SCOPUS
0Citation Export
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ma, Xiaohan | - |
dc.contributor.author | Jin, Rize | - |
dc.contributor.author | Chung, Tae Sun | - |
dc.date.issued | 2024-01-01 | - |
dc.identifier.uri | https://aurora.ajou.ac.kr/handle/2018.oak/37104 | - |
dc.identifier.uri | https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85195911057&origin=inward | - |
dc.description.abstract | The task of Sign Language Production (SLP) in machine learning involves converting text-based spoken language into corresponding sign language expressions. Sign language conveys meaning through the continuous movement of multiple articulators, including manual and non-manual channels. However, most current Transformer-based SLP models convert these multi-channel sign poses into a unified feature representation, ignoring the inherent structural correlations between channels. This paper introduces a novel approach called MCST-Transformer for skeletal sign language production. It employs multi-channel spatial attention to capture correlations across various channels within each frame, and temporal attention to learn sequential dependencies for each channel over time. Additionally, the paper explores and experiments with multiple fusion techniques to combine the spatial and temporal representations into naturalistic sign sequences. To validate the effectiveness of the proposed MCST-Transformer model and its constituent components, extensive experiments were conducted on two benchmark sign language datasets from diverse cultures. The results demonstrate that this new approach outperforms state-of-the-art models on both datasets. | - |
dc.description.sponsorship | This work was supported by the Institute of Information & communications Technology Planning & Evaluation (IITP) under the Artificial Intelligence Convergence Innovation Human Resources Development (IITP-2024-RS-2023-00255968) grant, the ITRC (Information Technology Research Center) support program (IITP-2021-0-02051) funded by the Korea government (MSIT), and the Foreign Intelligence support program funded by Shijiazhuang Science and Technology Bureau (Project No. 20240024). | - |
dc.language.iso | eng | - |
dc.publisher | European Language Resources Association (ELRA) | - |
dc.subject.mesh | Language production | - |
dc.subject.mesh | Machine-learning | - |
dc.subject.mesh | Multi channel | - |
dc.subject.mesh | Production models | - |
dc.subject.mesh | Sign language | - |
dc.subject.mesh | Sign language production | - |
dc.subject.mesh | Spatio-temporal | - |
dc.subject.mesh | Spatio-temporal fusions | - |
dc.subject.mesh | Spoken languages | - |
dc.subject.mesh | Transformer | - |
dc.title | Multi-Channel Spatio-Temporal Transformer for Sign Language Production | - |
dc.type | Conference | - |
dc.citation.conferenceDate | 2024.5.20. ~ 2024.5.25. | - |
dc.citation.conferenceName | Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024 | - |
dc.citation.edition | 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings | - |
dc.citation.endPage | 11712 | - |
dc.citation.startPage | 11699 | - |
dc.citation.title | 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings | - |
dc.identifier.bibliographicCitation | 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings, pp.11699-11712 | - |
dc.identifier.scopusid | 2-s2.0-85195911057 | - |
dc.subject.keyword | Sign Language Production | - |
dc.subject.keyword | Spatio-Temporal Fusion | - |
dc.subject.keyword | Transformer | - |
dc.type.other | Conference Paper | - |
dc.subject.subarea | Theoretical Computer Science | - |
dc.subject.subarea | Computational Theory and Mathematics | - |
dc.subject.subarea | Computer Science Applications | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.