CASIA OpenIR  > 模式识别国家重点实验室  > 先进数据分析与学习
Weakly Semantic Guided Action Recognition
Yu, Tingzhao1,2; Wang, Lingfeng1; Da, Cheng1,2; Gu, Huxiang1; Xiang, Shiming1; Pan, Chunhong1
Source PublicationIEEE TRANSACTIONS ON MULTIMEDIA
ISSN1520-9210
2019-10-01
Volume21Issue:10Pages:2504-2517
Corresponding AuthorYu, Tingzhao(tingzhao.yu@nlpr.ia.ac.cn)
AbstractAction recognition plays a fundamental role in computer vision and video analysis. Nevertheless, extracting effective spatial-temporal features remains a challenging task. This paper proposes three simple but effective weakly semantic guided modules (SGMs) for both environment-constrained and cross-domain action recognition. The SGMs are composed of total 3-D convolution and element-wise gated operations; thus, they are efficient and easy to implement. The semantic guidance is obtained in a weakly supervised manner, in which each video clip is labeled with only an action class instead of pixel-level semantics. Benefitting from the semantic guidance, the network [called semantic guided network (SGN)] can focus on the salient parts of the video clips. Consequently, the redundant information can be reduced and the model is more robust to noise. Besides, benefitting from the intrinsic property of SGMs, SGN is totally end-to-end trainable. Quantities of experiments on both environment-constrained (e.g., Penn, HMDB-51, and UCF-101) and cross-domain (e.g., ODAR) action recognition datasets demonstrate its effectiveness. Specifically, SGN gets improvements of 3.7%, 2.1%, and 5.2% for Penn, HMDB-51, and UCF-101 than the baseline ResNet3D, respectively, and SGN ranked third place in the ODAR 2017 challenge.
KeywordSemantic guided module action recognition cross domain 3D convolution attention model
DOI10.1109/TMM.2019.2907060
Indexed BySCI
Language英语
Funding ProjectNational Natural Science Foundation of China[61773377] ; National Natural Science Foundation of China[61573352] ; National Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[91438105]
Funding OrganizationNational Natural Science Foundation of China
WOS Research AreaComputer Science ; Telecommunications
WOS SubjectComputer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS IDWOS:000489728400007
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23708
Collection模式识别国家重点实验室_先进数据分析与学习
Corresponding AuthorYu, Tingzhao
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 101408, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Yu, Tingzhao,Wang, Lingfeng,Da, Cheng,et al. Weakly Semantic Guided Action Recognition[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2019,21(10):2504-2517.
APA Yu, Tingzhao,Wang, Lingfeng,Da, Cheng,Gu, Huxiang,Xiang, Shiming,&Pan, Chunhong.(2019).Weakly Semantic Guided Action Recognition.IEEE TRANSACTIONS ON MULTIMEDIA,21(10),2504-2517.
MLA Yu, Tingzhao,et al."Weakly Semantic Guided Action Recognition".IEEE TRANSACTIONS ON MULTIMEDIA 21.10(2019):2504-2517.
Files in This Item: Download All
File Name/Size DocType Version Access License
[Tsingzao]Weakly Sem(18774KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yu, Tingzhao]'s Articles
[Wang, Lingfeng]'s Articles
[Da, Cheng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yu, Tingzhao]'s Articles
[Wang, Lingfeng]'s Articles
[Da, Cheng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yu, Tingzhao]'s Articles
[Wang, Lingfeng]'s Articles
[Da, Cheng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: [Tsingzao]Weakly Semantic Guided Action Recognition.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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