Metraipolis › archive › dc_c468280c133f

Do Motion Tokenizers for Co-Speech Gesture Generation Encode Gesture Semantics? — arXiv:2610.03765

Source
arXiv
Original
https://arxiv.org/abs/2610.03765
License (as archived)
CC0-1.0
Archived
2026-10-06T05:25:48.669Z
SHA-256 of the archived text
d3d2b79bbf03965ed3b896bf670160794396bfbe31cd7c61e96cf94d32236176
Stable URL of this page
https://metraipolis.com/documento/dc_c468280c133f

How to cite

Do Motion Tokenizers for Co-Speech Gesture Generation Encode Gesture Semantics? — arXiv:2610.03765 — arXiv, https://arxiv.org/abs/2610.03765 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c468280c133f (Metraipolis archive dc_c468280c133f, sha256 d3d2b79bbf03965ed3b896bf670160794396bfbe31cd7c61e96cf94d32236176)
BibTeX
@misc{dcc468280c133f,
  title = {Do Motion Tokenizers for Co-Speech Gesture Generation Encode Gesture Semantics? — arXiv:2610.03765},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03765},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c468280c133f; sha256 d3d2b79bbf03965ed3b896bf670160794396bfbe31cd7c61e96cf94d32236176},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03765. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Discrete motion tokenizers encode motion as atomic units and are widely used for co-speech gesture generation. It remains unclear which motion properties, especially those relevant to gesture semantics, are recoverable from these codebooks. We probe a reconstruction-trained codebook using 19 co-speech gesture descriptors spanning from raw motion to abstract communicative function. Results show that geometry and handedness are readily decodable from token embeddings, while motion category is only weakly decoded despite showing systematic differences in discrete code usage. This gap between reconstruction quality and descriptor decodability suggests that reconstruction objectives alone do not guarantee that gesture semantics are captured, and that evaluating codebooks on such properties can guide the design of more semantic motion tokenizers.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.03765 — 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 2026-10-06T05:24:05.738Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).