Plenary (Doris Tsao)
16:30-18:30Poster Session (58 posters)
Posters P2 - Poster Session (3D Vision, Recognition, Statistical Methods and Learning, Action Recognition)
Piecewise Planar and Compact Floorplan Reconstruction from Images
Data-driven Flower Petal Modeling with Botany Priors
User-Specific Hand Modeling from Monocular Depth Sequences
Class Specific 3D Object Shape Priors Using Surface Normals
Frequency-Based 3D Reconstruction of Transparent and Specular Objects
Human Body Shape Estimation Using a Multi-Resolution Manifold Forest
Quality Dynamic Human Body Modeling Using a Single Low-cost Depth Camera
Single-View 3D Scene Parsing by Attributed Grammar
Separation of Line Drawings Based on Split Faces for 3D Object Reconstruction
When 3D Reconstruction Meets Ubiquitous RGB-D Images
Stable Template-Based Isometric 3D Reconstruction in All Imaging Conditions by Linear Least-Squares
Discrete-Continuous Depth Estimation from a Single Image
Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition
Seeing What You're Told: Sentence-Guided Activity Recognition In Video
Action localization by tubelets from motion
Actionness Ranking with Lattice Conditional Ordinal Random Fields
Multiple Granularity Analysis for Fine-grained Action Detection
Human Action Recognition across Datasets by Foreground-weighted Histogram Decomposition
A Depth-Aware Descriptor for Action Recognition
The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities
Complex Activity Recognition using Granger Constrained DBN (GCDBN) in Sports and Surveillance Video
Incremental Activity Modeling and Recognition in Streaming Videos
Super Normal Vector for Activity Recognition Using Depth Sequences
Discriminative Hierarchical Modeling of Spatio-Temporally Composable Human Activities
A Multigraph Representation for Improved Unsupervised/Semi-supervised Learning of Human Actions
StoryGraphs: Visualizing Character Interactions as a Timeline
Learning Receptive Fields for Pooling from Tensors of Feature Response
Towards Unified Human Parsing and Pose Estimation
Ask the image: supervised pooling to preserve feature locality
Similarity Comparisons for Interactive Fine-Grained Categorization
Time Machine: Continuous Manifold Based Adaptation for Evolving Visual Domains
Talking Heads: Detecting Humans and Recognizing Their Interactions
Salient Region Detection via High-Dimensional Color Transform
The Role of Context for Object Detection and Semantic Segmentation in the Wild
Switchable Deep Network for Pedestrian Detection
Compact Representation for Image Classification: To Choose or to Compress?
Capturing long-tail distributions of object subcategories
Accurate Object Detection with Joint Classification-Regression Random Forests
Additive Quantization for Extreme Vector Compression
Product Sparse Coding
Informed Haar-like Features Improve Pedestrian Detection
Image Reconstruction from Bag-of-Visual-Words
Beta Process Multiple Kernel Learning
Random Laplace Feature Maps for Semigroup Kernels on Histograms
Hash-SVM: Scalable Kernel Machines for Large-Scale Visual Classification
Transitive Distance Clustering with K-Means Duality
Simultaneous Twin Kernel Learning for Structured Prediction
Bregman Divergences for Infinite Dimensional Covariance Matrices
Optimizing Average Precision using Weakly Supervised Data
Subspace Clustering for Sequential Data
Predicting Multiple Attributes via Relative Multi-task Learning
Learning Inhomogeneous FRAME Models for Object Patterns
Empirical Minimum Bayes Risk Prediction: How to extract an extra few % performance from vision models with just three more parameters
Fantope Regularization in Metric Learning
Kernel-PCA Analysis of Surface Normals
Merging SVMs with Linear Discriminant Analysis: A Combined Model
Stable Learning in Coding Space for Multi-Class Decoding and Its Extension for Multi-Class Hypothesis Transfer Learning
Finding the Subspace Mean or Median to Fit Your Need


08:30-10:00Parallel Oral Sessions (6 papers each)
Orals 3A - Motion and Tracking Orals 3B - Discrete Optimization
