SIA OpenIR  > 机器人学研究室
SCR-Graph: Spatial-Causal Relationships Based Graph Reasoning Network for Human Action Prediction
Chen B(陈博)1,2,3; Sun XS(孙晓舒)1,2; Li DC(李德才)1,2; He YQ(何玉庆)1,2; Hua CS(华春生)4
Department机器人学研究室
Conference Name2nd International Conference on Computing and Data Science, CONF-CDS 2021
Conference DateJanuary 28-30, 2021
Conference PlaceStanford, CA, United states
Source PublicationProceedings of the 2nd International Conference on Computing and Data Science, CONF-CDS 2021
PublisherACM
Publication PlaceNew York
2021
Pages1-9
Indexed ByEI
EI Accession number20212110387380
Contribution Rank1
ISBN978-1-4503-8957-0
KeywordGraph neural network knowledge graph action prediction
AbstractTechnologies to predict human actions are extremely important for applications such as human robot cooperation and autonomous driving. However, a majority of the existing algorithms focus on exploiting visual features of the videos and do not consider the mining of relationships, which include spatial relationships between human and scene elements as well as causal relationships in temporal action sequences. In fact, human beings are good at using spatial and causal relational reasoning mechanism to predict the actions of others. Inspired by this idea, we proposed a Spatial and Causal Relationship based Graph Reasoning Network (SCR-Graph), which can be used to predict human actions by modeling the action-scene relationship, and causal relationship between actions, in spatial and temporal dimensions respectively. Here, in spatial dimension, a hierarchical graph attention module is designed by iteratively aggregating the features of different kinds of scene elements in different level. In temporal dimension, we designed a knowledge graph based causal reasoning module and map the past actions to temporal causal features through Diffusion RNN. Finally, we integrated the causality features into the heterogeneous graph in the form of shadow node, and introduced a self-attention module to determine the time when the knowledge graph information should be activated. Extensive experimental results on the VIRAT datasets demonstrate the favorable performance of the proposed framework.
Language英语
Document Type会议论文
Identifierhttp://ir.sia.cn/handle/173321/28937
Collection机器人学研究室
Corresponding AuthorHe YQ(何玉庆)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110016, China
3.University of Chinese Academy of Sciences, Beijing 100049, China
4.Liaoning University, Shenyang 110016, China
Recommended Citation
GB/T 7714
Chen B,Sun XS,Li DC,et al. SCR-Graph: Spatial-Causal Relationships Based Graph Reasoning Network for Human Action Prediction[C]. New York:ACM,2021:1-9.
Files in This Item:
File Name/Size DocType Version Access License
SCR-Graph_ Spatial-C(2242KB)会议论文 开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Chen B(陈博)]'s Articles
[Sun XS(孙晓舒)]'s Articles
[Li DC(李德才)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chen B(陈博)]'s Articles
[Sun XS(孙晓舒)]'s Articles
[Li DC(李德才)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chen B(陈博)]'s Articles
[Sun XS(孙晓舒)]'s Articles
[Li DC(李德才)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: SCR-Graph_ Spatial-Causal Relationships Based Graph Reasoning Network for Human Action Prediction.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.