Abstract | ||
---|---|---|
In this study, the authors investigate the possibility of boosting action recognition performance by exploiting the associated scene context. Towards this end, the authors model a scene as a mid-level `middle layer' in order to bridge action descriptors and action categories. This is achieved via a scene topic model, in which hybrid visual descriptors, including spatial-temporal action features an... |
Year | DOI | Venue |
---|---|---|
2016 | 10.1049/iet-cvi.2015.0420 | IET Computer Vision |
Keywords | Field | DocType |
Bayes methods,feature extraction,image motion analysis,image sequences,video signal processing | Nearest neighbour algorithm,Computer vision,Joint probability distribution,Pattern recognition,Naive Bayes classifier,Computer science,Action recognition,Visual descriptors,Boosting (machine learning),Artificial intelligence,Topic model,Machine learning | Journal |
Volume | Issue | ISSN |
10 | 6 | 1751-9632 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hongbo Zhang | 1 | 33 | 6.56 |
Qing Lei | 2 | 24 | 4.51 |
Duansheng Chen | 3 | 3 | 1.06 |
Bineng Zhong | 4 | 26 | 1.23 |
Jialin Peng | 5 | 54 | 6.41 |
Du Ji-Xiang | 6 | 69 | 10.58 |
Song-zhi Su | 7 | 61 | 8.53 |