Computer Vision -- ECCV 2012. Workshops and Demonstrations Florence, Italy, October 7-13, 2012, Proceedings, Part III

The three volume set LNCS 7583, 7584 and 7585 comprises the Workshops and Demonstrations which took place in connection with the European Conference on Computer Vision, ECCV 2012, held in Firenze, Italy, in October 2012. The total of 179 workshop papers and 23 demonstration papers was carefully reviewed and selected for inclusion in the proceedings. They where held at workshops with the following themes: non-rigid shape analysis and deformable image alignment; visual analysis and geo-localization of large-scale imagery; Web-scale vision and social media; video event categorization, tagging and retrieval; re-identification; biological and computer vision interfaces; where computer vision meets art; consumer depth cameras for computer vision; unsolved problems in optical flow and stereo estimation; what's in a face?; color and photometry in computer vision; computer vision in vehicle technology: from earth to mars; parts and attributes; analysis and retrieval of tracked events and motion in imagery streams; action recognition and pose estimation in still images; higher-order models and global constraints in computer vision; information fusion in computer vision for concept recognition; 2.5D sensing technologies in motion: the quest for 3D; benchmarking facial image analysis technologies.

Pixels, Stixels, and Objects.- Fast Stixel Computation for Fast Pedestrian Detection.- Second Workshop on Parts and Attributes Discovering a Lexicon of Parts and Attributes.- How Important Are “Deformable Parts” in the Deformable Parts Model? .- Bounding Part Scores for Rapid Detection with Deformable Part Models.- Learning Compact Visual Attributes for Large-Scale Image Classification.- Unsupervised Learning of Discriminative Relative Visual Attributes.- Retrieval of Tracked Events and Motion in Imagery Streams (ARTEMIS 2012) A Method for Online Analysis of Structured Processes Using Bayesian Filters and Echo State Networks.- Monocular Camera Fall Detection System Exploiting 3D Measures: A Semi-supervised Learning Approach.- Person Identification Using Full-Body Motion and Anthropometric Biometrics from Kinect Videos.- Spatio-temporal Video Representation with Locality-Constrained Linear Coding.- Real Time Detection of Social Interactions in Surveillance Video.- Towards Space-Time Semantics in Two Frames.- SuperFloxels: A Mid-level Representation for Video Sequences.- Relative Camera Localisation in Non-overlapping Camera Networks Using Multiple Trajectories.- Detecting Interesting Events Using Unsupervised Density Ratio Estimation.- Destination Flow for Crowd Simulation.- 3D Rotation Invariant Decomposition of Motion Signals.- Learn to Move: Activity Specific Motion Models for Tracking by Detection.- Flow Counting Using Realboosted Multi-sized Window Detectors.- Dynamic Markov Random Field Model for Visual Tracking.- Mode Seeking with an Adaptive Distance Measure.- Constrained Clustering with Local Constraint Propagation.- Occlusion Handling in Video Segmentation via Predictive Feedback.- Pose Estimation in Still Images Collective Activity Localization with Contextual Spatial Pyramid.- Viewpoint Invariant Collective Activity Recognition with Relative Action Context.- On Recognizing Actions in Still Images via Multiple Features.- Higher-Order Models and Global Constraints in Computer Vision Tighter Relaxations for Higher-Order Models Based on Generalized Roof Duality.- Approximate Envelope Minimization for Curvature Regularity.- Byung-soo Kim, Min Sun, Pushmeet Kohli, and Silvio Savarese Submodular Relaxation for MRFs with High-Order Potentials.- Adjacency Matrix Construction Using Sparse Coding for Label Propagation.- Climbing: A Unified Approach for Global Constraints on Hierarchical Segmentation.- Information Fusion in Computer Vision for Concept Recognition Hierarchical Late Fusion for Concept Detection in Videos.- Fast and Adaptive Deep Fusion Learning for Detecting Visual Objects.- Hybrid Pooling Fusion in the BoW Pipeline.- Joint Sparsity-Based Robust Multimodal Biometrics Recognition.- GPS-Based Multi-viewpoint Integration for Anticipative Scene Analysis.- Fusion of Speech, Faces and Text for Person Identification in TV Broadcast.- Explicit Performance Metric Optimization for Fusion-Based Video Retrieval.- Unsupervised Classemes.- A Benchmarking Campaign for the Multimodal Detection of Violent Scenes in Movies.- A Selective Weighted Late Fusion for Visual Concept Recognition.- Fusion of Multiple Visual Cues for Visual Saliency Extraction from Wearable Camera Settings with Strong Motion.- Enhancing Semantic Features with Compositional Analysis for Scene Recognition.- Object Reading: Text Recognition for Object Recognition.- Bayesian Multimodal Fusion in Forensic Applications.- 2.5D Sensing Technologies in Motion: The Quest for 3D (QU3ST) Noise Modelling and Uncertainty Propagation for TOF Sensors.- Single Color One-Shot Scan Using Topology Information.- View Planning Approach for Automatic 3D Digitization of Unknown Objects.- Depth Enhancement by Fusion for Passive and Active Sensing.- 2.1 Depth Estimation of Frames in Image Sequences Using Motion Occlusions.- Joint Spatio-temporal Depth Features Fusion Framework for 3D Structure Estimation in Urban Environment.- A Virtual Environment Tool for Benchmarking Face Analysis Systems.- An Open Source Framework for Standardized Comparisons of Face Recognition Algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 547 Manuel G¨unther, Roy Wallace, and S´ebastien Marcel Adaptive Registration for Occlusion Robust 3D Face Recognition . . . . . . 557 Nese Alyuz, Berk Gokberk, and Lale Akarun Robust and Computationally Efficient Face Detection Using Gaussian Derivative Features of Higher Orders.- Multi-view Facial Expression Recognition Analysis with Generic Sparse Coding Feature . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 578 Usman Tariq, Jianchao Yang, and Thomas S. Huang ECCV Demonstrations Real-Time Image Registration of RGB Webcams and Colorless 3D Time-of-Flight Cameras.- Technical Demonstration on Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes.- FaceHugger: The ALIEN Tracker Applied to Faces.- INTAIRACT: Joint Hand Gesture and Fingertip Classification for Touchless Interaction.- Fast and Precise Template Matching Based on Oriented Gradients.- Object Categorization Based on a Supervised Mean Shift Algorithm.- 3D Gesture Touchless Control Based on Real-Time Stereo Matching.- A Real-Time Scene Text to Speech System.- Face-Based Illuminant Estimation.- Object-Layout-Aware Image Retrieval for Personal Album Management.- A Human vs. Machine Challenge in Fashion Color Classification.- Understanding Road Scenes Using Visual Cues and GPS Information.- The Leiden Augmented Reality System (LARS).- Prosemantic Image Retrieval.- LZM in Action: Realtime Face Recognition System.- Using 3D Models for Real-Time Facial Feature Tracking, Pose Estimation, and Expression Monitoring.- Instant Scene Recognition on Mobile Platform.- Adasens Advanced Driver Assistance Systems Live Demo.- Real-Time 3D Motion Capture by Monocular Vision and Virtual Rendering.- A Tai Chi Training System Based on Fast Skeleton Matching Algorithm.- Emotion Mirror: A Novel Intervention for Autism Based on Real-Time Expression Recognition.- Unsupervised Activity Analysis and Monitoring Algorithms for Effective Surveillance Systems.