We propose a new method for human action recognition from video sequences using latent topic models. Video sequences are represented by a novel “bag-of-words” representation, w...
Content-based classification of audio data is an important problem for various applications such as overall analysis of audio-visual streams, boundary detection of video story se...
This paper presents novel techniques for using panoramas as spatial context to enhance browsing of personal media archives. This context, scenes where frequent media capture takes...
The work presented here solves two major problems of hand pose recognition: (A) determining what pose is shown in a given, input picture and (B) detecting the presence of a known ...
Modeling visual concepts using supervised or unsupervised machine learning approaches are becoming increasing important for video semantic indexing, retrieval, and filtering appli...