We describe a probabilistic framework for recognizing human activities in monocular video based on simple silhouette observations in this paper. The methodology combines kernel pr...
Online communities like Flickr, del.icio.us and YouTube have established themselves as very popular and powerful services for publishing and searching contents, but also for ident...
Tom Crecelius, Mouna Kacimi, Sebastian Michel, Tho...
Accurate grouping of video shots could lead to semantic indexing of video segments for content analysis and retrieval. This paper introduces a novel cluster analysis which, depend...
At FXPAL Japan we have built an (experimental) Smart Conference Room (SCR) that contains multiple cameras, microphones, displays, and capture devices. Based on our experience, in ...
A comprehensive novel multi-view dynamic face model is presented in this paper to address two challenging problems in face recognition and facial analysis: modelling faces with la...