Metraipolis › archive › dc_8d2f48fa765b

SeRV: Semantic-Aligned Residual Vector Quantization for American Sign Language Generation — arXiv:2609.05742

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.05742
License (as archived): CC0-1.0
Archived: 2026-10-16T15:06:36.327Z
SHA-256 of the archived text: ac5c41f86f27c82174ffae2de5f12854e2aa9d90033480257e2301db3dfa54c6
Stable URL of this page: https://metraipolis.com/documento/dc_8d2f48fa765b

How to cite

SeRV: Semantic-Aligned Residual Vector Quantization for American Sign Language Generation — arXiv:2609.05742 — arXiv (en), https://arxiv.org/abs/2609.05742 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8d2f48fa765b (Metraipolis archive dc_8d2f48fa765b, sha256 ac5c41f86f27c82174ffae2de5f12854e2aa9d90033480257e2301db3dfa54c6)

BibTeX

@misc{dc8d2f48fa765b,
  title = {SeRV: Semantic-Aligned Residual Vector Quantization for American Sign Language Generation — arXiv:2609.05742},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05742},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8d2f48fa765b; sha256 ac5c41f86f27c82174ffae2de5f12854e2aa9d90033480257e2301db3dfa54c6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05742. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

American Sign Language (ASL) generation remains challenging due to limited paired text-ASL motion data and the difficulty of learning motion representations both precise for reconstruction and predictable from linguistic input. Existing methods rely on motion tokenizers optimized for reconstruction, without explicit semantic supervision from paired text. As a result, the learned tokens remain limited in supporting semantically consistent and fine-grained ASL motion generation. To address this limitation, we propose SeRV (Semantic-Aligned Residual Vector Quantization), a semantic-aligned RVQ tokenizer for ASL generation. SeRV learns a semantically structured residual token space by combining global-level motion-text alignment with token-level text-conditioned supervision. Building on this tokenizer, a Hierarchical GPT predicts residual motion tokens in a coarse-to-fine manner, generating structurally coherent and semantically aligned 3D ASL motion. We further construct a large-scale reconstructed 3D ASL motion-text benchmark by recovering paired 3D motion from OpenASL videos. Experiments on How2Sign and OpenASL show that SeRV outperforms six state-of-the-art baselines, with user studies assessing reconstruction quality and semantic fidelity. Samples of our reconstructed 3D ASL motion are available on our project page: this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.05742 — 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 2026-10-16T14:49:56.997Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).