Trends and Topics in Computer Vision

The two volumes LNCS 6553 and 6554 constitute the refereed post-proceedings of 7 workshops held in conjunction with the 11th European Conference on Computer Vision, held in Heraklion, Crete, Greece in September 2010. The 62 revised papers presented together with 2 invited talks were carefully reviewed and selected from numerous submissions. The first volume contains 26 revised papers and 2 invited talks selected from the following workshops: First International Workshop on Parts and Attributes; Third Workshop on Human Motion Understanding, Modeling, Capture and Animation; and International Workshop on Sign, Gesture and Activity (SGA 2010).

State-of-the-art research Fast-track conference proceedings Unique visibility

Inhalt
Attribute Learning in Large-Scale Datasets.- Combining Language Sources and Robust Semantic Relatedness for Attribute-Based Knowledge Transfer.- Sparse Representations and Distance Learning for Attribute Based Category Recognition.- Semi-supervised Learning of Facial Attributes in Video.- Objects as Attributes for Scene Classification.- A Generic Model to Compose Vision Modules for Holistic Scene Understanding.- Automatic Facial Landmark Tracking in Video Sequences Using Kalman Filter Assisted Active Shape Models.- Tracking in Action Space.- A Tree-Based Approach to Integrated Action Localization, Recognition and Segmentation.- A SURF-Based Spatio-Temporal Feature for Feature-Fusion-Based Action Recognition.- Middle-Level Representation for Human Activities Recognition: The Role of Spatio-Temporal Relationships.- Retrieving Actions in Group Contexts.- Hough Forest-Based Facial Expression Recognition from Video Sequences.- Spatiotemporal Features for Effective Facial Expression Recognition.- Human Focused Action Localization in Video.- Head Tracking and Hand Segmentation during Hand over Face Occlusion in Sign Language.- Fusion of Human Posture Features for Continuous Action Recognition.- Hand Tracking and Affine Shape-Appearance Handshape Sub-units in Continuous Sign Language Recognition.- Detecting Regions from Single Scale Edges.- Generalised Pose Estimation Using Depth.- A Real-Time System for Head Tracking and Pose Estimation.- A System for Large Vocabulary Sign Search.