117
click to vote
CVPR
2012
IEEE
13 years 9 days ago
2012
IEEE
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...
107
click to vote
ICCV
2011
IEEE
13 years 10 months ago
2011
IEEE
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...