Viewpoint invariant pedestrian recognition is an important yet under-addressed problem in computer vision. This is likely due to the difficulty in matching two objects with unknown...
We introduce a discriminative hidden-state approach for the recognition of human gestures. Gesture sequences often have a complex underlying structure, and models that can incorpo...
Sy Bor Wang, Ariadna Quattoni, Louis-Philippe More...
Object recognition systems aiming to work in real world settings should use multiple cues in order to achieve robustness. We present a new cue integration scheme which extends the...
Human movements are important cues for recognizing human actions, which can be captured by explicit modeling and tracking of actor or through space-time low-level features. Howeve...
This paper presents a novel method for learning object manipulation such as rotating an object or placing one object on another. In this method, motions are learned using referenc...