CASIA OpenIR  > 模式识别国家重点实验室  > 视频内容安全
Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification
Du Y(杜杨)1,2,3,4,5; Chunfeng Yuan2,3; Bing Li2,3; Lili Zhao4; Yangxi Li5; Weiming Hu2,3,5
2018-09
Conference NameEuropean Conference on Computer Vision (ECCV2018)
Source PublicationProcedings of European Conference on Computer Vision (ECCV2018)
Pagespp. 388-404.
Conference Date2018-09-08---2018-09-14
Conference PlaceMunich, Germany
Author of SourceCommittee of ECCV 2018
Abstract

Local features at neighboring spatial positions in feature maps have high correlation since their receptive fields are often overlapped. Self-attention usually uses the weighted sum (or other functions) with internal elements of each local feature to obtain its weight score, which ignores interactions among local features. To address this, we propose an effective interaction-aware self-attention model inspired by PCA to learn attention maps. Furthermore, since different layers in a deep network capture feature maps of dfferent scales, we use these feature maps to construct a spatial pyramid and then utilize multi-scale information to obtain more accurate attention scores, which are used to weight the local features in all spatial positions of feature maps to calculate attention maps. Moreover, our spatial pyramid attention is unrestricted to the number of its input feature maps so it is easily extended to a spatiotemporal version. Finally, our model is embedded in general CNNs to form end-to-end attention networks for action classification. Experimental results show that our method achieves the state-of-the-art results on the UCF101, HMDB51 and untrimmed Charades.

MOST Discipline Catalogue工学
Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23366
Collection模式识别国家重点实验室_视频内容安全
Affiliation1.中国科学院大学
2.中国科学院脑科学与智能技术卓越创新中心(神经科学研究所)
3.中国科学院自动化研究所
4.Meitu, Mainland China
5.国家计算机网络应急技术处理协调中心
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Du Y,Chunfeng Yuan,Bing Li,et al. Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification[C]//Committee of ECCV 2018,2018:pp. 388-404..
Files in This Item: Download All
File Name/Size DocType Version Access License
eccv2018.pdf(6727KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Du Y(杜杨)]'s Articles
[Chunfeng Yuan]'s Articles
[Bing Li]'s Articles
Baidu academic
Similar articles in Baidu academic
[Du Y(杜杨)]'s Articles
[Chunfeng Yuan]'s Articles
[Bing Li]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Du Y(杜杨)]'s Articles
[Chunfeng Yuan]'s Articles
[Bing Li]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: eccv2018.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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