Adaptive Color Attributes for Real-Time Visual Tracking
A Primal-Dual Method for Higher-Order Multilabel Markov Random Fields
Local Layering for Joint Motion Estimation and Occlusion Detection
Energy based multi-model fitting & matching for 3D reconstruction
Realtime and Robust Hand Tracking from Depth
Local Submodular Approximations for Binary Pairwise Energies
Multi-Output Learning for Camera Relocalization
Search Space Reduction in Discrete Optimization
MAP Visibility Estimation for Large-Scale Dynamic 3D Reconstruction
Partial Optimality by Pruning for MAP-inference with General Graphical Models
Multi-Object Tracking via Constrained Sequential Labeling
Scene Labeling Using Beam Search Under Mutex Constraints
10:00-12:00Poster Session (56 posters)
Posters P3 - Poster Session (Motion and Tracking, Optimization Methods, Statistical Methods and Learning, Stereo and SFM)
Persistent Tracking for Wide Area Aerial Surveillance
Multi-Cue Visual Tracking Using Robust Feature-Level Fusion Based on Joint Sparse Representation
Multi-Forest Tracker: A Chameleon in Tracking
Rigid Motion Segmentation using Randomized Voting
Robust Online Multi-Object Tracking based on Tracklet Confidence and Online Discriminative Appearance Learning
Pyramid-based Visual Tracking Using Sparsity Represented Mean Transform
Tracklet Association with Online Reidentification in Network Flow Optimaiztion for Long-term Multi-Person Tracking
An Online Learned Elementary Grouping Model for Multi-target Tracking
Diversity-Enhanced Condensation Algorithm and Its Application for Robust and Accurate Endoscope Electromagnetic Tracking
Partial Occlusion Handling for Visual Tracking via Robust Part Matching
Speeding Up Tracking by Ignoring Features
Subspace Tracking under Dynamic Dimensionality for Online Background Subtraction
Multiple Target Tracking Based on Hierarchical Relation Hypergraph
Bi-label Propagation for Generic Multiple Object Tracking
A Probabilistic Framework for Multitarget Tracking with Mutual Occlusions
Occlusion Geodesics for Online Multi-Object Tracking
Efficient Nonlinear Markov Models for Human Motion
A Compositional Model for Low-Dimensional Image Set Representation
A Principled Approach for Coarse-to-Fine MAP Inference
Fast Approximate Inference in Higher Order MRF-MAP Labeling Problems
Scanline Sampler without Detailed Balance: An Efficient MCMC for MRF Optimization
Higher-Order Clique Reduction Without Auxiliary Variables
Topic Modeling of Multimodal Data: an Autoregressive Approach
Model Transport: Towards Scalable Transfer Learning on Manifolds
Learning Fine-grained Image Similarity with Deep Ranking
Attributed Graph Mining for Graph Matching: An Attempt to Define and Extract Soft Attributed Patterns
Deep Fisher Kernels
Transfer Joint Matching for Visual Domain Adaptation
Recognizing RGB Images by Learning from RGB-D Data
Instance-weighted Transfer Learning of Active Appearance Models
Scalable Multitask Representation Learning for Scene Classification
Learning to Learn, from Transfer Learning to Domain Adaptation: A Unifying Perspective
Constructing Robust Affinity Graph for Spectral Clustering
A fast and robust algorithm to count topologically persistent holes in noisy clouds
Co-localization in Real-World Images
Spectral Clustering with Jensen-type kernels and their multi-point extensions
Fast and Robust Archetypal Analysis for Representation Learning
Photometric Bundle Adjustment for Dense Multi-View 3D Modeling
The Photometry of Intrinsic Images
Super-resolving Appearance of 3D Deformable Shapes from Multiple Videos
PatchMatch Based Joint View Selection and Depthmap Estimation
Light Field Stereo Matching Using Bilateral Statistics of Surface Cameras
Recovering Surface Details under General Unknown Illumination Using Shading and Coarse Multi-view Stereo
Probabilistic Labeling Cost for High-Accuracy Multi-view Reconstruction
Complex Non-Rigid Motion 3D Reconstruction by Union of Subspaces
A Procrustean Markov Process for Non-Rigid Structure Recovery
Good Vibrations: A Modal Analysis Approach for Sequential Non-Rigid Structure from Motion
