Multi-Person Pose Estimation With Enhanced Channel-Wise and Spatial Information

Kai Su, Dongdong Yu, Zhenqi Xu, Xin Geng, Changhu Wang; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 5674-5682

Abstract


Multi-person pose estimation is an important but challenging problem in computer vision. Although current approaches have achieved significant progress by fusing the multi-scale feature maps, they pay little attention to enhancing the channel-wise and spatial information of the feature maps. In this paper, we propose two novel modules to perform the enhancement of the information for the multi-person pose estimation. First, a Channel Shuffle Module (CSM) is proposed to adopt the channel shuffle operation on the feature maps with different levels, promoting cross-channel information communication among the pyramid feature maps. Second, a Spatial, Channel-wise Attention Residual Bottleneck (SCARB) is designed to boost the original residual unit with attention mechanism, adaptively highlighting the information of the feature maps both in the spatial and channel-wise context. The effectiveness of our proposed modules is evaluated on the COCO keypoint benchmark, and experimental results show that our approach achieves the state-of-the-art results.

Related Material


[pdf]
[bibtex]
@InProceedings{Su_2019_CVPR,
author = {Su, Kai and Yu, Dongdong and Xu, Zhenqi and Geng, Xin and Wang, Changhu},
title = {Multi-Person Pose Estimation With Enhanced Channel-Wise and Spatial Information},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}