Computer Vision -- ECCV 2014

The 3D Jigsaw Puzzle: Mapping Large Indoor Spaces.- Pipe-Run Extraction and Reconstruction from Point Clouds.- Image-Based 4-d Reconstruction Using 3-d Change Detection.- VocMatch: Efficient Multiview Correspondence for Structure from Motion.- Robust Global Translations with 1DSfM.- Comparing Salient Object Detection Results without Ground Truth.- RGBD Salient Object Detection: A Benchmark and Algorithms.- Saliency Detection with Flash and No-flash Image Pairs.- Alpha Matting of Motion-Blurred Objects in Bracket Sequence Images.- An Active Patch Model for Real World Texture and Appearance Classification.- Material Classification Based on Training Data Synthesized Using a BTF Database.- Deja Vu: Motion Prediction in Static Images.- Transfer Learning Based Visual Tracking with Gaussian Processes Regression.- Separable Spatiotemporal Priors for Convex Reconstruction of Time-Varying 3D Point Clouds.- Highly Overparameterized Optical Flow Using PatchMatch Belief Propagation.- Local Estimation of High Velocity Optical Flow with Correlation Image Sensor.- Rank Minimization with Structured Data Patterns.- Duality and the Continuous Graphical Model.- Spectral Clustering with a Convex Regularizer on Millions of Images.- Riemannian Sparse Coding for Positive Definite Matrices.- Robust Sparse Coding and Compressed Sensing with the Difference Map.- Object Co-detection via Efficient Inference in a Fully-Connected CRF.- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition.- Context as Supervisory Signal: Discovering Objects with Predictable Context.- Learning to Hash with Partial Tags: Exploring Correlation between Tags and Hashing Bits for Large Scale Image Retrieval.- Multi-class Open Set Recognition Using Probability of Inclusion.- Sequential Max-Margin Event Detectors.- Which Looks Like Which: Exploring Inter-class Relationships in Fine-Grained Visual Categorization.- Object Detection and Viewpoint Estimation with Auto-masking Neural Network.- Statistical and Spatial Consensus Collection for Detector Adaptation.- Deep Learning of Scene-Specific Classifier for Pedestrian Detection.- A Contour Completion Model for Augmenting Surface Reconstructions.- Interactive Object Counting.- Recognizing City Identity via Attribute Analysis of Geo-tagged Images.- A Fast and Simple Algorithm for Producing Candidate Regions.- Closed-Form Approximate CRF Training for Scalable Image Segmentation.- A Graph Theoretic Approach for Object Shape Representation in Compositional Hierarchies Using a Hybrid Generative-Descriptive Model.- Finding Approximate Convex Shapes in RGBD Images.- ShapeForest: Building Constrained Statistical Shape Models with Decision Trees.- Optimizing Ranking Measures for Compact Binary Code Learning.- Exploiting Low-Rank Structure from Latent Domains for Domain Generalization.- Sparse Additive Subspace Clustering.- Boosting VLAD with Supervised Dictionary Learning and High-Order Statistics.- Recognizing Complex Events in Videos by Learning Key Static-Dynamic Evidences.- A Hierarchical Representation for Future Action Prediction.- Continuous Learning of Human Activity Models Using Deep Nets.- DaMN - Discriminative and Mutually Nearest: Exploiting Pairwise Category Proximity for Video Action Recognition.- Spatio-temporal Object Detection Proposals.- Depth-of-Field and Coded Aperture Imaging on XSlit Lens.- Refraction Wiggles for Measuring Fluid Depth and Velocity from Video.- Blind Deblurring Using Internal Patch Recurrence.- Crisp Boundary Detection Using Pointwise Mutual Information.- Physically Grounded Spatio-temporal Object Affordances.