Fangshi Wang

Learn More
Retrieving videos using key words requires obtaining the semantic features of the videos. Most work reported in the literature focuses on annotating a video shot with a fixed number of key words, no matter how much information is contained in the video shot. In this paper, we propose a new approach to automatically annotate a video shot with an adaptive(More)
Recently, many work propose to unify representation and classification in a single model to make the representations both characteristic and discrimina-tive. Some related outstanding methods include the relevance topic model [5], the max-margin LDA [4] and the Gibbs max-margin topic model [6], which show successful results with the aid of topic models.(More)
The performance of action recognition in video sequences depends significantly on the representation of actions and the similarity measurement between the representations. In this paper, we combine two kinds of features extracted from the spatio-temporal interest points with context-aware kernels for action recognition. For the action representation, local(More)
Motion is the most informative cue for human action recognition. Regions with high motion saliency indicate where actions occur and contain visual information that is most relevant to actions. In this paper, we propose a novel approach for human action recognition based on oriented motion salient regions (OMSRs). Firstly, we apply a bank of 3D Gabor filters(More)