Towards the goal of realizing a generic automatichuman activity recognition system, a new formalism is proposed. Activities are described by a chained hierarchical representation ...
The compositional nature of visual objects significantly limits their representation complexity and renders learning of structured object models tractable. Adopting this modeling ...
Numerous statistical learning methods have been developed for visual recognition tasks. Few attempts, however, have been made to address theoretical issues, and in particular, stud...
Recently, the bag-of-words approach has been successfully applied to automatic image annotation, object recognition, etc. The method needs to first quantize an image using the vis...
In this paper, we study the problem of landmark recognition and propose to leverage 3D visual phrases to improve the performance. A 3D visual phrase is a triangular facet on the s...
Qiang Hao, Rui Cai, Zhiwei Li, Lei Zhang 0001, Yan...