Abstract | ||
---|---|---|
Multi-person pose tracking aims to jointly estimate and track multi-person keypoints in the unconstrained videos. The most popular solution to this task follows the tracking-by-detection strategy that relies on human detection and data association. While human detection has been boosted by deep learning, existing works mainly exploit several separated stages with hand-crafted metrics to realize data association, leading to great uncertainty and feeble adaption in complex scenes. To handle these problems, we propose an end-to-end pose-guided ovonic insight network (POINet) for the data association in multi-person pose tracking, which jointly learns feature extraction, similarity estimation, and identity assignment. Specifically, we design a pose-guided representation network to integrate pose information into hierarchical convolutional features, generating a pose-aligned person representation for person, which helps handle partial occlusions. Moreover, we propose an ovonic insight network to adaptively encode the cross-frame identity transformation, which can cope with the tough tracking cases of person leaving and entering the scene. In general, the proposed POINet provides a new insight to realize multi-person pose tracking in an end-to-end fashion. Extensive experiments conducted on the PoseTrack benchmark demonstrate that our POINet outperforms the state-of-the-art methods.
|
Year | DOI | Venue |
---|---|---|
2019 | 10.1145/3343031.3350984 | Proceedings of the 27th ACM International Conference on Multimedia |
Keywords | Field | DocType |
end-to-end network, ovonic insight, pose tracking, pose-guided | Computer vision,Pose tracking,Computer science,Artificial intelligence | Conference |
ISBN | Citations | PageRank |
978-1-4503-6889-6 | 11 | 0.51 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Weijian Ruan | 1 | 14 | 1.91 |
Wu Liu | 2 | 275 | 34.53 |
Qian Bao | 3 | 13 | 1.59 |
Jun Chen | 4 | 67 | 5.94 |
Yuhao Cheng | 5 | 12 | 2.22 |
Tao Mei | 6 | 4702 | 288.54 |