Day 1
8:50–9:00
Welcome & Opening remarks (Announce Marr Prize)
9:00–10:00
Oral session 1A Recognition Orals 1A:01–1A:03
9:00–10:00 (Cordelia Schmid)
1HOGgles: Visualizing Object Detection Features
Authors:
9How Do You Tell a Blackbird from a Crow?
Authors:
17Regionlets for Generic Object Detection
Authors:
Authors:
10:00–10:45
Spotlights (45min, 52 spotlights at 50secs each)
10:00–10:45 (Vittorio Ferrari)
10:45–12:15
Poster session 1A: Posters 1A:01–1A:52
33Shape Anchors for Data-Driven Multi-view Reconstruction
Authors:
41Deterministic Fitting of Multiple Structures Using Iterative MaxFS with Inlier Scale Estimation
Authors:
49Constant Time Weighted Median Filtering for Stereo Matching and Beyond
Authors:
57Refractive Structure-from-Motion on Underwater Images
Authors:
65Live Metric 3D Reconstruction on Mobile Phones
Authors:
73Joint Subspace Stabilization for Stereoscopic Video
Authors:
81Video Synopsis by Heterogeneous Multi-source Correlation
Authors:
89DCSH - Matching Patches in RGBD Images
Authors:
97Scene Text Localization and Recognition with Oriented Stroke Detection
Authors:
105Adapting Classification Cascades to New Domains
Authors:
113Deep Learning Identity-Preserving Face Space
Authors:
121Multi-stage Contextual Deep Learning for Pedestrian Detection
Authors:
129Unsupervised Random Forest Manifold Alignment for Lipreading
Authors:
137Calibration-Free Gaze Estimation Using Human Gaze Patterns
Authors:
145Partial Sum Minimization of Singular Values in RPCA for Low-Level Vision
Authors:
153Saliency Detection: A Boolean Map Approach
Authors:
161Topology-Constrained Layered Tracking with Latent Flow
Authors:
169Stacked Predictive Sparse Coding for Classification of Distinct Regions in Tumor Histopathology
Authors:
177Higher Order Matching for Consistent Multiple Target Tracking
Authors:
185A General Dense Image Matching Framework Combining Direct and Feature-Based Costs
Authors:
193Revisiting Example Dependent Cost-Sensitive Learning with Decision Trees
Authors:
201Modeling Self-Occlusions in Dynamic Shape and Appearance Tracking
Authors:
209A Convex Optimization Framework for Active Learning
Authors:
217A Generalized Iterated Shrinkage Algorithm for Non-convex Sparse Coding
Authors:
225Latent Space Sparse Subspace Clustering
Authors:
233Tracking Revisited Using RGBD Camera: Unified Benchmark and Baselines
Authors:
241A Simple Model for Intrinsic Image Decomposition with Depth Cues
Authors:
249Quadruplet-Wise Image Similarity Learning
Authors:
257Complementary Projection Hashing
Authors:
265Find the Best Path: An Efficient and Accurate Classifier for Image Hierarchies
Authors:
273Detecting Dynamic Objects with Multi-view Background Subtraction
Authors:
281Low-Rank Sparse Coding for Image Classification
Authors:
289Allocentric Pose Estimation
Authors:
297Attribute Pivots for Guiding Relevance Feedback in Image Search
Authors:
305Decomposing Bag of Words Histograms
Authors:
313SYM-FISH: A Symmetry-Aware Flip Invariant Sketch Histogram Shape Descriptor
Authors:
321Symbiotic Segmentation and Part Localization for Fine-Grained Categorization
Authors:
Authors:
337Learning a Dictionary of Shape Epitomes with Applications to Image Labeling
Authors:
345Pyramid Coding for Functional Scene Element Recognition in Video Scenes
Authors:
353Box in the Box: Joint 3D Layout and Object Reasoning from Single Images
Authors:
361Semantic Transform: Weakly Supervised Semantic Inference for Relating Visual Attributes
Authors:
369From Subcategories to Visual Composites: A Multi-level Framework for Object Detection
Authors:
377Online Video SEEDS for Temporal Window Objectness
Authors:
385Temporally Consistent Superpixels
Authors:
393Semi-supervised Learning for Large Scale Image Cosegmentation
Authors:
401Automatic Kronecker Product Model Based Detection of Repeated Patterns in 2D Urban Images
Authors:
409Group Norm for Learning Structured SVMs with Unstructured Latent Variables
Authors:
417Alternating Regression Forests for Object Detection and Pose Estimation
Authors:
425Dynamic Label Propagation for Semi-supervised Multi-class Multi-label Classification
