Interest point detection in still images is a well-studied topic in computer vision. In the spatiotemporal domain, however, it is still unclear which features indicate useful inter...
We describe a system to learn an object template from a video stream, and localize and track the corresponding object in live video. The template is decomposed into a number of lo...
Most existing approaches for learning action models work by extracting suitable low-level features and then training appropriate classifiers. Such approaches require large amount...
We have developed a method that can discriminate anomalous image sequences for more efficiently utilizing security videos. To match the wide popularity of security cameras, the me...
We present Transitive Closure based visual word formation technique for obtaining robust object representations from smoothly varying multiple views. Each one of our visual words ...