TokenPose: Learning Keypoint Tokens for Human Pose Estimation
Yanjie Li, Shoukui Zhang, Zhicheng Wang, Sen Yang, Wankou Yang, Shu-Tao Xia, Erjin Zhou
Abstract
Human pose estimation deeply relies on visual clues and anatomical constraints between parts to locate keypoints. Most existing CNN-based methods do well in visual representation, however, lacking in the ability to explicitly learn the constraint relationships between keypoints. In this paper, we propose a novel approach based on Token representation for human Pose estimation (TokenPose). In detail, each keypoint is explicitly embedded as a token to simultaneously learn constraint relationships and appearance cues from images. Extensive experiments show that the small and large TokenPose models are on par with state-of-the-art CNN-based counterparts while being more lightweight. Specifically, our TokenPose-S and TokenPose-L achieve 72.5 AP and 75.8 AP on COCO validation dataset respectively, with significant reduction in parameters and GFLOPs. Code is publicly available at https://github.com/leeyegy/TokenPose.
BibTeX
@inproceedings{iccv2021_tokenposelearnin,
title = {TokenPose: Learning Keypoint Tokens for Human Pose Estimation},
author = {Yanjie Li and Shoukui Zhang and Zhicheng Wang and Sen Yang and Wankou Yang and Shu-Tao Xia and Erjin Zhou},
booktitle = {ICCV 2021},
year = {2021}
}