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

Front Matter....Pages -
Pixels, Stixels, and Objects....Pages 1-10
Fast Stixel Computation for Fast Pedestrian Detection....Pages 11-20
Discovering a Lexicon of Parts and Attributes....Pages 21-30
How Important Are “Deformable Parts” in the Deformable Parts Model?....Pages 31-40
Bounding Part Scores for Rapid Detection with Deformable Part Models....Pages 41-50
Learning Compact Visual Attributes for Large-Scale Image Classification....Pages 51-60
Unsupervised Learning of Discriminative Relative Visual Attributes....Pages 61-70
A Method for Online Analysis of Structured Processes Using Bayesian Filters and Echo State Networks....Pages 71-80
Monocular Camera Fall Detection System Exploiting 3D Measures: A Semi-supervised Learning Approach....Pages 81-90
Person Identification Using Full-Body Motion and Anthropometric Biometrics from Kinect Videos....Pages 91-100
Spatio-temporal Video Representation with Locality-Constrained Linear Coding....Pages 101-110
Real Time Detection of Social Interactions in Surveillance Video....Pages 111-120
Towards Space-Time Semantics in Two Frames....Pages 121-130
SuperFloxels: A Mid-level Representation for Video Sequences....Pages 131-140
Relative Camera Localisation in Non-overlapping Camera Networks Using Multiple Trajectories....Pages 141-150
Detecting Interesting Events Using Unsupervised Density Ratio Estimation....Pages 151-161
Destination Flow for Crowd Simulation....Pages 162-171
3D Rotation Invariant Decomposition of Motion Signals....Pages 172-182
Learn to Move: Activity Specific Motion Models for Tracking by Detection....Pages 183-192
Flow Counting Using Realboosted Multi-sized Window Detectors....Pages 193-202
Dynamic Markov Random Field Model for Visual Tracking....Pages 203-212
Mode Seeking with an Adaptive Distance Measure....Pages 213-222
Constrained Clustering with Local Constraint Propagation....Pages 223-232
Occlusion Handling in Video Segmentation via Predictive Feedback....Pages 233-242
Collective Activity Localization with Contextual Spatial Pyramid....Pages 243-252
Viewpoint Invariant Collective Activity Recognition with Relative Action Context....Pages 253-262
On Recognizing Actions in Still Images via Multiple Features....Pages 263-272
Tighter Relaxations for Higher-Order Models Based on Generalized Roof Duality....Pages 273-282
Approximate Envelope Minimization for Curvature Regularity....Pages 283-292
Relating Things and Stuff by High-Order Potential Modeling....Pages 293-304
Submodular Relaxation for MRFs with High-Order Potentials....Pages 305-314
Adjacency Matrix Construction Using Sparse Coding for Label Propagation....Pages 315-323
Climbing: A Unified Approach for Global Constraints on Hierarchical Segmentation....Pages 324-334
Hierarchical Late Fusion for Concept Detection in Videos....Pages 335-344
Fast and Adaptive Deep Fusion Learning for Detecting Visual Objects....Pages 345-354
Hybrid Pooling Fusion in the BoW Pipeline....Pages 355-364
Joint Sparsity-Based Robust Multimodal Biometrics Recognition....Pages 365-374
GPS-Based Multi-viewpoint Integration for Anticipative Scene Analysis....Pages 375-384
Fusion of Speech, Faces and Text for Person Identification in TV Broadcast....Pages 385-394
Explicit Performance Metric Optimization for Fusion-Based Video Retrieval....Pages 395-405
Unsupervised Classemes....Pages 406-415
A Benchmarking Campaign for the Multimodal Detection of Violent Scenes in Movies....Pages 416-425
A Selective Weighted Late Fusion for Visual Concept Recognition....Pages 426-435
Fusion of Multiple Visual Cues for Visual Saliency Extraction from Wearable Camera Settings with Strong Motion....Pages 436-445
Enhancing Semantic Features with Compositional Analysis for Scene Recognition....Pages 446-455
Object Reading: Text Recognition for Object Recognition....Pages 456-465
Bayesian Multimodal Fusion in Forensic Applications....Pages 466-475
Noise Modelling and Uncertainty Propagation for TOF Sensors....Pages 476-485
Single Color One-Shot Scan Using Topology Information....Pages 486-495
View Planning Approach for Automatic 3D Digitization of Unknown Objects....Pages 496-505
Depth Enhancement by Fusion for Passive and Active Sensing....Pages 506-515
2.1 Depth Estimation of Frames in Image Sequences Using Motion Occlusions....Pages 516-525
Joint Spatio-temporal Depth Features Fusion Framework for 3D Structure Estimation in Urban Environment....Pages 526-535
A Virtual Environment Tool for Benchmarking Face Analysis Systems....Pages 536-546
An Open Source Framework for Standardized Comparisons of Face Recognition Algorithms....Pages 547-556
Adaptive Registration for Occlusion Robust 3D Face Recognition....Pages 557-566
Robust and Computationally Efficient Face Detection Using Gaussian Derivative Features of Higher Orders....Pages 567-577
Multi-view Facial Expression Recognition Analysis with Generic Sparse Coding Feature....Pages 578-588
Real-Time Image Registration of RGB Webcams and Colorless 3D Time-of-Flight Cameras....Pages 589-592
Technical Demonstration on Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes....Pages 593-596
FaceHugger: The ALIEN Tracker Applied to Faces....Pages 597-601
INTAIRACT: Joint Hand Gesture and Fingertip Classification for Touchless Interaction....Pages 602-606
Fast and Precise Template Matching Based on Oriented Gradients....Pages 607-610
Object Categorization Based on a Supervised Mean Shift Algorithm....Pages 611-614
3D Gesture Touchless Control Based on Real-Time Stereo Matching....Pages 615-618
A Real-Time Scene Text to Speech System....Pages 619-622
Face-Based Illuminant Estimation....Pages 623-626
Object-Layout-Aware Image Retrieval for Personal Album Management....Pages 627-630
A Human vs. Machine Challenge in Fashion Color Classification....Pages 631-634
Understanding Road Scenes Using Visual Cues and GPS Information....Pages 635-638
The Leiden Augmented Reality System (LARS)....Pages 639-642
Prosemantic Image Retrieval....Pages 643-646
LZM in Action: Realtime Face Recognition System....Pages 647-650
Using 3D Models for Real-Time Facial Feature Tracking, Pose Estimation, and Expression Monitoring....Pages 651-654
Instant Scene Recognition on Mobile Platform....Pages 655-658
Adasens Advanced Driver Assistance Systems Live Demo....Pages 659-662
Real-Time 3D Motion Capture by Monocular Vision and Virtual Rendering....Pages 663-666
A Tai Chi Training System Based on Fast Skeleton Matching Algorithm....Pages 667-670
Emotion Mirror: A Novel Intervention for Autism Based on Real-Time Expression Recognition....Pages 671-674
Unsupervised Activity Analysis and Monitoring Algorithms for Effective Surveillance Systems....Pages 675-678
Erratum: A Method for Online Analysis of Structured Processes Using Bayesian Filters and Echo State Networks....Pages E1-E1
Back Matter....Pages -