In the novelty task on sentence level, the amount of information used in similarity computation is the major challenging issue. A shallow NLP approach extracts noun and verb featu...
Abstract This paper presents an approach to designing and implementing extensible computational models for perceiving systems based on a knowledge-driven joint inference approach. ...
This paper describes a vision based pedestrian detection and tracking system which is able to count people in very crowded situations like escalator entrances in underground stati...
The ability to detect and track human heads and faces in video sequences is useful in a great number of applications, such as human-computer interaction and gesture recognition. Re...
Recognition of complex activities from surveillance video requires detection and temporal ordering of its constituent "atomic" events. It also requires the capacity to ro...