Shu-Tao Xia, Yanjie Li, Sen Yang, Wankou Yang, Erjin Zhou, Zhicheng Wang, Shoukui Zhang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 (↓ 80.6% ; ↓ 56.8%) and GFLOPs (↓ 75.3%; ↓ 24.7%). Code is publicly available 1 .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2104.03516")
get_code_for_paper("2104.03516")
have("2104.03516")
Connect an agent — have() is free.