When editing a story from a large collection of media, such as photos and video clips captured from daily life, it is not always easy to understand how particular scenes fit into ...
There has been a growing interest in exploiting contextual information in addition to local features to detect and localize multiple object categories in an image. Context models ...
Myung Jin Choi, Joseph Lim, Antonio Torralba, Alan...
This paper presents a spatial-semantic modeling system featuring automated learning of object-place relations from an online annotated database, and the application of these relat...
Pooja Viswanathan, David Meger, Tristram Southey, ...
We address the problem of automatic interpretation of nonexaggerated human facial and body behaviours captured in video. We illustrate our approach by three examples. (1) We intro...
An attractive approach to improve tracking performance for visual surveillance is to use information from multiple visual sensory cues such as position, color, shape, etc. Previou...