Computer Vision -- Eccv 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part Iii (lecture Notes In Computer Science)

The seven-volume set comprising LNCS volumes 8689-8695 constitutes the refereed proceedings of the 13th European Conference on Computer Vision, ECCV 2014, held in Zurich, Switzerland, in September 2014. The 363 revised papers presented were carefully reviewed and selected from 1444 submissions. The papers are organized in topical sections on tracking and activity recognition; recognition; learning and inference; structure from motion and feature matching; computational photography and low-level vision; vision; segmentation and saliency; context and 3D scenes; motion and 3D scene analysis; and poster sessions. Front Matter....Pages - The 3D Jigsaw Puzzle: Mapping Large Indoor Spaces....Pages 1-16 Pipe-Run Extraction and Reconstruction from Point Clouds....Pages 17-30 Image-Based 4-d Reconstruction Using 3-d Change Detection....Pages 31-45 VocMatch: Efficient Multiview Correspondence for Structure from Motion....Pages 46-60 Robust Global Translations with 1DSfM....Pages 61-75 Comparing Salient Object Detection Results without Ground Truth....Pages 76-91 RGBD Salient Object Detection: A Benchmark and Algorithms....Pages 92-109 Saliency Detection with Flash and No-flash Image Pairs....Pages 110-124 Alpha Matting of Motion-Blurred Objects in Bracket Sequence Images....Pages 125-139 An Active Patch Model for Real World Texture and Appearance Classification....Pages 140-155 Material Classification Based on Training Data Synthesized Using a BTF Database....Pages 156-171 Déjà Vu:....Pages 172-187 Transfer Learning Based Visual Tracking with Gaussian Processes Regression....Pages 188-203 Separable Spatiotemporal Priors for Convex Reconstruction of Time-Varying 3D Point Clouds....Pages 204-219 Highly Overparameterized Optical Flow Using PatchMatch Belief Propagation....Pages 220-234 Local Estimation of High Velocity Optical Flow with Correlation Image Sensor....Pages 235-249 Rank Minimization with Structured Data Patterns....Pages 250-265 Duality and the Continuous Graphical Model....Pages 266-281 Spectral Clustering with a Convex Regularizer on Millions of Images....Pages 282-298 Riemannian Sparse Coding for Positive Definite Matrices....Pages 299-314 Robust Sparse Coding and Compressed Sensing with the Difference Map....Pages 315-329 Object Co-detection via Efficient Inference in a Fully-Connected CRF....Pages 330-345 Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition....Pages 346-361 Context as Supervisory Signal: Discovering Objects with Predictable Context....Pages 362-377 Learning to Hash with Partial Tags: Exploring Correlation between Tags and Hashing Bits for Large Scale Image Retrieval....Pages 378-392 Multi-class Open Set Recognition Using Probability of Inclusion....Pages 393-409 Sequential Max-Margin Event Detectors....Pages 410-424 Which Looks Like Which: Exploring Inter-class Relationships in Fine-Grained Visual Categorization....Pages 425-440 Object Detection and Viewpoint Estimation with Auto-masking Neural Network....Pages 441-455 Statistical and Spatial Consensus Collection for Detector Adaptation....Pages 456-471 Deep Learning of Scene-Specific Classifier for Pedestrian Detection....Pages 472-487 A Contour Completion Model for Augmenting Surface Reconstructions....Pages 488-503 Interactive Object Counting....Pages 504-518 Recognizing City Identity via Attribute Analysis of Geo-tagged Images....Pages 519-534 A Fast and Simple Algorithm for Producing Candidate Regions....Pages 535-549 Closed-Form Approximate CRF Training for Scalable Image Segmentation....Pages 550-565 A Graph Theoretic Approach for Object Shape Representation in Compositional Hierarchies Using a Hybrid Generative-Descriptive Model....Pages 566-581 Finding Approximate Convex Shapes in RGBD Images....Pages 582-596 ShapeForest: Building Constrained Statistical Shape Models with Decision Trees....Pages 597-612 Optimizing Ranking Measures for Compact Binary Code Learning....Pages 613-627 Exploiting Low-Rank Structure from Latent Domains for Domain Generalization....Pages 628-643 Sparse Additive Subspace Clustering....Pages 644-659 Boosting VLAD with Supervised Dictionary Learning and High-Order Statistics....Pages 660-674 Recognizing Complex Events in Videos by Learning Key Static-Dynamic Evidences....Pages 675-688 A Hierarchical Representation for Future Action Prediction....Pages 689-704 Continuous Learning of Human Activity Models Using Deep Nets....Pages 705-720 DaMN – Discriminative and Mutually Nearest: Exploiting Pairwise Category Proximity for Video Action Recognition....Pages 721-736 Spatio-temporal Object Detection Proposals....Pages 737-752 Depth-of-Field and Coded Aperture Imaging on XSlit Lens....Pages 753-766 Refraction Wiggles for Measuring Fluid Depth and Velocity from Video....Pages 767-782 Blind Deblurring Using Internal Patch Recurrence....Pages 783-798 Crisp Boundary Detection Using Pointwise Mutual Information....Pages 799-814 Rolling Guidance Filter....Pages 815-830 Physically Grounded Spatio-temporal Object Affordances....Pages 831-847 Back Matter....Pages -