High Accuracy Monocular Localization for Autonomous Driving Using Adaptive Ground Estimation
On the quotient representation for the essential manifold
Efficient High-Resolution Stereo Matching using Local Plane Sweeps
Cross-Scale Cost Aggregation for Stereo Matching
Asymmetrical Gauss Mixture Models for Point Sets Matching
Fast and Reliable Two-View Translation Estimation
Graph Cut based Continuous Stereo Matching using Locally Shared Labels
Learning to Detect Ground Control Points for Improving the Accuracy of Stereo Matching
13:30-15:00Parallel Oral Sessions (6 papers each)
Orals 4A - PAMI/IJCV Special Journal Session Orals 4B - Attribute-based Recognition and Human Pose Estimation
Make3D: Learning 3D Scene Structure from a Single Still Image
Decorrelating Semantic Visual Attributes by Resisting the Urge to Share
Product quantization for nearest neighbor search
PANDA: Pose Aligned Networks for Deep Attribute Modeling
The PASCAL Visual Object Classes (VOC) Challenge
Learning Scalable Discriminative Attributes with Sample Relatedness
Convex and Semi-Nonnegative Matrix Factorizations
DeepPose: Human Pose Estimation via Deep Neural Networks
Robust face recognition via sparse representation
Iterated Second-Order Label Sensitive Pooling for 3D Human Pose Estimation
Deep Learning with Hierarchical Convolutional Factor Analysis
3D Pictorial Structures for Multiple Human Pose Estimation
15:30-16:30Parallel Oral Sessions (4 papers each)
Orals 5A - Face and Gesture Orals 5B - Convolutional Neural Nets
Learning Euclidean-to-Riemannian Metric for Point-to-Set Classification
Filter Forests for Learning Data-Dependent Convolutional Kernels
Face Alignment at 3000 FPS via Regressing Local Binary Features
Learning and Transferring Mid-Level Image Representations using Convolutional Neural Networks
A Compact and Discriminative Face Track Descriptor
Large-scale Video Classification using Convolutional Neural Networks
DeepFace: Closing the Gap to Human-Level Performance in Face Verification
Convolutional Neural Networks for No-Reference Image Quality Assessment
16:30-18:30Poster Session (53 posters)
Posters P4 - Poster Session (Face and Gesture, Recognition)
Occlusion Coherence: Localizing Occluded Faces with a Hierarchical Deformable Part Model
Nonparametric Context Modeling of Local Appearance for Pose- and Expression-Robust Facial Landmark Localization
Learning Expressionlets on Spatio-Temporal Manifold for Dynamic Facial Expression Recognition
Who Do I Look Like? Determining Parent-Offspring Resemblance via Genetic Features
Unified Face Analysis by Iterative Multi-Output Random Forests
Geometric Generative Gaze Estimation (G3E) for Remote RGB-D Cameras
A Hierarchical Probabilistic Model for Facial Feature Detection
RAPS: Robust and Efficient Automatic Construction of Person-Specific Deformable Models
Non-Parametric Bayesian Constrained Local Models
Facial Expression Recognition via a Boosted Deep Belief Network
Automatic Construction of Deformable Models In-The-Wild
Learning-by-Synthesis for Appearance-based 3D Gaze Estimation
Towards Multi-view and Partially-occluded Face Alignment
Head Pose Estimation Based on Multivariate Label Distribution
Efficient Boosted Exemplar-based Face Detection
Gauss-Newton Deformable Part Models for Face Alignment in-the-Wild
Incremental Face Alignment in the Wild
One Millisecond Face Alignment with an Ensemble of Regression Trees
Discriminative Deep Metric Learning for Face Verification in the Wild
Stacked Progressive Auto-Encoder (SPAE) for Face Recognition Across Poses
Deep Learning Hidden Identity Features for Face Verification
3D-aided face recognition robust to expression and pose variations
Learning Non-Linear Reconstruction Models for Image Set Classification
Gesture Recognition Portfolios for Personalization
Sign Language Spotting using Hierarchical Sequential Patterns with Temporal Intervals
Automatic Feature Learning for Robust Shadow Detection
Packing and Padding: Coupled Multi-index for Accurate Image Retrieval
