Exploiting Offset-guided Network for Pose Estimation and Tracking

Rui Zhang, Zheng Zhu, Peng Li, Rui Wu, Chaoxu Guo, Guan Huang, Hailun Xia; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 20-28

Abstract


Human pose estimation has witnessed a significant advance thanks to the development of deep learning. Recent human pose estimation approaches tend to directly predict the location heatmaps, which causes quantization errors and inevitably deteriorates the performance within the reduced network output. Aim at solving it, we revisit the heatmap-offset aggregation method and propose the Offset- guided Network (OGN) with an intuitive but effective fusion strategy for both two-stages pose estimation and Mask R-CNN. For two-stages pose estimation, a greedy box generation strategy is also proposed to keep more necessary candidates while performing person detection. For mask R-CNN, ratio-consistent is adopted to improve the generalization ability of the network. State-of-the-art results on COCO and PoseTrack dataset verify the effectiveness of our offset-guided pose estimation and tracking.

Related Material


[pdf] [dataset]
[bibtex]
@InProceedings{Zhang_2019_CVPR_Workshops,
author = {Zhang, Rui and Zhu, Zheng and Li, Peng and Wu, Rui and Guo, Chaoxu and Huang, Guan and Xia, Hailun},
title = {Exploiting Offset-guided Network for Pose Estimation and Tracking},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}
}