Metraipolis › archive › dc_6bf1c8a8208d
Semantic Residual Vector Quantization for Sign Language Generation — arXiv:2611.06781
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06781
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:30:11.847Z
- SHA-256 of the archived text
ba3bedc67277dfabb85e7d4cd3a0e7c73d3a341246c7719fc2bbee2b4284be11- Stable URL of this page
https://metraipolis.com/documento/dc_6bf1c8a8208d
How to cite
Semantic Residual Vector Quantization for Sign Language Generation — arXiv:2611.06781 — arXiv (en), https://arxiv.org/abs/2611.06781 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6bf1c8a8208d (Metraipolis archive dc_6bf1c8a8208d, sha256 ba3bedc67277dfabb85e7d4cd3a0e7c73d3a341246c7719fc2bbee2b4284be11)
BibTeX
@misc{dc6bf1c8a8208d,
title = {Semantic Residual Vector Quantization for Sign Language Generation — arXiv:2611.06781},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06781},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6bf1c8a8208d; sha256 ba3bedc67277dfabb85e7d4cd3a0e7c73d3a341246c7719fc2bbee2b4284be11},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06781. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Sign language generation (SLG) maps written sentences into signing motion while preserving both lexical content and fine-grained articulation. This requires a model to decide what signs should be expressed and to realize them through precise handshape, trajectory, facial expression and body coordination. Existing pose-based systems and reconstruction-only motion tokenizers often entangle these two decisions, leaving the generator without an explicit text-aligned intermediate target for what to sign before refining how to sign it. To address this issue, we introduce Semantic Residual Vector Quantization (SRVQ), a framework for SLG that frames generation as a two-level process moving from semantics to kinematics. The newly introduced SRV Quantizer learns a hierarchy in which the first residual level encodes sign content and subsequent levels refine pose, handshape, trajectory, and body coordination, all within a single quantizer and without separate semantic representations or external planning stages. Through word-aware conditioning for hierarchical code generation, a masked semantic generator predicts semantic codes and a kinematic generator completes the residual codes for full SMPL-X motion synthesis. We evaluate using retrieval and FID in a shared text-motion embedding space, alongside standard geometric metrics. On CSL-Daily and Phoenix-2014T, SRVQ achieves R@1 of 82.3 and 70.3, outperforming the previous SOTA by 30 and 46 points, respectively. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.06781 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-05T18:19:49.064Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).