Authors:
433Translating Video Content to Natural Language Descriptions
Authors:
441POP: Person Re-identification Post-rank Optimisation
Authors:
12:15–14:15
Lunch
14:15–15:00
Oral session 1B (3 papers, 45mins) Computational Photography Orals 1B:01–1B:03
14:15–15:00 (Srinivasa Narasimhan)
449First-Photon Imaging: Scene Depth and Reflectance Acquisition from One Detected Photon per Pixel
Authors:
Authors:
Authors:
15:00–15:45
Spotlights (45mins)
15:00–15:45 (Yasuyuki Matsushita)
15:45–16:15
Break (30 mins)
16:15–17:15
Oral session 1C 3D Vision Orals 1C:01–1C:04
16:15–17:15 (Fredrik Kahl)
473Elastic Fragments for Dense Scene Reconstruction
Authors:
481A Global Linear Method for Camera Pose Registration
Authors:
489A Rotational Stereo Model Based on XSlit Imaging
Authors:
497Lifting 3D Manhattan Lines from a Single Image
Authors:
17:15–18:45
Poster session 1B : Posters 1B:01–1B:52
505Dynamic Probabilistic Volumetric Models
Authors:
513Network Principles for SfM: Disambiguating Repeated Structures with Local Context
Authors:
521Efficient and Robust Large-Scale Rotation Averaging
Authors:
529Pose Estimation with Unknown Focal Length Using Points, Directions and Lines
Authors:
537Unsupervised Intrinsic Calibration from a Single Frame Using a “Plumb-Line” Approach
Authors:
545Structured Light in Sunlight
Authors:
Authors:
561Fast Direct Super-Resolution by Simple Functions
Authors:
569Recognizing Text with Perspective Distortion in Natural Scenes
Authors:
577Rank Minimization across Appearance and Shape for AAM Ensemble Fitting
Authors:
585Face Recognition via Archetype Hull Ranking
Authors:
593Optimization Problems for Fast AAM Fitting in-the-Wild
Authors:
601Robust Feature Set Matching for Partial Face Recognition
Authors:
609Cross-View Action Recognition over Heterogeneous Feature Spaces
Authors:
617Efficient Image Dehazing with Boundary Constraint and Contextual Regularization
Authors:
625From Where and How to What We See
Authors:
633Restoring an Image Taken through a Window Covered with Dirt or Rain
Authors:
Authors:
649Tracking via Robust Multi-task Multi-view Joint Sparse Representation
Authors:
657Online Robust Non-negative Dictionary Learning for Visual Tracking
Authors:
665Robust Object Tracking with Online Multi-lifespan Dictionary Learning
Authors:
673Depth from Combining Defocus and Correspondence Using Light-Field Cameras
Authors:
681Affine-Constrained Group Sparse Coding and Its Application to Image-Based Classifications
Authors:
689Sparse Variation Dictionary Learning for Face Recognition with a Single Training Sample per Person
Authors:
697On the Mean Curvature Flow on Graphs with Applications in Image and Manifold Processing
Authors:
705Perceptual Fidelity Aware Mean Squared Error
Authors:
713Real-World Normal Map Capture for Nearly Flat Reflective Surfaces
Authors:
721Human Attribute Recognition by Rich Appearance Dictionary
Authors:
729Deformable Part Descriptors for Fine-Grained Recognition and Attribute Prediction
Authors:
737Handling Uncertain Tags in Visual Recognition
Authors:
745Implied Feedback: Learning Nuances of User Behavior in Image Search
Authors:
753Learning Near-Optimal Cost-Sensitive Decision Policy for Object Detection
Authors:
761NYC3DCars: A Dataset of 3D Vehicles in Geographic Context
Authors:
769Unsupervised Domain Adaptation by Domain Invariant Projection
Authors:
777SIFTpack: A Compact Representation for Efficient SIFT Matching
Authors:
785PhotoOCR: Reading Text in Uncontrolled Conditions
Authors:
793Probabilistic Elastic Part Model for Unsupervised Face Detector Adaptation
Authors:
801New Graph Structured Sparsity Model for Multi-label Image Annotations
Authors:
Authors:
817A Fully Hierarchical Approach for Finding Correspondences in Non-rigid Shapes
Authors:
825Learning to Rank Using Privileged Information
Authors:
833Joint Segmentation and Pose Tracking of Human in Natural Videos
Authors:
841Characterizing Layouts of Outdoor Scenes Using Spatial Topic Processes
Authors:
849Image Co-segmentation via Consistent Functional Maps
Authors:
857Exemplar Cut
Authors:
