57 search results - page 1 / 12 » action recognition by dense trajectories |
CVPR
2011
IEEE
12 years 12 months ago
2011
IEEE
Feature trajectories have shown to be efficient for representing videos. Typically, they are extracted using the KLT tracker or matching SIFT descriptors between frames. However,...
ICCV
2011
IEEE
11 years 8 months ago
2011
IEEE
Recognition of human actions in a video acquired by a moving camera typically requires standard preprocessing steps such as motion compensation, moving object detection and object ...
CVPR
1999
IEEE
14 years 6 months ago
1999
IEEE
CVPR
2009
IEEE
14 years 11 months ago
2009
IEEE
Several spatiotemporal feature point detectors have been recently used in video analysis for action recognition. Feature points are detected using a number of measures, namely sali...
ECCV
2008
Springer
14 years 6 months ago
2008
Springer
Abstract. The use of sparse invariant features to recognise classes of actions or objects has become common in the literature. However, features are often "engineered" to...