SIA OpenIR  > 其他
An Improved Human-Object Interaction Detection Network
Gao S(高松)1,2,3; Wang, HY(王宏玉)1,2,4; Song JL(宋吉来)4; Xu F(徐方)1,2,4; Zou FS(邹风山)4
Department其他
Conference Name13th IEEE International Conference on Anti-Counterfeiting, Security, and Identification, ASID 2019
Conference DateOctober 25-27, 2019
Conference PlaceXiamen, China
Source PublicationProceedings of 2019 IEEE 13th International Conference on Anti-Counterfeiting, Security, and Identification, ASID 2019
PublisherIEEE Computer Society
Publication PlaceNew York
2019
Pages192-196
Indexed ByEI ; CPCI(ISTP)
EI Accession number20200208018743
WOS IDWOS:000521754700040
Contribution Rank1
ISSN2163-5048
ISBN978-1-7281-2458-2
Keywordhuman-object interaction detection deep learning loss function convolutional neural networks
AbstractHuman-Object Interaction (HOI) Detection is an important problem which is expected not only to detect individual object instances, but also to recognize the visual relationship between object pairs. In this paper, we improve the performance of the HOI detection task based on the instance-centric attention network. At first, we improve the accuracy of existing model by optimizing loss function and training details. We validate the improved method on the recently introduced Verbs in COCO (V-COCO) dataset. Then, to analyze the experimental results, we set several error modes and get the distribution of the false positives for each action class. Finally, we apply the trained model to HOI detection in surveillance scenario. The experimental result shows that the improved method can accurately detect the human-object interactions, which are involved in the VCOCO dataset.
Language英语
Citation statistics
Document Type会议论文
Identifierhttp://ir.sia.cn/handle/173321/26188
Collection其他
Corresponding AuthorWang, HY(王宏玉)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
2.Institute for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
3.University of Chinese Academy of Sciences, Beijing 100049, China
4.Shenyang SIASUN Robot Automation Co. Ltd., Shenyang 110168, China
Recommended Citation
GB/T 7714
Gao S,Wang, HY,Song JL,et al. An Improved Human-Object Interaction Detection Network[C]. New York:IEEE Computer Society,2019:192-196.
Files in This Item:
File Name/Size DocType Version Access License
An Improved Human-Ob(1317KB)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
[Gao S(高松)]'s Articles
[Wang, HY(王宏玉)]'s Articles
[Song JL(宋吉来)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Gao S(高松)]'s Articles
[Wang, HY(王宏玉)]'s Articles
[Song JL(宋吉来)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Gao S(高松)]'s Articles
[Wang, HY(王宏玉)]'s Articles
[Song JL(宋吉来)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: An Improved Human-Object Interaction Detection Network.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.
 

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