The proceedings contain 11 papers. The topics discussed include: robust face alignment based on hierarchical classifier network; eigenExpress approach in recognition of facial expression using GPU; face representation method using pixel-to-vertex map (PVM) for 3D model based face recognition; robust head tracking with particles based on multiple cues fusion; vision-based interpretation of hand gestures for remote control of a computer mouse; computing emotion awareness through facial electromyography; silhouette-based method for object classification and human action recognition in video; voice activity detection using wavelet-based multiresolution spectrum and support vector machines and audio mixing algorithm; action recognition in broadcast tennis video using optical flow and support vector machine; facemouse: a human-computer interface for tetraplegic people; and object retrieval by query with sensibility based on the KANSEI-vocabulary scale.
Computer Vision in Human-Computer Interaction - ECCV 2006 Workshop on HCI, Proceedings
Sebe, Niculae;
2006-01-01
Abstract
The proceedings contain 11 papers. The topics discussed include: robust face alignment based on hierarchical classifier network; eigenExpress approach in recognition of facial expression using GPU; face representation method using pixel-to-vertex map (PVM) for 3D model based face recognition; robust head tracking with particles based on multiple cues fusion; vision-based interpretation of hand gestures for remote control of a computer mouse; computing emotion awareness through facial electromyography; silhouette-based method for object classification and human action recognition in video; voice activity detection using wavelet-based multiresolution spectrum and support vector machines and audio mixing algorithm; action recognition in broadcast tennis video using optical flow and support vector machine; facemouse: a human-computer interface for tetraplegic people; and object retrieval by query with sensibility based on the KANSEI-vocabulary scale.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione



