This paper presents a multi-scale generative model for representing animate shapes and extracting meaningful parts of objects. The model assumes that animate shapes (2D simple clo...
This paper concerns recognition of human actions under view changes. We explore self-similarities of action sequences over time and observe the striking stability of such measures ...
Imran N. Junejo, Emilie Dexter, Ivan Laptev, Patri...
Abstract. There is considerable interest in techniques capable of identifying anomalies and unusual events in busy outdoor scenes, e.g. road junctions. Many approaches achieve this...
We present a new scheme to robustly detect a type of human attentive behavior, which we call frequent change in focus of attention (FCFA), from video sequences. FCFA behavior can b...
Abstract. Figure/ground assignment is a key step in perceptual organization which assigns contours to one of the two abutting regions, providing information about occlusion and all...