CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Body Joint Guided 3-D Deep Convolutional Descriptors for Action Recognition
Cao, Congqi1,2; Zhang, Yifan1,2; Zhang, Chunjie2,3; Lu, Hanqing1,2
Source PublicationIEEE TRANSACTIONS ON CYBERNETICS
2018-03-01
Volume48Issue:3Pages:1095-1108
SubtypeArticle
Abstract3-D convolutional neural networks (3-D CNNs) have been established as a powerful tool to simultaneously learn features from both spatial and temporal dimensions, which is suitable to be applied to video-based action recognition. In this paper, we propose not to directly use the activations of fully connected layers of a 3-D CNN as the video feature, but to use selective convolutional layer activations to form a discriminative descriptor for video. It pools the feature on the convolutional layers under the guidance of body joint positions. Two schemes of mapping body joints into convolutional feature maps for pooling are discussed. The body joint positions can be obtained from any off-the-shelf skeleton estimation algorithm. The helpfulness of the body joint guided feature pooling with inaccurate skeleton estimation is systematically evaluated. To make it end-to-end and do not rely on any sophisticated body joint detection algorithm, we further propose a two-stream bilinear model which can learn the guidance from the body joints and capture the spatio-temporal features simultaneously. In this model, the body joint guided feature pooling is conveniently formulated as a bilinear product operation. Experimental results on three real-world datasets demonstrate the effectiveness of body joint guided pooling which achieves promising performance.
KeywordAction Recognition Body Joints Convolutional Networks Feature Pooling Two-stream Bilinear Model
WOS HeadingsScience & Technology ; Technology
DOI10.1109/TCYB.2017.2756840
WOS KeywordCLASSIFICATION ; TRAJECTORIES ; HISTOGRAMS ; PARTS
Indexed BySCI
Language英语
Funding OrganizationNational Natural Science Foundation of China(61332016 ; Youth Innovation Promotion Association CAS ; 61572500)
WOS Research AreaAutomation & Control Systems ; Computer Science
WOS SubjectAutomation & Control Systems ; Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS IDWOS:000424826800022
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/20410
Collection模式识别国家重点实验室_图像与视频分析
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Inst Automat, Res Ctr Brain Inspired Intelligence, Beijing 100190, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Cao, Congqi,Zhang, Yifan,Zhang, Chunjie,et al. Body Joint Guided 3-D Deep Convolutional Descriptors for Action Recognition[J]. IEEE TRANSACTIONS ON CYBERNETICS,2018,48(3):1095-1108.
APA Cao, Congqi,Zhang, Yifan,Zhang, Chunjie,&Lu, Hanqing.(2018).Body Joint Guided 3-D Deep Convolutional Descriptors for Action Recognition.IEEE TRANSACTIONS ON CYBERNETICS,48(3),1095-1108.
MLA Cao, Congqi,et al."Body Joint Guided 3-D Deep Convolutional Descriptors for Action Recognition".IEEE TRANSACTIONS ON CYBERNETICS 48.3(2018):1095-1108.
Files in This Item: Download All
File Name/Size DocType Version Access License
曹聪琦_T-Cybernetics_Bo(1731KB)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
[Cao, Congqi]'s Articles
[Zhang, Yifan]'s Articles
[Zhang, Chunjie]'s Articles
Baidu academic
Similar articles in Baidu academic
[Cao, Congqi]'s Articles
[Zhang, Yifan]'s Articles
[Zhang, Chunjie]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Cao, Congqi]'s Articles
[Zhang, Yifan]'s Articles
[Zhang, Chunjie]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 曹聪琦_T-Cybernetics_Body Joint guided 3D Deep Convolutional Descriptors for 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.