• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Sun, Yuechao (Sun, Yuechao.) | Kong, Dehui (Kong, Dehui.) | Li, Jinghua (Li, Jinghua.) | Yin, Baocai (Yin, Baocai.)

Indexed by:

EI Scopus

Abstract:

Capturing the hidden relationships in 2D pose sequences is crucial for accurate 3D human pose estimation(HPE). Recent studies have shown that frequency domain information, independent of spatio-temporal information, has strong capabilities on representing the pose sequences. However, there are few works exploring more appropriate ways to fuse these different kinds of information. In this paper, we propose an alternating cyclic approach for fusing spatio-temporal information and frequency information to achieve accurate 3D human pose estimation. The designed alternating cyclic fusion network allows for a more comprehensive integration of different features, leading to improved accuracy. By leveraging feature splitting and time-frequency convolution, the existing features are processed more appropriately, and achieving model lightweighting. Experimental results demonstrate that our approach achieves comparable accuracy to state-of-the-art methods while significantly outperforming mainstream methods in terms of model lightweighting. In conclusion, the introduction of frequency domain information is of great significance for pose estimation tasks. © 2024 SPIE. All rights reserved.

Keyword:

Computer vision Frequency estimation Frequency domain analysis

Author Community:

  • [ 1 ] [Sun, Yuechao]Beijing University of Technology, China
  • [ 2 ] [Kong, Dehui]Beijing University of Technology, China
  • [ 3 ] [Li, Jinghua]Beijing University of Technology, China
  • [ 4 ] [Yin, Baocai]Beijing University of Technology, China

Reprint Author's Address:

Email:

Show more details

Related Keywords:

Related Article:

Source :

ISSN: 0277-786X

Year: 2024

Volume: 13089

Language: English

Cited Count:

WoS CC Cited Count:

SCOPUS Cited Count:

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 1

Affiliated Colleges:

Online/Total:750/5313031
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.