5082 search results - page 45 / 1017 » Actionable Information in Vision |
141
Voted
ICPR
2008
IEEE
16 years 5 months ago
2008
IEEE
We propose the use of 3D (2D+time) Shape Context to recognize the spatial and temporal details inherent in human actions. We represent an action in a video sequence by a 3D point ...
136
click to vote
CVPR
2010
IEEE
16 years 15 days ago
2010
IEEE
We present a method to classify and localize human actions in video using a Hough transform voting framework. Random trees are trained to learn a mapping between densely-sampled f...
148
click to vote
ECCV
2010
Springer
15 years 9 months ago
2010
Springer
3D human pose estimation in multi-view settings benefits from embeddings of human actions in low-dimensional manifolds, but the complexity of the embeddings increases with the num...
163
click to vote
ECCV
2006
Springer
15 years 7 months ago
2006
Springer
In this paper, we represent human actions as short sequences of atomic body poses. The knowledge of body pose is stored only implicitly as a set of silhouettes seen from multiple ...
154
click to vote
CVPR
2012
IEEE
13 years 6 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...