Learning dominant motion patterns or activities from a video is an important surveillance problem, especially in crowded environments like markets, subways etc., where tracking of...
Hierarchical topic taxonomies have proliferated on the World Wide Web [5, 18], and exploiting the output space decompositions they induce in automated classification systems is an...
Abstract—Social conventions are useful self-sustaining protocols for groups to coordinate behavior without a centralized entity enforcing coordination. We perform an in-depth stu...
We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a lowdimensional embedding of the pose manifol...
Tobias Jaeggli, Esther Koller-Meier, Luc J. Van Go...
Scalable approaches to video content classification are limited by an inability to automatically generate representations of events ode abstract temporal structure. This paper pre...