Adaptive Object Retrieval with Kernel Reconstructive Hashing
Bayes Merging of Multiple Vocabularies for Scalable Image Retrieval
Fast Supervised Hashing with Decision Trees for High-Dimensional Data
Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts
Associative embeddings for large-scale knowledge transfer with self-assessment
Detecting Objects using Deformation Dictionaries
Persistence-based Object Recognition
Inferring Unseen Views of People
Birdsnap: Large-scale Fine-grained Visual Categorization of Birds
Predicting Object Dynamics in Scenes
Enriching Visual Knowledge Bases via Object Discovery and Segmentation
Seeing the Arrow of Time
Hierarchical Feature Hashing for Fast Dimensionality Reduction
Modeling Image Patches with a Generic Dictionary of Mini-Epitomes
Simplex-Based 3D Spatio-Temporal Feature Description for Action Recognition
In Search of Inliers: 3D Correspondence by Local and Global Voting
Collective Matrix Factorization Hashing for Multimodal Data
Finding Matches in a Haystack: A Max-Pooling Strategy for Graph Matching in the Presence of Outliers
Locality in Generic Instance Search from One Example
Congruency-Based Reranking
Asymmetric sparse kernel approximations for large-scale visual search
Locally Linear Hashing for Extracting Non-Linear Manifolds
Active Frame, Location, and Detector Selection for Automated and Manual Video Annotation
Distance Encoded Product Quantization
Collaborative Hashing
Scalable Object Detection using Deep Neural Networks


08:30-10:00Parallel Oral Sessions (6 papers each)
Orals 6A - Physics-based Vision and Shape-from-X Orals 6B - Video: Events, Activities and Surveillance
Multiview Shape and Reflectance from Natural Illumination
Socially-aware Large-scale Crowd Forecasting
Reflectance and Fluorescent Spectra Recovery based on Fluorescent Chromaticity Invariance under Varying Illumination
L0 Regularized Stationary Time Estimation for Crowd Group Analysis
What Camera Motion Reveals About Shape with Unknown BRDF
Scene-Independent Group Profiling in Crowd
Photometric Stereo using Constrained Bivariate Regression for General Isotropic Surfaces
Temporal Sequence Modeling For Video Event Detection
Robust Separation of Reflection from Multiple Images
Recognition of Complex Events exploiting Temporal Dynamics between Underlying Concepts
Surface-from-Gradients: An Approach Based on Discrete Geometry Processing
Video Event Detection by Inferring Temporal Instance Labels
10:00-12:00Poster Session (55 posters)
Posters P5 - Poster Session (Physics-based Vision, Recognition, Video: Events, Activities and Surveillance)
Backscatter Compensated Photometric Stereo with 3 Sources
Calibrating a non-isotropic near point light source using a plane
A New Perspective on Material Classification and Ink Identification
High Quality Photometric Reconstruction using a Depth Camera
Robust Surface Reconstruction via Triple Sparsity
Scattering Parameters and Surface Normals from Homogeneous Translucent Materials using Photometric Stereo
Better Shading for Better Shape Recovery
Stable and Informative Spectral Signatures for Graph Matching
Deformable Object Matching via Deformation Decomposition based 2D Label MRF
Locally Optimized Product Quantization for Approximate Nearest Neighbor Search
Multi-source Deep Learning for Human Pose Estimation
Posebits for Monocular Human Pose Estimation
Real-time Simultaneous Pose and Shape Estimation for Articulated Objects with a Single Depth Camera
Mixing Body-Part Sequences for Human Pose Estimation
Robust Estimation of 3D Human Poses from Single Images
Fisher and VLAD with FLAIR
Immediate, scalable object category detection
Word Channel Based Multiscale Pedestrian Detection Without Image Resizing and Using Only One Classifier
Parsing Occluded People
Multi-fold MIL Training for Weakly Supervised Object Localization
Generating object segmentation proposals using global and local search
A Novel Chamfer Template Matching Method Using Variational Mean Field
Confidence-Rated Multiple Instance Boosting for Object Detection
COSTA: Co-Occurrence Statistics for Zero-Shot Classification
