STN-enhanced message passing guided by adversarial learning for human pose estimation | |
Zhou Lu1,3; Chen Yingying1,3; Cao Congqi2; Wang Jinqiao1,3; Lu Hanqing1,3 | |
刊名 | Neurocomputing |
2021 | |
期号 | 453页码:60-72 |
关键词 | Spatial transformer network Message passing Limb guidance Adversarial learning Human pose estimation |
英文摘要 | In this paper, an STN (Spatial Transformer Network)-enhanced message passing module guided by adversarial learning is proposed for human pose estimation. Transformations performed on the predicted heatmaps mean to modify the raw predictions and conduct the message passing among human joints in an elegant way. Firstly, we employ STN submodule to transform the predicted heatmap of one human joint to heatmap of its neighboring joint to remove ambiguity of its neighboring predictions. STN submodule automatically learns the geometric information between adjacent joints and thus builds related neighboring associations among them. Nevertheless, it seems difficult for STN submodule to learn inherent geometric information from a single RGB image alone. Secondly, limb guidance is introduced to assist STN in predicting corresponding correlations. Since quality of limb predictions poses great significance for the guidance, we propose to exploit adversarial learning to improve the quality of limb heatmaps which are easier to learn than precise keypoint location. Hence, the precision of STN transformation improves owing to more precise prior instructions. However, STN submodule might be confused when performing the transformation due to massive noises of the heatmaps. To circumvent this dilemma, at last, we propose to utilize Weighted Mean Square Error (WMSE) loss and convolutional random walk (CRW) which improve the performance further. Our method achieves competitive results on both MPII and LSP benchmarks. |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44870] |
专题 | 自动化研究所_模式识别国家重点实验室_图像与视频分析团队 |
通讯作者 | Chen Yingying |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.Northwestern Polytechnical University 3.University of Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Zhou Lu,Chen Yingying,Cao Congqi,et al. STN-enhanced message passing guided by adversarial learning for human pose estimation[J]. Neurocomputing,2021(453):60-72. |
APA | Zhou Lu,Chen Yingying,Cao Congqi,Wang Jinqiao,&Lu Hanqing.(2021).STN-enhanced message passing guided by adversarial learning for human pose estimation.Neurocomputing(453),60-72. |
MLA | Zhou Lu,et al."STN-enhanced message passing guided by adversarial learning for human pose estimation".Neurocomputing .453(2021):60-72. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论