CASIA OpenIR  > 模式识别国家重点实验室  > 视频内容安全
Spatio-Temporal Attention-Based LSTM Networks for 3D Action Recognition and Detection
Song, Sijie1; Lan, Cuiling2; Xing, Junliang4; Zeng, Wenjun2,3; Liu, Jiaying1
Source PublicationIEEE TRANSACTIONS ON IMAGE PROCESSING
2018-07-01
Volume27Issue:7Pages:3459-3471
SubtypeArticle
AbstractHuman action analytics has attracted a lot of attention for decades in computer vision. It is important to extract discriminative spatio-temporal features to model the spatial and temporal evolutions of different actions. In this paper, we propose a spatial and temporal attention model to explore the spatial and temporal discriminative features for human action recognition and detection from skeleton data. We build our networks based on the recurrent neural networks with long short-term memory units. The learned model is capable of selectively focusing on discriminative joints of skeletons within each input frame and paying different levels of attention to the outputs of different frames. To ensure effective training of the network for action recognition, we propose a regularized cross-entropy loss to drive the learning process and develop a joint training strategy accordingly. Moreover, based on temporal attention, we develop a method to generate the action temporal proposals for action detection. We evaluate the proposed method on the SBU Kinect Interaction data set, the NTU RGB + D data set, and the PKU-MMD data set, respectively. Experiment results demonstrate the effectiveness of our proposed model on both action recognition and action detection.
KeywordSpatio Attention Temporal Attention Action Recognition Action Detection Skeleton Data
WOS HeadingsScience & Technology ; Technology
DOI10.1109/TIP.2018.2818328
WOS KeywordMOTION ; MODEL
Indexed BySCI
Language英语
Funding OrganizationNational Natural Science Foundation of China(61772043 ; Microsoft Research Asia Fund(FY17-RES-THEME-013) ; CCF-Tencent Open Research Fund ; 61672519)
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000430594300008
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/22007
Collection模式识别国家重点实验室_视频内容安全
Affiliation1.Peking Univ, Inst Comp Sci & Technol, Beijing 100080, Peoples R China
2.Microsoft Res Asia, Beijing 100080, Peoples R China
3.Microsoft Res Asia, Senior Leadership Team, Beijing 100080, Peoples R China
4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100080, Peoples R China
Recommended Citation
GB/T 7714
Song, Sijie,Lan, Cuiling,Xing, Junliang,et al. Spatio-Temporal Attention-Based LSTM Networks for 3D Action Recognition and Detection[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2018,27(7):3459-3471.
APA Song, Sijie,Lan, Cuiling,Xing, Junliang,Zeng, Wenjun,&Liu, Jiaying.(2018).Spatio-Temporal Attention-Based LSTM Networks for 3D Action Recognition and Detection.IEEE TRANSACTIONS ON IMAGE PROCESSING,27(7),3459-3471.
MLA Song, Sijie,et al."Spatio-Temporal Attention-Based LSTM Networks for 3D Action Recognition and Detection".IEEE TRANSACTIONS ON IMAGE PROCESSING 27.7(2018):3459-3471.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Song, Sijie]'s Articles
[Lan, Cuiling]'s Articles
[Xing, Junliang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Song, Sijie]'s Articles
[Lan, Cuiling]'s Articles
[Xing, Junliang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Song, Sijie]'s Articles
[Lan, Cuiling]'s Articles
[Xing, Junliang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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