Analysis by Synthesis: 3D Object Recognition by Object Reconstruction
Submodular Object Recognition
Multimodal Learning in Loosely-organized Web Images
Generalized Max Pooling
Domain Adaptation on the Statistical Manifold
Nonparametric Part Transfer for Fine-grained Recognition
The Fastest Deformable Part Model for Object Detection
Unsupervised Learning of Dictionaries of Hierarchical Compositional Models
Quasi Real-Time Summarization for Consumer Videos
Gait Recognition under Speed Transition
Video Classification Based on Generalized Maximum Co-occurrence Cliques
Temporal Segmentation of Egocentric Videos
Efficient Localization with Fisher Vectors using Approximate Normalizations
Unsupervised Trajectory Modelling using Temporal Information via Minimal Paths
A Hierarchical Context Model for Event Recognition in Surveillance Video
DISCOVER: Discovering Important Segments for Classification of Video Events and Recounting
Towards Good Practices for Action Video Encoding
Efficient feature extraction, encoding and classification\\ for action recognition
3D Pose from Motion for Cross-view Action Recognition via Non-linear Circulant Temporal Encoding
Human Action Recognition Based on Context-Dependent Graph Kernels
Depth and Skeleton Associated Action Recognition without Online Accessible RGB-D Cameras
Deeply-Learned Slow Feature Analysis for Action Recognition
A Cause and Effect analysis of motion trajectories for modeling actions
From Stochastic Grammar to Bayes Network: Probabilistic Parsing of Complex Activity
Cross-view Action Modeling, Learning and Recognition
Visual Semantic Search: Retrieving Videos via Complex Textual Queries
Zero-shot Event Detection using Multi-modal Fusion of Weakly Supervised Concepts
Dual Linear Regression Based Classification for Face Cluster Recognition
Bags of Spacetime Energies for Dynamic Scene Recognition
Feature-Independent Action Spotting Without Human Localization, Segmentation or Frame-wise Tracking
From Human-Annotated to Machine-Discovered Concepts using Consensus Regularization
13:30-15:00Parallel Oral Sessions (6 papers each)
Orals 7A - Low-level Vision and Image Processing Orals 7B - Medical and Biological Image Analysis
Scale-space Processing Using Polynomial Representations
Multiscale Centerline Detection by Learning a Scale-Space Distance Transform
Single Image Layer Separation using Relative Smoothness
Multivariate General Linear Models (MGLM) on Riemannian Manifolds with Applications to Statistical Analysis of Diffusion Weighted Images
Image Fusion with Local Spectral Consistency and Dynamic Gradient Sparsity
Preconditioning for Accelerated Iteratively Reweighted Least Squares in Structured Sparsity Reconstruction
Segmentation-Free Dynamic Scene Deblurring
Joint Coupled-Feature Representation and Coupled Boosting for AD Diagnosis
Shrinkage Fields for Effective Image Restoration
Deformable Registration of Feature-Endowed Point Sets Based on Tensor Fields
Camouflaging an Object from Many Viewpoints
Learning to disambiguate indistinguishable objects over time using weakly supervised structured learning
15:30-16:30Plenary Session (Stephane Mallat)
16:30-18:30Poster Session (55 posters)
Posters P6 - Poster Session (Biologically Inpired Vision, Low-level Vision, Medical and Biological Image Analysis, Segmentation)
Mirror Symmetry Histograms for Capturing Geometric Properties in Images
Learning optimal features for salient object detection
Large-Scale Optimization of Hierarchical Features for Saliency Prediction in Natural Images
Saliency Detection on Light Fields
Saliency Optimization from Robust Background Detection
A Reverse Hierarchy Model for Predicting Eye Fixations
Joint-Histogram Weighted Median Filter
Edge-aware Gradient Domain Optimization Framework for Image Filtering by Local Propagation
Super-Resolving Noisy Images
Sparse Dictionary Learning for Edit Propagation of High-resolution Images
Weighted Nuclear Norm Minimization with Application to Image Denoising
Using Projection Kurtosis Concentration Of Natural Images For Blind Noise Covariance Matrix Estimation
