2 search results - page 1 / 1 » Discovering discriminative action parts from mid-level video... |
CVPR
2012
IEEE
13 years 1 months ago
2012
IEEE
We describe a mid-level approach for action recognition. From an input video, we extract salient spatio-temporal structures by forming clusters of trajectories that serve as candi...
105
click to vote
ECCV
2010
Springer
14 years 12 months ago
2010
Springer
Abstract. This paper presents an exemplar-based approach to detecting and localizing human actions, such as running, cycling, and swinging, in realistic videos with dynamic backgro...