Sciweavers

CVPR
2012
IEEE
13 years 9 days ago
Action bank: A high-level representation of activity in video
Activity recognition in video is dominated by low- and mid-level features, and while demonstrably capable, by nature, these features carry little semantic meaning. Inspired by the...
Sreemanananth Sadanand, Jason J. Corso
ICCV
2011
IEEE
13 years 10 months ago
Discriminative Figure-Centric Models for Joint Action Localization and Recognition
In this paper we develop an algorithm for action recognition and localization in videos. The algorithm uses a figurecentric visual word representation. Different from previous ap...
Tian Lan, Yang Wang, Greg Mori