Histograms of local appearance descriptors are a popular representation for visual recognition. They are highly discriminant with good resistance to local occlusions and to geomet...
Recognizing multiple interleaved activities in a video requires implicitly partitioning the detections for each activity. Furthermore, constraints between activities are important ...
Automatic video browsing requires algorithms for detecting a variety of events, including production effects (e.g., scene breaks and captions) and moving objects. We present new m...
This paper presents Geo-Linda, a physically distributed tuple space. Geo-Linda targets ubiquitous computing applications involving the detection of movement patterns of objects an...
In automatic video content analysis domain, the key challenges are how to recognize important objects and how to model the spatiotemporal relationships between them. In this paper...
Liang Bai, Songyang Lao, Gareth J. F. Jones, Alan ...