papers AI Learner
The Github is limit! Click to go to the new site.

Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Information

2019-05-09
Kai Su, Dongdong Yu, Zhenqi Xu, Xin Geng, Changhu Wang

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.03466

PDF

http://arxiv.org/pdf/1905.03466


Similar Posts

Comments