Bibliothèque de L'IMIST/CNRST

All-In-Focus Synthetic Aperture Imaging -- Photo Uncrop -- Solving Square Jigsaw Puzzles with Loop Constraints -- Geometric Calibration of Micro-Lens-Based Light-Field Cameras Using Line Features -- Spatio-temporal Matching for Human Detection in Video -- Collaborative Facial Landmark Localization for Transferring Annotations Across Datasets -- Facial Landmark Detection by Deep Multi-task Learning -- Joint Cascade Face Detection and Alignment -- Weighted Block-Sparse Low Rank Representation for Face Clustering in Videos -- Crowd Tracking with Dynamic Evolution of Group Structures -- Tracking Using Multilevel Quantizations -- Occlusion and Motion Reasoning for Long-Term Tracking -- MEEM: Robust Tracking via Multiple Experts Using Entropy Minimization -- Robust Motion Segmentation with Unknown Correspondences -- Monocular Multiview Object Tracking with 3D Aspect Parts -- Modeling Blurred Video with Layers -- Efficient Image and Video Co-localization with Frank-Wolfe Algorithm -- Non-parametric Higher-Order Random Fields for Image Segmentation -- Co-Sparse Textural Similarity for Interactive Segmentation -- A Convergent Incoherent Dictionary Learning Algorithm for Sparse Coding -- Free-Shape Polygonal Object Localization -- Interactively Guiding Semi-Supervised Clustering via Attribute-Based Explanations -- Attributes Make Sense on Segmented Objects -- Towards Transparent Systems: Semantic Characterization of Failure Modes -- Orientation Covariant Aggregation of Local Descriptors with Embeddings -- Similarity-Invariant Sketch-Based Image Retrieval in Large Databases -- Discovering Object Classes from Activities -- Weakly Supervised Object Localization with Latent Category Learning -- Food-101 – Mining Discriminative Components with Random Forests -- Latent-Class Hough Forests for 3D Object Detection and Pose Estimation -- FPM: Fine Pose Parts-Based Model with 3D CAD Models -- Learning High-Level Judgments of Urban Perception -- CollageParsing: Nonparametric Scene Parsing by Adaptive Overlapping Windows -- Discovering Video Clusters from Visual Features and Noisy Tags -- Category-Specific Video Summarization -- Assessing the Quality of Actions -- HiRF: Hierarchical Random Field for Collective Activity Recognition in Videos -- Part Bricolage: Flow-Assisted Part-Based Graphs for Detecting Activities in Videos -- GIS-Assisted Object Detection and Geospatial Localization -- Context-Based Pedestrian Path Prediction -- Sliding Shapes for 3D Object Detection in Depth Images -- Integrating Context and Occlusion for Car Detection by Hierarchical And-Or Model -- PanoContext: A Whole-Room 3D Context Model for Panoramic Scene Understanding -- Unfolding an Indoor Origami World -- Joint Semantic Segmentation and 3D Reconstruction from Monocular Video -- A New Variational Framework for Multiview Surface Reconstruction -- Multi-body Depth-Map Fusion with Non-intersection Constraints -- Shape from Light Field Meets Robust PCA -- Cross-Age Reference Coding for Age-Invariant Face Recognition and Retrieval -- Reverse Training: An Efficient Approach for Image Set Classification -- Real-Time Exemplar-Based Face Sketch Synthesis -- Domain-Adaptive Discriminative One-Shot Learning of Gestures.

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.