865Parallel Transport of Deformations in Shape Space of Elastic Surfaces
Authors:
873A Method of Perceptual-Based Shape Decomposition
Authors:
881Curvature-Aware Regularization on Riemannian Submanifolds
Authors:
Authors:
897Frustratingly Easy NBNN Domain Adaptation
Authors:
905Video Event Understanding Using Natural Language Descriptions
Authors:
913ACTIVE: Activity Concept Transitions in Video Event Classification
Authors:
19:00
IEEE PAMI Technical Committee Meeting
Day 2
9:00–10:00
Oral session 2A Low level vision Orals 2A:01–2A:03
9:00–10:00 (Michael Brown)
921Analysis of Scores, Datasets, and Models in Visual Saliency Prediction
Authors:
929A Color Constancy Model with Double-Opponency Mechanisms
Authors:
937Toward Guaranteed Illumination Models for Non-convex Objects
Authors:
945Nonparametric Blind Super-resolution
Authors:
10:00–10:45
Spotlights (45min, 52 spotlights at 50secs each)
10:00–10:45 (Erik Learned-Miller)
10:45–12:15
Poster session 2A: Posters 2A:01–2A:52
953Street View Motion-from-Structure-from-Motion
Authors:
961A Robust Analytical Solution to Isometric Shape-from-Template with Focal Length Calibration
Authors:
969Point-Based 3D Reconstruction of Thin Objects
Authors:
977Space-Time Tradeoffs in Photo Sequencing
Authors:
Authors:
993Image Guided Depth Upsampling Using Anisotropic Total Generalized Variation
Authors:
1001Fluttering Pattern Generation Using Modified Legendre Sequence for Coded Exposure Imaging
Authors:
1009Towards Motion Aware Light Field Video for Dynamic Scenes
Authors:
1017Handwritten Word Spotting with Corrected Attributes
Authors:
1025Exemplar-Based Graph Matching for Robust Facial Landmark Localization
Authors:
1033Cascaded Shape Space Pruning for Robust Facial Landmark Detection
Authors:
1041Two-Point Gait: Decoupling Gait from Body Shape
Authors:
1049Learning People Detectors for Tracking in Crowded Scenes
Authors:
1057Efficient Pedestrian Detection by Directly Optimizing the Partial Area under the ROC Curve
Authors:
1065Example-Based Facade Texture Synthesis
Authors:
1073Single-Patch Low-Rank Prior for Non-pointwise Impulse Noise Removal
Authors:
1081SGTD: Structure Gradient and Texture Decorrelating Regularization for Image Decomposition
Authors:
1089Drosophila Embryo Stage Annotation Using Label Propagation
Authors:
1097Measuring Flow Complexity in Videos
Authors:
1105Real-Time Body Tracking with One Depth Camera and Inertial Sensors
Authors:
1113Constructing Adaptive Complex Cells for Robust Visual Tracking
Authors:
1121Camera Alignment Using Trajectory Intersections in Unsynchronized Videos
Authors:
1129Slice Sampling Particle Belief Propagation
Authors:
1137Multi-attributed Dictionary Learning for Sparse Coding
Authors:
1145Semi-supervised Robust Dictionary Learning via Efficient l-Norms Minimization
Authors:
1153Saliency and Human Fixations: State-of-the-Art and Study of Comparison Metrics
Authors:
1161Multiview Photometric Stereo Using Planar Mesh Parameterization
Authors:
1169Elastic Net Constraints for Shape Matching
Authors:
Authors:
1185Compositional Models for Video Event Detection: A Multiple Kernel Learning Latent Variable Approach
Authors:
1193Event Recognition in Photo Collections with a Stopwatch HMM
Authors:
Authors:
1209Collaborative Active Learning of a Kernel Machine Ensemble for Recognition
Authors:
1217A Max-Margin Perspective on Sparse Representation-Based Classification
Authors:
1225Attribute Dominance: What Pops Out?
Authors:
1233Neighbor-to-Neighbor Search for Fast Coding of Feature Vectors
Authors:
1241Text Localization in Natural Images Using Stroke Feature Transform and Text Covariance Descriptors
Authors:
1249A Framework for Shape Analysis via Hilbert Space Embedding
Authors:
1257Offline Mobile Instance Retrieval with a Small Memory Footprint
Authors:
1265BOLD Features to Detect Texture-less Objects
Authors:
1273Estimating the 3D Layout of Indoor Scenes and Its Clutter from Depth Sensors
Authors:
1281A Non-parametric Bayesian Network Prior of Human Pose
Authors:
1289Pictorial Human Spaces: How Well Do Humans Perceive a 3D Articulated Pose?
