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. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/CVPR.2019.00582 | 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) |
Field | DocType | Volume |
Spatial analysis,Computer vision,Pattern recognition,Computer science,Communication channel,Pose,Artificial intelligence | Journal | abs/1905.03466 |
ISSN | Citations | PageRank |
1063-6919 | 5 | 0.40 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kai Su | 1 | 8 | 1.79 |
Dongdong Yu | 2 | 63 | 7.07 |
Zhenqi Xu | 3 | 5 | 0.40 |
Xin Geng | 4 | 1557 | 83.54 |
Changhu Wang | 5 | 1296 | 70.36 |