Computer Vision – ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part II

Front Matter....Pages I-XXIII
Front Matter....Pages 1-1
Real-Time Semantic Segmentation with Label Propagation....Pages 3-14
Front Matter....Pages 15-15
Performance Measures and a Data Set for Multi-target, Multi-camera Tracking....Pages 17-35
POI: Multiple Object Tracking with High Performance Detection and Appearance Feature....Pages 36-42
Long-Term Time-Sensitive Costs for CRF-Based Tracking by Detection....Pages 43-51
Tracking Multiple Persons Based on a Variational Bayesian Model....Pages 52-67
Multi-class Multi-object Tracking Using Changing Point Detection....Pages 68-83
Online Multi-target Tracking with Strong and Weak Detections....Pages 84-99
Multi-person Tracking by Multicut and Deep Matching....Pages 100-111
Front Matter....Pages 113-113
Visual and Human-Interpretable Feedback for Assisting Physical Activity....Pages 115-129
Mobile Mapping and Visualization of Indoor Structures to Simplify Scene Understanding and Location Awareness....Pages 130-145
Automatic Video Captioning via Multi-channel Sequential Encoding....Pages 146-161
Validation of Automated Mobility Assessment Using a Single 3D Sensor....Pages 162-177
Deep Eye-CU (DECU): Summarization of Patient Motion in the ICU....Pages 178-194
Fall Detection Based on Depth-Data in Practice....Pages 195-208
A Real-Time Vehicular Vision System to Seamlessly See-Through Cars....Pages 209-222
Solving Rendering Issues in Realistic 3D Immersion for Visual Rehabilitation....Pages 223-237
Human-Drone-Interaction: A Case Study to Investigate the Relation Between Autonomy and User Experience....Pages 238-253
Feasibility Analysis of Eye Typing with a Standard Webcam....Pages 254-268
A Technological Framework to Support Standardized Protocols for the Diagnosis and Assessment of ASD....Pages 269-284
Combining Human Body Shape and Pose Estimation for Robust Upper Body Tracking Using a Depth Sensor....Pages 285-301
Front Matter....Pages 113-113
Multi-level Net: A Visual Saliency Prediction Model....Pages 302-315
Learning and Detecting Objects with a Mobile Robot to Assist Older Adults in Their Homes....Pages 316-330
An Interactive Multimedia System for Treating Autism Spectrum Disorder....Pages 331-342
Vision-Based SLAM Navigation for Vibro-Tactile Human-Centered Indoor Guidance....Pages 343-359
Perfect Accuracy with Human-in-the-Loop Object Detection....Pages 360-374
Using Computer Vision to See....Pages 375-390
Brazilian Sign Language Recognition Using Kinect....Pages 391-402
Human Interaction Prediction Using Deep Temporal Features....Pages 403-414
Human Joint Angle Estimation and Gesture Recognition for Assistive Robotic Vision....Pages 415-431
A 3D Human Posture Approach for Activity Recognition Based on Depth Camera....Pages 432-447
ISANA: Wearable Context-Aware Indoor Assistive Navigation with Obstacle Avoidance for the Blind....Pages 448-462
An Integrated Framework for 24-hours Fire Detection....Pages 463-479
Smart Toothbrushes: Inertial Measurement Sensors Fusion with Visual Tracking....Pages 480-494
Evaluation of Infants with Spinal Muscular Atrophy Type-I Using Convolutional Neural Networks....Pages 495-507
Front Matter....Pages 509-509
The First 3D Face Alignment in the Wild (3DFAW) Challenge....Pages 511-520
3D Face Alignment Without Correspondences....Pages 521-535
Bi-Level Multi-column Convolutional Neural Networks for Facial Landmark Point Detection....Pages 536-551
Fully Automated and Highly Accurate Dense Correspondence for Facial Surfaces....Pages 552-568
Joint Face Detection and Alignment with a Deformable Hough Transform Model....Pages 569-580
3D Face Alignment in the Wild: A Landmark-Free, Nose-Based Approach....Pages 581-589
Front Matter....Pages 509-509
Fast and Precise Face Alignment and 3D Shape Reconstruction from a Single 2D Image....Pages 590-603
Shape Augmented Regression for 3D Face Alignment....Pages 604-615
Two-Stage Convolutional Part Heatmap Regression for the 1st 3D Face Alignment in the Wild (3DFAW) Challenge....Pages 616-624
Front Matter....Pages 625-625
Multi-person Pose Estimation with Local Joint-to-Person Associations....Pages 627-642
Density-Aware Pedestrian Proposal Networks for Robust People Detection in Crowded Scenes....Pages 643-654
People Counting in Videos by Fusing Temporal Cues from Spatial Context-Aware Convolutional Neural Networks....Pages 655-667
Abnormal Crowd Behavior Detection Based on Gaussian Mixture Model....Pages 668-675
Unsupervised Deep Domain Adaptation for Pedestrian Detection....Pages 676-691
Pixel Level Tracking of Multiple Targets in Crowded Environments....Pages 692-708
LCrowdV: Generating Labeled Videos for Simulation-Based Crowd Behavior Learning....Pages 709-727
Anomaly Detection and Activity Perception Using Covariance Descriptor for Trajectories....Pages 728-742
Automatic Calibration of Stationary Surveillance Cameras in the Wild....Pages 743-759
Data-Driven Motion Pattern Segmentation in a Crowded Environments....Pages 760-774
Front Matter....Pages 775-775
The Visual Object Tracking VOT2016 Challenge Results....Pages 777-823
The Thermal Infrared Visual Object Tracking VOT-TIR2016 Challenge Results....Pages 824-849
Fully-Convolutional Siamese Networks for Object Tracking....Pages 850-865
Front Matter....Pages 867-867
Speech-Driven Facial Animation Using Manifold Relevance Determination....Pages 869-882
GeThR-Net: A Generalized Temporally Hybrid Recurrent Neural Network for Multimodal Information Fusion....Pages 883-899
Suggesting Sounds for Images from Video Collections....Pages 900-917
Back Matter....Pages 919-922