Spatial-Temporal Graph Transformer With Sign Mesh Regression for Skinned-Based Sign Language Production
文献类型：期刊论文
| 作者 | Cui, Zhenchao2,3; Chen, Ziang2,3; Li, Zhaoxin1; Wang, Zhaoqi1 |
| 刊名 | IEEE ACCESS
 |
| 出版日期 | 2022 |
| 卷号 | 10页码:127530-127539 |
| ISSN号 | 2169-3536 |
| 关键词 | Transformer graph convolution human mesh reconstruction sign language production |
| DOI | 10.1109/ACCESS.2022.3227042 |
| 英文摘要 | 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. |
| 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 |
| 语种 | 英语 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| WOS记录号 | WOS:000899181500001 |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/20163]  |
| 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.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.Hebei Univ, Hebei Machine Vis Engn Res Ctr, Baoding 071002, Peoples R China 3.Hebei Univ, Sch Cyber Secur & Comp, Baoding 071002, 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. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。