Authors:
1297Co-segmentation by Composition
Authors:
1305Cosegmentation and Cosketch by Unsupervised Learning
Authors:
1313Predicting Sufficient Annotation Strength for Interactive Foreground Segmentation
Authors:
1321Sequential Bayesian Model Update under Structured Scene Prior for Semantic Road Scenes Labeling
Authors:
1329Learning Graph Matching: Oriented to Category Modeling from Cluttered Scenes
Authors:
1337Robust Matrix Factorization with Unknown Noise
Authors:
1345Correlation Adaptive Subspace Segmentation by Trace Lasso
Authors:
1353Monte Carlo Tree Search for Scheduling Activity Recognition
Authors:
1361Manipulation Pattern Discovery: A Nonparametric Bayesian Approach
Authors:
12:15–14:15
lunch
14:15–15:00
Oral session 2B (3 papers 45 mins) Motion and Tracking Orals 2B:01–2B:03
14:15–15:00 (Ian Reid)
1369Perspective Motion Segmentation via Collaborative Clustering
Authors:
1377Piecewise Rigid Scene Flow
Authors:
1385DeepFlow: Large Displacement Optical Flow with Deep Matching
Authors:
15:00–15:45
Spotlights (45mins)
15:00–15:45 (Raquel Urtasun)
15:45–16:15
Break (30 min)
16:15–17:15
Oral session 2C Recognition Orals 2C:01–2C:04
16:15–17:15 (Antonio Torralba)
1393Shufflets: Shared Mid-level Parts for Fast Object Detection
Authors:
1401To Aggregate or Not to aggregate: Selective Match Kernels for Image Search
Authors:
1409NEIL: Extracting Visual Knowledge from Web Data
Authors:
1417Holistic Scene Understanding for 3D Object Detection with RGBD Cameras
Authors:
17:15–18:45
Poster session 2B: Posters 2B:01–2B:52
14253D Scene Understanding by Voxel-CRF
Authors:
1433Complex 3D General Object Reconstruction from Line Drawings
Authors:
1441Subpixel Scanning Invariant to Indirect Lighting Using Quadratic Code Length
Authors:
1449Semi-dense Visual Odometry for a Monocular Camera
Authors:
1457Go-ICP: Solving 3D Registration Efficiently and Globally Optimally
Authors:
Authors:
1473Fibonacci Exposure Bracketing for High Dynamic Range Imaging
Authors:
1481Compensating for Motion during Direct-Global Separation
Authors:
1489Hybrid Deep Learning for Face Verification
Authors:
1497Like Father, Like Son: Facial Expression Dynamics for Kinship Verification
Authors:
1505Handling Occlusions with Franken-Classifiers
Authors:
1513Robust Face Landmark Estimation under Occlusion
Authors:
1521Fingerspelling Recognition with Semi-Markov Conditional Random Fields
Authors:
1529Efficient Salient Region Detection with Soft Image Abstraction
Authors:
1537Cross-Field Joint Image Restoration via Scale Map
Authors:
1545A Joint Intensity and Depth Co-sparse Analysis Model for Depth Map Super-resolution
Authors:
Authors:
1561STAR3D: Simultaneous Tracking and Reconstruction of 3D Objects Using RGB-D Data
Authors:
1569Discriminant Tracking Using Tensor Representation with Semi-supervised Improvement
Authors:
1577Coherent Motion Segmentation in Moving Camera Videos Using Optical Flow Orientations
Authors:
1585Minimal Basis Facility Location for Subspace Segmentation
Authors:
1593Non-convex P-Norm Projection for Robust Sparsity
Authors:
1601Log-Euclidean Kernels for Sparse Representation and Dictionary Learning
Authors:
1609Large-Scale Image Annotation by Efficient and Robust Kernel Metric Learning
Authors:
1617High Quality Shape from a Single RGB-D Image under Uncalibrated Natural Illumination
Authors:
1625SUN3D: A Database of Big Spaces Reconstructed Using SfM and Object Labels
Authors:
1633The Interestingness of Images
Authors:
1641Hierarchical Part Matching for Fine-Grained Visual Categorization
Authors:
1649Joint Optimization for Consistent Multiple Graph Matching
Authors:
1657Unbiased Metric Learning: On the Utilization of Multiple Datasets and Web Images for Softening Bias
Authors:
1665Saliency Detection via Absorbing Markov Chain
Authors:
1673Semantic-Aware Co-indexing for Image Retrieval
Authors:
1681Learning the Visual Interpretation of Sentences
Authors:
1689A Novel Earth Mover's Distance Methodology for Image Matching with Gaussian Mixture Models
Authors:
1697Hierarchical Joint Max-Margin Learning of Mid and Top Level Representations for Visual Recognition
Authors:
1705Query-Adaptive Asymmetrical Dissimilarities for Visual Object Retrieval
