Spatio-Temporal Dynamic Interlaced Network for 3D human pose estimation in video

Open Webpage

Feiyi Xu, Jifan Wang, Ying Sun, Jin Qi, Zhenjiang Dong, Yanfei Sun

Published: 01 Jan 2025, Last Modified: 25 Jul 2025Comput. Vis. Image Underst. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•A spatio-temporal dynamic interlaced network, containing DSGCE and ITTE blocks.•Designing purposeful dynamic and static adjacency matrices to model spatial features.•Introducing a global–local interlaced mechanism to reduce motion interference.