Name
Abstract | ||
|---|---|---|
Temporal segmentation of successive actions in a long-term video sequence has been a long-standing problem in computer vision. In this paper, we exploit a novel learning-based framework. Given a video sequence, only a few characteristic frames are selected by the proposed selection algorithm, and then the likelihood to trained models is calculated in a pair-wise way, and finally segmentation is obtained as the optimal model sequence to realize the maximum likelihood. The average accuracy on IXMAS dataset reached to 80.5% at frame level, using only 16.5% of all frames in computation time of 1.57s per video which has 1160 frames on the average. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1016/j.patrec.2012.10.023 | Pattern Recognition Letters |
Keywords | Field | DocType |
temporal segmentation,maximum likelihood,computer vision,computation time,long-term video sequence,average accuracy,successive action,ixmas dataset,optimal model sequence,characteristic frame,video sequence,viterbi algorithm | Reference frame,Computer vision,Scale-space segmentation,Pattern recognition,Segmentation,Selection algorithm,Maximum likelihood,Exploit,Artificial intelligence,Mathematics,Viterbi algorithm,Computation | Journal |
Volume | Issue | ISSN |
34 | 15 | 0167-8655 |
Citations | PageRank | References |
3 | 0.38 | 33 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Guoliang Lu | 1 | 41 | 3.65 |
| Mineichi Kudo | 2 | 927 | 116.09 |
| Jun Toyama | 3 | 130 | 19.87 |