Authors:
1713Fine-Grained Categorization by Alignments
Authors:
1721Locally Affine Sparse-to-Dense Matching for Motion and Occlusion Estimation
Authors:
1729Predicting an Object Location Using a Global Image Representation
Authors:
1737Heterogeneous Image Features Integration via Multi-modal Semi-supervised Learning Model
Authors:
1745Building Part-Based Object Detectors via 3D Geometry
Authors:
1753Detecting Curved Symmetric Parts Using a Deformable Disc Model
Authors:
1761Category-Independent Object-Level Saliency Detection
Authors:
Authors:
1777Fast Object Segmentation in Unconstrained Video
Authors:
1785Bayesian Robust Matrix Factorization for Image and Video Processing
Authors:
1793Recursive Estimation of the Stein Center of SPD Matrices and Its Applications
Authors:
1801Correntropy Induced L2 Graph for Robust Subspace Clustering
Authors:
1809Group Sparsity and Geometry Constrained Dictionary Learning for Action Recognition from Depth Maps
Authors:
1817Action and Event Recognition with Fisher Vectors on a Compact Feature Set
Authors:
1825Stable Hyper-pooling and Query Expansion for Event Detection
Authors:
1833Active Learning of an Action Detector from Untrimmed Videos
Authors:
18:45–19:00
Award Session
19:00
Welcome Reception
Day 3
9:00–10:00
Oral session 3A Recognition + Segmentation Orals 3A:01–3A:04
9:00–10:00 (Rene Vidal)
1841Structured Forests for Fast Edge Detection
Authors:
1849Weakly Supervised Learning of Image Partitioning Using Decision Trees with Structured Split Criteria
Authors:
1857Style-Aware Mid-level Representation for Discovering Visual Connections in Space and Time
Authors:
1865Coarse-to-Fine Semantic Video Segmentation Using Supervoxel Trees
Authors:
10:00–10:45
Spotlights (45min, 52 spotlights at 50secs each)
10:00–10:45 (Kyoung Mu Lee)
10:45–12:15
Poster session 3A: Posters 3A:01–3A:52
18733DNN: Viewpoint Invariant 3D Geometry Matching for Scene Understanding
Authors:
1881Local Signal Equalization for Correspondence Matching
Authors:
1888Monocular Image 3D Human Pose Estimation under Self-Occlusion
Authors:
1896Multi-view 3D Reconstruction from Uncalibrated Radially-Symmetric Cameras
Authors:
1904Corrected-Moment Illuminant Estimation
Authors:
1912Target-Driven Moire Pattern Synthesis by Phase Modulation
Authors:
1920Anchored Neighborhood Regression for Fast Example-Based Super-Resolution
Authors:
1928Multi-scale Topological Features for Hand Posture Representation and Analysis
Authors:
1936Sieving Regression Forest Votes for Facial Feature Detection in the Wild
Authors:
1944Pose-Free Facial Landmark Fitting via Optimized Part Mixtures and Cascaded Deformable Shape Model
Authors:
1952Markov Network-Based Unified Classifier for Face Identification
Authors:
1960Fast High Dimensional Vector Multiplication Face Recognition
Authors:
1968A Generalized Low-Rank Appearance Model for Spatio-temporally Correlated Rain Streaks
Authors:
1976Salient Region Detection by UFO: Uniqueness, Focusness and Objectness
Authors:
1984Estimating the Material Properties of Fabric from Video
Authors:
1992Multiple Non-rigid Surface Detection and Registration
Authors:
2000Discriminative Label Propagation for Multi-object Tracking with Sporadic Appearance Features
Authors:
2008Online Motion Segmentation Using Dynamic Label Propagation
Authors:
2016A Unified Rolling Shutter and Motion Blur Model for 3D Visual Registration
Authors:
2024Shortest Paths with Curvature and Torsion
Authors:
2032Bounded Labeling Function for Global Segmentation of Multi-part Objects with Geometric Constraints
Authors:
2040Randomized Ensemble Tracking
Authors:
2048Discriminatively Trained Templates for 3D Object Detection: A Real Time Scalable Approach
Authors:
2056Joint Deep Learning for Pedestrian Detection
Authors:
2064Detecting Avocados to Zucchinis: What Have We Done, and Where Are We Going?
Authors:
2072Ensemble Projection for Semi-supervised Image Classification
Authors:
2080Latent Task Adaptation with Large-Scale Hierarchies
Authors:
2088Learning Coupled Feature Spaces for Cross-Modal Matching
Authors:
2096CoDeL: A Human Co-detection and Labeling Framework
Authors:
2104How Related Exemplars Help Complex Event Detection in Web Videos?
