Name
Abstract | ||
|---|---|---|
Most existing action recognition approaches directly leverage the video-level features to recognize human actions from videos. Although these methods have made remarkable progress, the accuracy is still unsatisfied. When the test video involves complex backgrounds and activities, existing methods usually suffer from a significant drop in accuracy. Human action is inherently a high-level concept. M... |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1109/TCSVT.2021.3100842 | IEEE Transactions on Circuits and Systems for Video Technology |
Keywords | DocType | Volume |
Semantics,Image segmentation,Three-dimensional displays,Streaming media,Image recognition,Training,Target recognition | Journal | 32 |
Issue | ISSN | Citations |
5 | 1051-8215 | 0 |
PageRank | References | Authors |
0.34 | 28 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Haonan Luo | 1 | 0 | 0.68 |
| Guosheng Lin | 2 | 688 | 33.91 |
| Yazhou Yao | 3 | 86 | 16.61 |
| Zhenmin Tang | 4 | 678 | 55.54 |
| Qingyao Wu | 5 | 0 | 0.34 |
| Xian-Sheng Hua | 6 | 6566 | 328.17 |