CASIA OpenIR  > 视频内容安全团队
Hierarchical Contextual Refinement Networks for Human Pose Estimation
Nie, Xuecheng1; Feng, Jiashi1; Xing, Junliang2; Xiao, Shengtao3; Yan, Shuicheng1,3
Source PublicationIEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN1057-7149
2019-02-01
Volume28Issue:2Pages:924-936
Corresponding AuthorNie, Xuecheng(niexuecheng@u.nus.edu)
AbstractPredicting human pose in the wild is a challenging problem due to high flexibility of joints and possible occlusion. Existing approaches generally tackle the difficulties either by holistic prediction or multi-stage processing, which suffer from poor performance for locating challenging joints or high computational cost. In this paper, we propose a new hierarchical contextual refinement network (HCRN) to robustly predict human poses in an efficient manner, where human body joints of different complexities are processed at different layers in a context hierarchy. Different from existing approaches, our proposed model predicts positions of joints from easy to difficult in a single stage through effectively exploiting informative contexts provided in the previous layer. Such approach offers two appealing advantages over state-of-the-arts: 1) more accurate than predicting all the joints together and 2) more efficient than multi-stage processing methods. We design a contextual refinement unit (CRU) to implement the proposed model, which enables auto-diffusion of joint detection results to effectively transfer informative context from easy joints to difficult ones. In this way, difficult joints can be reliably detected even in presence of occlusion or severe distracting factors. Multiple CRUs are organized into a tree-structured hierarchy which is end-to-end trainable and does not require processing joints for multiple iterations. Comprehensive experiments evaluate the efficacy and efficiency of the proposed HCRN model to improve well-established baselines and achieve the new state-of-the-art on multiple human pose estimation benchmarks.
KeywordHuman pose estimation joint complexity-aware hierarchical contextual refinement network
DOI10.1109/TIP.2018.2872628
WOS KeywordPICTORIAL STRUCTURES ; FLEXIBLE MIXTURES ; RECOGNITION ; PEOPLE ; PARTS
Indexed BySCI
Language英语
Funding ProjectNUS[IDS R-263-000-C67-646] ; ECRA[R-263-000-C87-133] ; MOE Tier-II[R-263-000-D17-112]
Funding OrganizationNUS ; ECRA ; MOE Tier-II
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000448501800007
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/22807
Collection视频内容安全团队
Corresponding AuthorNie, Xuecheng
Affiliation1.Natl Univ Singapore, ECE Dept, Learning & Vis Lab, Singapore 117583, Singapore
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
3.Qihoo 360 AI Inst, Beijing 100016, Peoples R China
Recommended Citation
GB/T 7714
Nie, Xuecheng,Feng, Jiashi,Xing, Junliang,et al. Hierarchical Contextual Refinement Networks for Human Pose Estimation[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2019,28(2):924-936.
APA Nie, Xuecheng,Feng, Jiashi,Xing, Junliang,Xiao, Shengtao,&Yan, Shuicheng.(2019).Hierarchical Contextual Refinement Networks for Human Pose Estimation.IEEE TRANSACTIONS ON IMAGE PROCESSING,28(2),924-936.
MLA Nie, Xuecheng,et al."Hierarchical Contextual Refinement Networks for Human Pose Estimation".IEEE TRANSACTIONS ON IMAGE PROCESSING 28.2(2019):924-936.
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
[Nie, Xuecheng]'s Articles
[Feng, Jiashi]'s Articles
[Xing, Junliang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Nie, Xuecheng]'s Articles
[Feng, Jiashi]'s Articles
[Xing, Junliang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Nie, Xuecheng]'s Articles
[Feng, Jiashi]'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.