Authors:
2112Pose Estimation and Segmentation of People in 3D Movies
Authors:
2120A Unified Probabilistic Approach Modeling Relationships between Attributes and Objects
Authors:
2128Fast Neighborhood Graph Search Using Cartesian Concatenation
Authors:
2136Codemaps - Segment, Classify and Search Objects Locally
Authors:
2144Support Surface Prediction in Indoor Scenes
Authors:
2152Incorporating Cloud Distribution in Sky Representation
Authors:
2160Spoken Attributes: Mixing Binary and Relative Attributes to Say the Right Thing
Authors:
2168Image Segmentation with Cascaded Hierarchical Models and Logistic Disjunctive Normal Networks
Authors:
2176Semantic Segmentation without Annotating Segments
Authors:
2184Progressive Multigrid Eigensolvers for Multiscale Spectral Segmentation
Authors:
2192Video Segmentation by Tracking Many Figure-Ground Segments
Authors:
2200Transfer Feature Learning with Joint Distribution Adaptation
Authors:
2208Manifold Based Face Synthesis from Sparse Samples
Authors:
2216Robust Dictionary Learning by Error Source Decomposition
Authors:
2224Inferring "Dark Matter" and "Dark Energy" from Videos
Authors:
2232Video Co-segmentation for Meaningful Action Extraction
Authors:
2240Flattening Supervoxel Hierarchies by the Uniform Entropy Slice
Authors:
2248From Actemes to Action: A Strongly-Supervised Representation for Detailed Action Understanding
Authors:
2256From Semi-supervised to Transfer Counting of Crowds
Authors:
2264Learning to Share Latent Tasks for Action Recognition
Authors:
2272Large-Scale Video Hashing via Structure Learning
Authors:
2280Finding Actors and Actions in Movies
Authors:
12:15–14:15
Lunch
14:15–15:00
Oral session 3B (3 papers, 45mins) Motion and Tracking Orals 3B:01–3B:03
14:15–15:00 (Michal Irani)
2288Hierarchical Data-Driven Descent for Efficient Optimal Deformation Estimation
Authors:
2296Orderless Tracking through Model-Averaged Posterior Estimation
Authors:
2304The Way They Move: Tracking Multiple Targets with Similar Appearance
Authors:
15:00–15:45
Spotlights (45mins)
15:00–15:45 (Tinne Tuytelaars)
15:45–16:15
Break (30mins)
16:15–17:15
Oral session 3C Optimization Orals 3C:01–3C:04
16:15–17:15 (Ramin Zabih)
2312Active MAP Inference in CRFs for Efficient Semantic Segmentation
Authors:
2320Potts Model, Parametric Maxflow and K-Submodular Functions
Authors:
2328Proportion Priors for Image Sequence Segmentation
Authors:
2336Tree Shape Priors with Connectivity Constraints Using Convex Relaxation on General Graphs
Authors:
17:15–18:45
Poster session 3B: Posters 3B:01–3B:52
2344Revisiting the PnP Problem: A Fast, General and Optimal Solution
Authors:
2352Direct Optimization of Frame-to-Frame Rotation
Authors:
2360PM-Huber: PatchMatch with Huber Regularization for Stereo Matching
Authors:
2368Extrinsic Camera Calibration without a Direct View Using Spherical Mirror
Authors:
2376Robust Non-parametric Data Fitting for Correspondence Modeling
Authors:
2384Deblurring by Example Using Dense Correspondence
Authors:
2392On One-Shot Similarity Kernels: Explicit Feature Maps and Properties
Authors:
2400Facial Action Unit Event Detection by Cascade of Tasks
Authors:
2408Similarity Metric Learning for Face Recognition
Authors:
2416Random Faces Guided Sparse Many-to-One Encoder for Pose-Invariant Face Recognition
Authors:
2424Breaking the Chain: Liberation from the Temporal Markov Assumption for Tracking Human Poses
Authors:
2432Exploiting Reflection Change for Automatic Reflection Removal
Authors:
2440Shape Index Descriptors Applied to Texture-Based Galaxy Analysis
Authors:
2448Robust Tucker Tensor Decomposition for Effective Image Representation
Authors:
2456Interactive Markerless Articulated Hand Motion Tracking Using RGB and Depth Data
Authors:
2464Video Motion for Every Visible Point
Authors:
2472EVSAC: Accelerating Hypotheses Generation by Modeling Matching Scores with Extreme Value Theory
Authors:
2480PixelTrack: A Fast Adaptive Algorithm for Tracking Non-rigid Objects
Authors:
2488Unifying Nuclear Norm and Bilinear Factorization Approaches for Low-Rank Matrix Decomposition
Authors:
Authors:
2504Multi-view Normal Field Integration for 3D Reconstruction of Mirroring Objects
Authors:
2512Discovering Object Functionality
Authors:
2520Bird Part Localization Using Exemplar-Based Models with Enforced Pose and Subcategory Consistency
Authors:
2528Person Re-identification by Salience Matching
Authors:
2536Prime Object Proposals with Randomized Prim's Algorithm
Authors:
Authors:
2552A General Two-Step Approach to Learning-Based Hashing
Authors:
2560Modeling Occlusion by Discriminative AND-OR Structures
Authors:
2568An Adaptive Descriptor Design for Object Recognition in the Wild
Authors:
2576Coherent Object Detection with 3D Geometric Context from a Single Image
