Pose Recognition with Cascade Transformers

In this paper, we present a regression-based pose recognition method using cascade Transformers. One way to categorize the existing approaches in this domain is to separate them into 1). heatmap-based and 2). regression-based. In general, heatmap-based methods achieve higher accuracy but are subject...

Full description

Saved in:
Bibliographic Details
Published inProceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 1944 - 1953
Main Authors Li, Ke, Wang, Shijie, Zhang, Xiang, Xu, Yifan, Xu, Weijian, Tu, Zhuowen
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2021
Subjects
Computer vision
Decoding
Heating systems
Pattern recognition
Task analysis
Transformers
Visualization
Online AccessGet full text

Cover

More Information
Summary:In this paper, we present a regression-based pose recognition method using cascade Transformers. One way to categorize the existing approaches in this domain is to separate them into 1). heatmap-based and 2). regression-based. In general, heatmap-based methods achieve higher accuracy but are subject to various heuristic designs (not end-to-end mostly), whereas regression-based approaches attain relatively lower accuracy but they have less intermediate non-differentiable steps. Here we utilize the encoder-decoder structure in Transformers to perform regression-based person and keypoint detection that is general-purpose and requires less heuristic design compared with the existing approaches. We demonstrate the keypoint hypothesis (query) refinement process across different self-attention layers to reveal the recursive self-attention mechanism in Transformers. In the experiments, we report competitive results for pose recognition when compared with the competing regression-based methods.
ISSN:1063-6919
DOI:10.1109/CVPR46437.2021.00198