中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 视频内容安全团队
Hierarchical Contextual Refinement Networks for Human Pose Estimation

文献类型：期刊论文

作者Nie, Xuecheng1; Feng, Jiashi1; Xing, Junliang2; Xiao, Shengtao3; Yan, Shuicheng1,3
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2019-02-01
卷号28期号:2页码:924-936
关键词Human pose estimation joint complexity-aware hierarchical contextual refinement network
ISSN号1057-7149
DOI10.1109/TIP.2018.2872628
通讯作者Nie, Xuecheng(niexuecheng@u.nus.edu)
英文摘要Predicting 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.
WOS关键词PICTORIAL STRUCTURES ; FLEXIBLE MIXTURES ; RECOGNITION ; PEOPLE ; PARTS
资助项目NUS[IDS R-263-000-C67-646] ; ECRA[R-263-000-C87-133] ; MOE Tier-II[R-263-000-D17-112]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000448501800007
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构NUS ; ECRA ; MOE Tier-II
源URL[http://ir.ia.ac.cn/handle/173211/22806]  
专题自动化研究所_模式识别国家重点实验室_视频内容安全团队
通讯作者Nie, Xuecheng
作者单位1.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
推荐引用方式
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.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。