Authors:
2584Write a Classifier: Zero-Shot Learning Using Purely Textual Descriptions
Authors:
2592Random Forests of Local Experts for Pedestrian Detection
Authors:
2600Visual Reranking through Weakly Supervised Multi-graph Learning
Authors:
2608Domain Adaptive Classification
Authors:
2616Supervised Binary Hash Code Learning with Jensen Shannon Divergence
Authors:
2624Model Recommendation with Virtual Probes for Egocentric Hand Detection
Authors:
2632Geometric Registration Based on Distortion Estimation
Authors:
2640Multi-view Object Segmentation in Space and Time
Authors:
2648Pedestrian Parsing via Deep Decompositional Network
Authors:
2656Dynamic Structured Model Selection
Authors:
2664From Point to Set: Extend the Learning of Distance Metrics
Authors:
2672Class-Specific Simplex-Latent Dirichlet Allocation for Image Classification
Authors:
2680Mining Motion Atoms and Phrases for Complex Action Recognition
Authors:
2688Learning Maximum Margin Temporal Warping for Action Recognition
Authors:
2696Combining the Right Features for Complex Event Recognition
Authors:
2704Space-Time Robust Representation for Action Recognition
Authors:
Authors:
2720Abnormal Event Detection at 150 FPS in MATLAB
Authors:
2728Dynamic Pooling for Complex Event Recognition
Authors:
2736Relative Attributes for Large-Scale Abandoned Object Detection
Authors:
2744Action Recognition and Localization by Hierarchical Space-Time Segments
Authors:
Authors:
Day 4
9:00–10:00
Oral session 4A Recognition Orals 4A:01–4A:04
9:00–10:00 (Kristen Graumann)
2760Beyond Hard Negative Mining: Efficient Detector Learning via Block-Circulant Decomposition
Authors:
2768From Large Scale Image Categorization to Entry-Level Categories
Authors:
2776Fast Subspace Search via Grassmannian Based Hashing
Authors:
Authors:
10:00–10:45
Spotlights (45min, 52 spotlights at 50secs each)
10:00–10:45 (Josef Sivic)
10:45–12:15
Poster session 4A: Posters 4A:01–4A:52
2792Line Assisted Light Field Triangulation and Stereo Matching
Authors:
2800A Flexible Scene Representation for 3D Reconstruction Using an RGB-D Camera
Authors:
2808Automatic Registration of RGB-D Scans via Salient Directions
Authors:
2816Real-Time Solution to the Absolute Pose Problem with Unknown Radial Distortion and Focal Length
Authors:
2824Rectangling Stereographic Projection for Wide-Angle Image Visualization
Authors:
2832Accurate Blur Models vs. Image Priors in Single Image Super-resolution
Authors:
2840Learning Slow Features for Behaviour Analysis
Authors:
2848Fast Face Detector Training Using Tailored Views
Authors:
2856Simultaneous Clustering and Tracklet Linking for Multi-face Tracking in Videos
Authors:
2864A Deep Sum-Product Architecture for Robust Facial Attributes Analysis
Authors:
2872Hidden Factor Analysis for Age Invariant Face Recognition
Authors:
2880A Learning-Based Approach to Reduce JPEG Artifacts in Image Matting
Authors:
2888A New Image Quality Metric for Image Auto-denoising
Authors:
2896Joint Noise Level Estimation from Personal Photo Collections
Authors:
2904Latent Data Association: Bayesian Model Selection for Multi-target Tracking
Authors:
2912Initialization-Insensitive Visual Tracking through Voting with Salient Local Features
Authors:
2920Pose-Configurable Generic Tracking of Elongated Objects
Authors:
Authors:
2936Partial Enumeration and Curvature Regularization
Authors:
2944Total Variation Regularization for Functions with Values in a Manifold
Authors:
2952Matching Dry to Wet Materials
Authors:
2960Unsupervised Visual Domain Adaptation Using Subspace Alignment
Authors:
2968Segmentation Driven Object Detection with Fisher Vectors
Authors:
2976Saliency Detection via Dense and Sparse Reconstruction
Authors:
2984Bayesian Joint Topic Modelling for Weakly Supervised Object Localisation
Authors:
2992Parsing IKEA Objects: Fine Pose Estimation
Authors:
3000Active Visual Recognition with Expertise Estimation in Crowdsourcing
Authors:
Authors:
3016Training Deformable Part Models with Decorrelated Features
Authors:
Authors:
3032Learning Hash Codes with Listwise Supervision
Authors:
3040Image Retrieval Using Textual Cues
Authors:
3048Scene Collaging: Analysis and Synthesis of Natural Images with Semantic Layers
Authors:
3056Understanding High-Level Semantics by Modeling Traffic Patterns
Authors:
3064Efficient 3D Scene Labeling Using Fields of Trees
Authors:
3072Multi-channel Correlation Filters
Authors:
3080Learning CRFs for Image Parsing with Adaptive Subgradient Descent
Authors:
3088Robust Trajectory Clustering for Motion Segmentation
Authors:
3096Robust Subspace Clustering via Half-Quadratic Minimization
Authors:
3104Structured Learning of Sum-of-Submodular Higher Order Energy Functions
Authors:
3112Joint Learning of Discriminative Prototypes and Large Margin Nearest Neighbor Classifiers
