TMS-Net: A multi-feature multi-stream multi-level information sharing network for skeleton-based sign language recognition

Open Webpage

Zhiwen Deng, Yuquan Leng, Junkang Chen, Xiang Yu, Yang Zhang, Qing Gao

Published: 01 Jan 2024, Last Modified: 12 Nov 2025Neurocomputing 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•A universal skeleton multi-feature has been proposed to characterize sign language motions from different perspectives.•An end-to-end multi-stream network architecture has been constructed to efficiently extract multiple feature information from the input.•A universal multi-level information sharing mechanism has been designed.