Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Information
This work addresses a challenging problem in computer vision for applications like human-computer interaction, but it is incremental as it builds on existing multi-scale fusion methods.
The paper tackles multi-person pose estimation by enhancing channel-wise and spatial information in feature maps, achieving state-of-the-art results on the COCO keypoint benchmark.
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.