Name
Abstract | ||
|---|---|---|
For achieving efficient action recognition, some recent works propose to select a smaller number of frames in a video sequence instead of the entire sequence of frames. In this study, we propose to represent a frame by a combination of local and global descriptors instead of the silhouette used in our previous approach aiming at frame selection. Action recognition is then executed on the basis of the selected frames. The experiment on KTH database shows that the selected frames by the proposed framework are, in the minimum number to achieve the best recognition rate, better than those by two compared selection ways. |
Year | Venue | Keywords |
|---|---|---|
2012 | ICPR | kth database,video signal processing,image representation,global descriptors,local descriptors,efficient action recognition,image sequences,frame selection,gesture recognition,characteristic frames,sparse representation,video sequence |
Field | DocType | ISSN |
Reference frame,Computer vision,Pattern recognition,Silhouette,Computer science,Sparse approximation,Action recognition,Image representation,Gesture recognition,Video tracking,Artificial intelligence | Conference | 1051-4651 |
ISBN | Citations | PageRank |
978-1-4673-2216-4 | 0 | 0.34 |
References | Authors | |
8 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Guoliang Lu | 1 | 8 | 2.84 |
| Mineichi Kudo | 2 | 927 | 116.09 |
| Jun Toyama | 3 | 130 | 19.87 |