中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 紫东太初大模型研究中心
  5. 图像与视频分析团队
Action recognition via pose-based graph convolutional networks with intermediate dense supervision

文献类型：期刊论文

作者Shi, Lei1,2,3,4; Zhang, Yifan1,2,3; Cheng, Jian1,2,3; Lu, Hanqing1,2,3
刊名PATTERN RECOGNITION
出版日期2022
卷号121页码:9
关键词Action recognition Skeleton
ISSN号0031-3203
DOI10.1016/j.patcog.2021.108170
通讯作者Zhang, Yifan(yfzhang@nlpr.ia.ac.cn)
英文摘要Pose-based action recognition has drawn considerable attention recently. Existing methods exploit the joint position to extract body-part features from the activation maps of the backbone CNN to assist human action recognition. However, there are two limitations: (1) the body-part features are independently used or simply concatenated to obtain a representation, where the prior knowledge about the structured correlations between body parts are not fully exploited; (2) the backbone CNN, from which the body-part features are extracted, is "lazy". It always contents itself with identifying patterns from the most discriminative areas of the input, which causes no information on the features extracted from other areas. This consequently hampers the performance of the followed aggregation process and makes the model easy to be misled by the training data bias. To address these problems, we encode the body-part features into a human-based spatiotemporal graph and employ a light-weight graph convolutional module to explicitly model the dependencies between body parts. Besides, we introduce a novel intermediate dense supervision to promote the backbone CNN to treat all regions equally, which is simple and effective, without extra parameters and computations. The proposed approach, namely, the pose-based graph convolutional network (PGCN), is evaluated on three popular benchmarks, where our approach significantly outperforms the state-of-the-art methods. (c) 2021 Elsevier Ltd. All rights reserved.
资助项目Jiangsu Frontier Technology Basic Research[BK20192004] ; NSFC[61876182] ; NSFC[61872364] ; Key project of Chinese Academy of Sciences[ZDRW-XH-2021-3]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000701175900012
出版者ELSEVIER SCI LTD
资助机构Jiangsu Frontier Technology Basic Research ; NSFC ; Key project of Chinese Academy of Sciences
源URL[http://ir.ia.ac.cn/handle/173211/45744]  
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Zhang, Yifan
作者单位1.Chinese Acad Sci, Inst Automat, NLPR, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Automat, AIRIA, Beijing, Peoples R China
3.Meituan, Beijing, Peoples R China
4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Shi, Lei,Zhang, Yifan,Cheng, Jian,et al. Action recognition via pose-based graph convolutional networks with intermediate dense supervision[J]. PATTERN RECOGNITION,2022,121:9.
APA Shi, Lei,Zhang, Yifan,Cheng, Jian,&Lu, Hanqing.(2022).Action recognition via pose-based graph convolutional networks with intermediate dense supervision.PATTERN RECOGNITION,121,9.
MLA Shi, Lei,et al."Action recognition via pose-based graph convolutional networks with intermediate dense supervision".PATTERN RECOGNITION 121(2022):9.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

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。