Computer Vision - ECCV 2014 : 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings

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.

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.- Déjà 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.