Spatial-Temporal Graph Transformer With Sign Mesh Regression for Skinned-Based Sign Language Production

doi:10.1109/ACCESS.2022.3227042

	Spatial-Temporal Graph Transformer With Sign Mesh Regression for Skinned-Based Sign Language Production
	Cui, Zhenchao 1,2; Chen, Ziang 1,2; Li, Zhaoxin 3; Wang, Zhaoqi 3
	2022
发表期刊	IEEE ACCESS
ISSN	2169-3536
卷号	10 页码:127530-127539
摘要	Sign language production aims to automatically generate coordinated sign language videos from spoken language. As a typical sequence to sequence task, the existing methods are mostly to regard the skeletons as a whole sequence, however, those do not take the rich graph information among both joints and edges into consideration. In this paper, we propose a novel method named Spatial-Temporal Graph Transformer (STGT) to deal with this problem. Specifically, according to kinesiology, we first design a novel graph representation to achieve graph features from skeletons. Then the spatial-temporal graph self-attention utilizes graph topology to capture the intra-frame and inter-frame correlations, respectively. Our key innovation is that the attention maps are calculated on both spatial and temporal dimensions in turn, meanwhile, graph convolution is used to strengthen the short-term features of skeletal structure. Finally, due to the generated skeletons are based on the form of skeleton points and lines so far. In order to visualize the generated sign language videos, we design a sign mesh regression module to render the skeletons into skinned animations including body and hands posture. Comparing with states of art baseline on RWTH-PHONEIX Weather-2014T in Experiment Section, STGT can obtain the highest values on BLEU and ROUGE, which indicates our method produces most accurate and intuitive sign language videos.
关键词	Transformer graph convolution human mesh reconstruction sign language production
DOI	10.1109/ACCESS.2022.3227042
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2020YFC1523302] ; Post-Graduate's Innovation Fund Project of Hebei University[HBU2022ss014] ; National Natural Science Foundation of China[62172392] ; Scientific Research Foundation for Talented Scholars of Hebei University[521100221081] ; Scientific Research Foundation of Colleges and Universities in Hebei Province[QN2022107]
WOS研究方向	Computer Science ; Engineering ; Telecommunications
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:000899181500001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/20164
专题	中国科学院计算技术研究所期刊论文
通讯作者	Li, Zhaoxin
作者单位	1.Hebei Univ, Sch Cyber Secur & Comp, Baoding 071002, Peoples R China 2.Hebei Univ, Hebei Machine Vis Engn Res Ctr, Baoding 071002, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Cui, Zhenchao,Chen, Ziang,Li, Zhaoxin,et al. Spatial-Temporal Graph Transformer With Sign Mesh Regression for Skinned-Based Sign Language Production[J]. IEEE ACCESS,2022,10:127530-127539.
APA	Cui, Zhenchao,Chen, Ziang,Li, Zhaoxin,&Wang, Zhaoqi.(2022).Spatial-Temporal Graph Transformer With Sign Mesh Regression for Skinned-Based Sign Language Production.IEEE ACCESS,10,127530-127539.
MLA	Cui, Zhenchao,et al."Spatial-Temporal Graph Transformer With Sign Mesh Regression for Skinned-Based Sign Language Production".IEEE ACCESS 10(2022):127530-127539.