Convolutional relation network for skeleton-based action recognition
文献类型：期刊论文
| 作者 | Zhu, Jiagang1,2 ; Zou, Wei1,3,4; Zhu, Zheng1,2; Hu, Yiming1,2
|
| 刊名 | NEUROCOMPUTING
 |
| 出版日期 | 2019-12-22 |
| 卷号 | 370页码:109-117 |
| ISSN号 | 0925-2312 |
| 关键词 | Action recognition Skeleton Deep learning Joint interaction Dilation Attention |
| DOI | 10.1016/j.neucom.2019.08.043 |
| 通讯作者 | Zou, Wei(wei.zou@ia.ac.cn) |
| 英文摘要 | In the skeleton-based action recognition, mining information from the joints and limbs of human skeletons plays a key role. Previous studies treated the skeleton data as vectors and could not explicitly capture the joint interactions (e.g., RNN-based methods), or modeled the joint interactions in a local manner and may lose important cues without global response mapping (e.g., CNN and GCN (Graph Convolution Network) based methods). In this work, we address these problems by considering the potential relations of all the node pairs and edge pairs on the skeleton graphs. A dilation group-specific convolution module is proposed to aggregate relation messages of all the unit pairs on the skeleton graphs. By enumerating all the pair relations, the joint interactions could be learned explicitly and globally. It is then enhanced by introducing the attention pooling including temporal attention, spatial attention and channel attention. By stacking such several blocks, the relation messages of the node pairs are augmented by multi-layer propagation. Finally, the late fusion of four streams is used to combine the predictions of different inputs including node pairs, edge pairs and corresponding frame differences. The proposed method, termed cony-relation network, achieves competitive performance on two large scale datasets, NTU RGB+D and Kinetics. (C) 2019 Elsevier B.V. All rights reserved. |
| 资助项目 | National Key Research and Development Program of China[2017YFB1300104] ; National Natural Science Foundation of China[61773374] ; Project of Development In Tianjin for Scientific Research Institutes Supported By Tianjin government[16PTYJGX00050] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| 出版者 | ELSEVIER |
| WOS记录号 | WOS:000493285800011 |
| 资助机构 | National Key Research and Development Program of China ; National Natural Science Foundation of China ; Project of Development In Tianjin for Scientific Research Institutes Supported By Tianjin government |
| 源URL | [http://ir.ia.ac.cn/handle/173211/28894]  |
| 专题 | 精密感知与控制研究中心_精密感知与控制 |
| 通讯作者 | Zou, Wei |
| 作者单位 | 1.Univ Chinese Acad Sci, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing, Peoples R China 4.CASIA Co Ltd, TianJin Intelligent Tech Inst, Tianjin, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhu, Jiagang,Zou, Wei,Zhu, Zheng,et al. Convolutional relation network for skeleton-based action recognition[J]. NEUROCOMPUTING,2019,370:109-117. |
| APA | Zhu, Jiagang,Zou, Wei,Zhu, Zheng,&Hu, Yiming.(2019).Convolutional relation network for skeleton-based action recognition.NEUROCOMPUTING,370,109-117. |
| MLA | Zhu, Jiagang,et al."Convolutional relation network for skeleton-based action recognition".NEUROCOMPUTING 370(2019):109-117. |
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。