Blind Image Quality Assessment using Semi-supervised Rectifier Networks
Separable Kernel for Image Deblurring
Joint Depth Estimation and Camera Shake Removal from Single Blurry Image
Deblurring Text Images via L0-Regularized Intensity and Gradient Prior
Total Variation Blind Deconvolution: The Devil is in the Details
Single Image Super-resolution using Deformable Patches
Multi-Shot Imaging: Joint Alignment, Deblurring and Resolution-Enhancement
CID: Combined Image Denoising in Spatial and Frequency Domains Using Web Images
Multipoint Filtering with Local Polynomial Approximation and Range Guidance
Decomposable Nonlocal Tensor Dictionary Learning for Multispectral Image Denoising
Robust 3D Features for Matching between Distorted Range Scans Captured by Moving Systems
Discriminative Blur Detection Features
Detection, Rectification and Segmentation of Co-planar Repeated Patterns
A Learning-to-Rank Approach for Image Color Enhancement
Investigating Haze-relevant Features in A Learning Framework for Image Dehazing
Quality Assessment for Comparing Image Enhancement Algorithms
Shadow Removal from Single RGB-D Images
Manifold Based Dynamic Texture Synthesis from Extremely Few Samples
The Synthesizability of texture examples
Reconstructing Evolving Tree Structures in Time Lapse Sequences
Total-Variation Minimization on Unstructured Volumetric Mesh: Biophysical Applications on Reconstruction of 3D Ischemic Myocardium
Tracking on the Product Manifold of Shape and Orientation for Tractography from Diffusion MRI
Curvilinear Structure Tracking by Low Rank Tensor Approximation with Model Propagation
Patch-based Evaluation of Image Segmentation
Evaluation of Scan-Line Optimization for 3D Medical Image Registration
Tissue Classification via Multispectral Convolutional Sparse Coding
Matrix-Similarity Based Loss Function and Feature Selection for Alzheimer's Disease Diagnosis
Discriminative Sparse Inverse Covariance Matrix: Application in Brain Functional Network Classification
A Bayesian Framework For the Local Configuration of Retinal Junctions
Learning-Based Atlas Selection for Multiple-Atlas Segmentation
Fully Automated Non-rigid Segmentation with Distance Regularized Level Set Evolution Initialized and Constrained by Deep-structured Inference
FAST LABEL: Easy and Efficient Optimization of Joint Multi-Label and Estimation Problems
Learning to Group Objects
Joint Unsupervised Multi-Class Image Segmentation
Semantic Object Selection
Discrete-Continuous Gradient Orientation Estimation for Faster Unsupervised Segmentation
Object-based Multiple Foreground Video Co-segmentation
Parsing World's Skylines using Shape-Constrained MRFs
Clothing Co-Parsing by Joint Image Segmentation and Labeling
Tell Me What You See and I will Show You Where It Is
Beat the MTurkers: Automatic Image Labeling from Weak 3D Supervision
Efficient Structured Parsing of Facades Using Dynamic Programming
Dense Semantic Image Segmentation with Objects and Attributes

FRIDAY, June 27

08:30-10:00Parallel Oral Sessions (6 papers each)
Orals 8A - Recognition: Detection, Categorization, and Classification Orals 8B - Computational Photography: Sensing and Display
Learning Everything about Anything: Webly-Supervised Visual Concept Learning
Diffuse Mirrors: 3D Reconstruction from Diffuse Indirect Illumination Using Inexpensive Time-of-Flight Sensors
Dirichlet-based Histogram Feature Transform for Image Classification
Fourier Analysis on Transient Imaging by Multifrequency Time-of-Flight Camera
BING: Binarized Normed Gradients for Objectness Estimation at 300fps
Transparent Object Reconstruction via Coded Transport of Intensity
Context Driven Scene Parsing with Attention to Rare Classes
3D Shape and Indirect Appearance by Structured Light Transport
Patch to the Future: Unsupervised Visual Prediction
Shape-Preserving Half-Projective Warps for Image Stitching
Triangulation embedding and democratic aggregation for image search
Parallax-tolerant Image Stitching
10:00-12:00Poster Session (56 posters)