Authors:
3120Dictionary Learning and Sparse Coding on Grassmann Manifolds: An Extrinsic Solution
Authors:
3128Latent Multitask Learning for View-Invariant Action Recognition
Authors:
3136Concurrent Action Detection with Structural Prediction
Authors:
3144Recognising Human-Object Interaction via Exemplar Based Modelling
Authors:
3152Human Re-identification by Matching Compositional Template with Cluster Sampling
Authors:
Authors:
3168Directed Acyclic Graph Kernels for Action Recognition
Authors:
3176Learning View-Invariant Sparse Representations for Cross-View Action Recognition
Authors:
3184Event Detection in Complex Scenes Using Interval Temporal Constraints
Authors:
3192Towards Understanding Action Recognition
Authors:
3200Modifying the Memorability of Face Photographs
Authors:
12:15–13:45
Lunch
13:45–14:45
Keynote Speech
14:45–15:15
Break
15:15–16:15
Oral session 4B Orals 4B:01–4B:04
15:15–16:15 (Serge Belongie)
3208A Practical Transfer Learning Algorithm for Face Verification
Authors:
3216Learning to Predict Gaze in Egocentric Video
Authors:
3224Real-Time Articulated Hand Pose Estimation Using Semi-supervised Transductive Regression Forests
Authors:
3232Semantically-Based Human Scanpath Estimation with HMMs
Authors:
16:15–17:00
Spotlights (45mins)
16:15–17:00 (Hongdong Li)
17:00–18:30
Poster session 4B: Posters 4B:01–4B:50
3240Enhanced Continuous Tabu Search for Parameter Estimation in Multiview Geometry
Authors:
3248Global Fusion of Relative Motions for Robust, Accurate and Scalable Structure from Motion
Authors:
3256Internet Based Morphable Model
Authors:
3264Large-Scale Multi-resolution Surface Reconstruction from RGB-D Sequences
Authors:
3272Modeling 4D Human-Object Interactions for Event and Object Recognition
Authors:
Authors:
3288Face Recognition Using Face Patch Networks
Authors:
3296Coupling Alignments with Recognition for Still-to-Video Face Recognition
Authors:
3304Capturing Global Semantic Relationships for Facial Action Unit Recognition
Authors:
3312Estimating Human Pose with Flowing Puppets
Authors:
3320Illuminant Chromaticity from Image Sequences
Authors:
3328Contextual Hypergraph Modeling for Salient Object Detection
Authors:
3336Super-resolution via Transform-Invariant Group-Sparse Regularization
Authors:
3344Optical Flow via Locally Adaptive Fusion of Complementary Data Costs
Authors:
3352Optimal Orthogonal Basis and Image Assimilation: Motion Modeling
Authors:
Authors:
3368Bayesian 3D Tracking from Monocular Video
Authors:
3376GOSUS: Grassmannian Online Subspace Updates with Structured-Sparsity
Authors:
3384Fast Sparsity-Based Orthogonal Dictionary Learning for Image Restoration
Authors:
3392Data-Driven 3D Primitives for Single Image Understanding
Authors:
3400Learning Discriminative Part Detectors for Image Classification and Cosegmentation
Authors:
3408A Deformable Mixture Parsing Model with Parselets
Authors:
Authors:
3424Improving Graph Matching via Density Maximization
Authors:
3432Attribute Adaptation for Personalized Image Search
Authors:
3440Feature Weighting via Optimal Thresholding for Video Analysis
Authors:
3448Volumetric Semantic Segmentation Using Pyramid Context Features
Authors:
3456Efficient Hand Pose Estimation from a Single Depth Image
Authors:
3463Synergistic Clustering of Image and Segment Descriptors for Unsupervised Scene Understanding
Authors:
3471Random Grids: Fast Approximate Nearest Neighbors and Range Searching for Image Search
Authors:
3479Discovering Details and Scene Structure with Hierarchical Iconoid Shift
Authors:
3487Strong Appearance and Expressive Spatial Models for Human Pose Estimation
Authors:
34953D Sub-query Expansion for Improving Sketch-Based Multi-view Image Retrieval
Authors:
3503Predicting Primary Gaze Behavior Using Social Saliency Fields
Authors:
3511Efficient Higher-Order Clustering on the Grassmann Manifold
Authors:
3519Paper Doll Parsing: Retrieving Similar Styles to Parse Clothing Items
Authors:
3527A Unified Video Segmentation Benchmark: Annotation, Metrics and Analysis
Authors:
Authors:
3543Distributed Low-Rank Subspace Segmentation
Authors:
3551Action Recognition with Improved Trajectories
Authors:
3559Action Recognition with Actons
Authors:
Authors:
3575Finding Causal Interactions in Video Sequences
Authors:
3583A New Adaptive Segmental Matching Measure for Human Activity Recognition
Authors:
3591Saliency Detection in Large Point Sets
Authors:
3599Motion-Aware KNN Laplacian for Video Matting
Authors:
3607Viewing Real-World Faces in 3D
Authors:
3615Accurate and Robust 3D Facial Capture Using a Single RGBD Camera
Authors:
3623Visual Semantic Complex Network for Web Images
Authors:
3631What Do You Do? Occupation Recognition in a Photo via Social Context
Authors: