Fast Human Pose Estimation

被引:163
|
作者
Zhang, Feng [1 ]
Zhu, Xiatian [2 ]
Ye, Mao [1 ]
机构
[1] Univ Elect Sci & Technol China, Sch Comp Sci & Engn, Chengdu, Peoples R China
[2] Vis Semant Ltd, London, England
基金
中国国家自然科学基金;
关键词
D O I
10.1109/CVPR.2019.00363
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Existing human pose estimation approaches often only consider how to improve the model generalisation performance, but putting aside the significant efficiency problem. This leads to the development of heavy models with poor scalability and cost-effectiveness in practical use. In this work, we investigate the under-studied but practically critical pose model efficiency problem. To this end, we present a new Fast Pose Distillation (FPD) model learning strategy. Specifically, the FPD trains a lightweight pose neural network architecture capable of executing rapidly with low computational cost. It is achieved by effectively transferring the pose structure knowledge of a strong teacher network. Extensive evaluations demonstrate the advantages of our FPD method over a broad range of state-of-the-art pose estimation approaches in terms of model cost-effectiveness on two standard benchmark datasets, MPII Human Pose and Leeds Sports Pose.
引用
收藏
页码:3512 / 3521
页数:10
相关论文
共 50 条
  • [1] Fast and Lightweight Human Pose Estimation
    Ren, Haopan
    Wang, Wenming
    Zhang, Kaixiang
    Wei, Dejian
    Gao, Yanyan
    Sun, Yue
    [J]. IEEE ACCESS, 2021, 9 : 49576 - 49589
  • [2] An Approach for Fast Human Head Pose Estimation
    Yari, Yessenia
    Scharcanski, Jacob
    [J]. MOBILE MULTIMEDIA/IMAGE PROCESSING, SECURITY, AND APPLICATIONS 2011, 2011, 8063
  • [3] Fast and Flexible Human Pose Estimation with HyperPose
    Guo, Yixiao
    Liu, Jiawei
    Li, Guo
    Mai, Luo
    Dong, Hao
    [J]. PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2021, 2021, : 3763 - 3766
  • [4] A Fast and Effective Transformer for Human Pose Estimation
    Wang, Dong
    Xie, Wenjun
    Cai, Youcheng
    Liu, Xiaoping
    [J]. IEEE SIGNAL PROCESSING LETTERS, 2022, 29 : 992 - 996
  • [5] Fast Human Pose Estimation in Compressed Videos
    Liu, Huan
    Liu, Wentao
    Chi, Zhixiang
    Wang, Yang
    Yu, Yuanhao
    Chen, Jun
    Tang, Jin
    [J]. IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 : 1390 - 1400
  • [6] Fast Head Pose Estimation for Human-Computer Interaction
    Garcia-Montero, Mario
    Redondo-Cabrera, Carolina
    Lopez-Sastre, Roberto
    Tuytelaars, Tinne
    [J]. PATTERN RECOGNITION AND IMAGE ANALYSIS (IBPRIA 2015), 2015, 9117 : 101 - 110
  • [7] Fast and Scalable Human Pose Estimation using mmWave Point Cloud
    An, Sizhe
    Ogras, Umit Y.
    [J]. PROCEEDINGS OF THE 59TH ACM/IEEE DESIGN AUTOMATION CONFERENCE, DAC 2022, 2022, : 889 - 894
  • [8] FastNet: Fast high-resolution network for human pose estimation
    Luo, Yanmin
    Ou, Zhilong
    Wan, Tianjun
    Guo, Jing-Ming
    [J]. IMAGE AND VISION COMPUTING, 2022, 119
  • [9] Fast and compact driver pose estimation
    Nishiyuki, Kenta
    Hyuga, Tadashi
    Tasaki, Hiroshi
    Kinoshita, Koichi
    Hasegawa, Yuki
    Yamashita, Takayoshi
    Fujiyoshi, Hironobu
    [J]. Transactions of the Japanese Society for Artificial Intelligence, 2020, 35 (06) : 1 - 10
  • [10] THANet: Transferring Human Pose Estimation to Animal Pose Estimation
    Liao, Jincheng
    Xu, Jianzhong
    Shen, Yunhang
    Lin, Shaohui
    [J]. ELECTRONICS, 2023, 12 (20)