Name
Abstract | ||
|---|---|---|
This notebook paper presents an overview and comparative analysis of our system designed for activity detection in extended videos (ActEV-PC) in ActivityNet Challenge 2019. Specifically, we exploit person/vehicle detections in spatial level and action localization in temporal level for action detection in surveillance videos. The mechanism of different tubelet generation and model decomposition methods are studied as well. The detection results are finally predicted by late fusing the results from each component. |
Year | Venue | DocType |
|---|---|---|
2019 | CoRR | Journal |
Volume | Citations | PageRank |
abs/1906.08547 | 0 | 0.34 |
References | Authors | |
0 | 7 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Fuchen Long | 1 | 43 | 3.18 |
| Qi Cai | 2 | 13 | 2.18 |
| Zhaofan Qiu | 3 | 117 | 10.06 |
| Zhijian Hou | 4 | 0 | 1.01 |
| Yingwei Pan | 5 | 357 | 23.66 |
| Ting Yao | 6 | 842 | 52.62 |
| C. W. Ngo | 7 | 4271 | 211.46 |