Posters P7 - Poster Session (Computational Photography, Motion and Tracking, Recognition)
Low-Cost Compressive Sensing for Color Video and Depth
Aliasing Detection and Reduction in Plenoptic Imaging
Illumination-Aware Age Progression
Color Transfer using Probabilistic Moving Least Squares
Image Preconditioning: Balancing Contrast and Ringing
Time-Mapping Using Space-Time Saliency
Gyro-Based Multi-Image Deconvolution for Removing Handshake Blur
Similarity-Aware Patchwork Assembly for Depth Image Super-Resolution
Deblurring Low-light Images with Light Streaks
Depth Enhancement via Low-rank Matrix Completion
Raw-to-raw: Mapping between image sensor color responses
DAISY Filter Flow: A Generalized Discrete Approach to Dense Correspondences
Robust 3D Tracking with Descriptor Fields
Evolutionary Quasi-random Search for Hand Articulations Tracking
Scalable 3D Tracking of Multiple Interacting Objects
Bayesian Active Appearance Models
Human Shape and Pose Tracking Using Keyframes
Better Feature Tracking Through Subspace Constraints
Online Object Tracking, Learning and Parsing with And-Or Graphs
Region-based particle filter for video object segmentation
Visual Tracking via Probability Continuous Outlier Model
Visual Tracking Using Pertinent Patch Selection and Masking
Interval Tracker: Tracking by Interval Analysis
Unifying Spatial and Attribute Selection for Distracter-resilient Tracking
Pedestrian Detection in Low-resolution Imagery by Learning Multi-scale Intrinsic Motion Structures (MIMS)
Multi-target Tracking with Motion Context in Tensor Power Iteration
SphereFlow: 6 DoF Scene Flow from RGB-D Pairs
Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow
Learning an image-based motion context for multiple people tracking
Semi-Supervised Coupled Dictionary Learning for Person Re-identification
What are you talking about? Text-to-Image Coreference
Predicting Failures of Vision Systems
Three Guidelines of Online Learning for Large-Scale Visual Recognition
Using k-poselets for detecting people and localizing their keypoints
Randomized Max-Margin Compositions for Visual Recognition
Large-scale visual font recognition
Describing Textures in the Wild
Relative Parts: Distinctive Parts for Learning Relative Attributes
Understanding Objects in Detail with Fine-grained Attributes
Predicting User Annoyance Using Visual Attributes
Linear Ranking Analysis
Transformation Pursuit for Image Classification
Incremental Learning of NCM Forests for Large-Scale Image Classification
Object Classification with Adaptive Regions
Discriminative Ferns Ensemble for Hand Pose Recognition
Are Cars Just 3D Boxes? - Jointly Estimating the 3D Shape of Multiple Objects
Human Pose Estimation: New Benchmark and State of the Art Analysis
Using a deformation field model for localizing faces and facial points under weak supervision
Active Annotation Translation
Looking Beyond the Visible Scene
Two-Class Weather Labeling
Learning Important Spatial Pooling Regions for Scene Classification
Orientational Pyramid Matching for Recognizing Indoor Scenes
Multilabel Ranking with Inconsistent Rankers
Scene Parsing with Object Instances and Occlusion Ordering
13:30-15:00Parallel Oral Sessions (6 papers each)
Orals 9A - Statistical Methods and Learning II Orals 9B - 3D Geometry / Shape
Optimizing Over Radial Kernels on Compact Manifolds
A Riemannian framework for matching point clouds represented by the Schr\"{o}dinger distance transform
Grassmann Averages for Scalable Robust PCA
Seeing 3D chairs: exemplar part-based 2D-3D alignment using a large dataset of CAD models
Robust Subspace Segmentation with Block-diagonal Prior
A Mixture of Manhattan Frames: Beyond the Manhattan World
Unsupervised One-Class Learning for Automatic Outlier Removal
Local Regularity-driven City-scale Facade Detection from Aerial Images
Smooth Representation Clustering
Latent Regression Forest: Structural Estimation of 3D Articulated Hand Posture
Novel methods for multilinear data completion and de-noising based on tensor-SVD
FAUST: Dataset and evaluation for 3D mesh registration
15:30-16:30Parallel Oral Sessions (4 papers each)
Orals 10A - Optimization Methods Orals 10B - View Synthesis and Other Applications
Second-order Shape Optimization for Geometric Inverse Problems in Vision
Reconstructing Storyline Graphs for Image Recommendation from Web Community Photos
L0 norm based dictionary learning method with global convergence
Active Flattening of Curved Document Images via Two Structured Beams
Adaptive Partial Differential Equation Learning for Visual Saliency Detection
Image-based Synthesis and Re-Synthesis of Viewpoints Guided by 3D Models
Robust Orthonormal Subspace Learning: Efficient Recovery of Corrupted Low-rank Matrices
Bayesian View Synthesis and Image-Based Rendering Principles
16:30-18:30Poster Session (47 posters)
Posters P8 - Poster Session (3D Vision, Optimization Methods, Shape, Vision for Graphics, Web and Vision Systems, Document Analysis)
Ground Plane Estimation using a Hidden Markov Model
Fast MRF Optimization with Application to Depth Reconstruction
Exploiting Shading Cues in Kinect IR Images for Geometry Refinement
Fast Rotation Search with Stereographic Projections for 3D Registration
Local Readjustment for High-Resolution 3D Reconstruction
Turning Mobile Phones into 3D Scanners
T-Linkage: a Continuous Relaxation of J-Linkage for Multi-Model Fitting
Motion-Depth: RGB-D Depth Map Enhancement with Motion and Depth in Complement
Generalized Pupil-Centric Imaging and Analytical Calibration for a Non-frontal Camera
Geometric Urban Geo-Localization
3D Reconstruction from Accidental Motion
Real-time Model-based Articulated Object Pose Detection and Tracking with Variable Rigidity Constraints
Occluding Contours for Multi-View Stereo
Aerial Reconstructions via Probabilistic Data Fusion
3D Modeling from Wide Baseline Range Scans using Contour Coherence
Orientation Robust Textline Detection in Natural Images
Strokelets: A Learned Multi-Scale Representation for Scene Text Recognition
Region-based Discriminative Feature Pooling for Scene Text Recognition
Fast and Exact: Shape Segmentation Using ADMM and Structured Prediction
Pseudoconvex Proximal Splitting for $L_\infty$ Problems in Multiview Geometry
A Convex Relaxation of the Ambrosio--Tortorelli Elliptic Functionals for the Mumford--Shah Functional
Sequential Convex Relaxation for Mutual Information-Based Unsupervised Figure-Ground Segmentation
Decorrelated Vectorial Total Variation
Efficient Squared Curvature
Multi-feature Spectral Clustering with Minimax Optimization
Quality-based Multimodal Classification Using Tree-Structured Sparsity
Newton Greedy Pursuit: a Quadratic Approximation Method for Sparsity-Constrained Optimization
Generalized Nonconvex Nonsmooth Low-Rank Minimization
Latent Dictionary Learning for Sparse Representation based Classification
Is Rotation a Nuisance in Shape Recognition?
Dual-Space Decomposition of 2D Complex Shapes
Noising versus Smoothing for Vertex Identification in Unknown Shapes
Surface Registration by Optimization in Constrained Diffeomorphism Space
Dense Non-Rigid Shape Correspondence using Random Forests
Covariance descriptors for 3D shape matching and retrieval
Symmetry-Aware Isometric Matching of Incomplete 3D Surfaces
An Automated Estimator of Image Visual Realism Based on Human Cognition
SteadyFlow: Spatially Smooth Optical Flow for Video Stabilization
Automatic Face Reenactment
Joint Summarization of Large-scale Collections of Web Images and Videos for Storyline Reconstruction
Semi-supervised Relational Topic Model for Weakly Annotated Image Recognition in Social Media
Beyond Human Opinion Scores: Blind Image Quality Assessment based on Synthetic Scores
Active Sampling for Subjective Image Quality Assessment
A Study on Cross-Population Age Estimation
Remote Heart Rate Measurement From Face Videos Under Realistic Situations
6 Seconds of Sound and Vision: Creativity in Micro-Videos
Robust Refinement of GPS-Tags Using RandomWalks with an Adaptive Damping Factor
Multi Label Generic Cuts: Optimal Inference in Multi Label Multi Clique MRF-MAP Problems