Metraipolis › archive › dc_f379dc80aa39

Zero-Shot Skeleton-Based Action Anticipation — arXiv:2608.14243

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14243
License (as archived)
CC0-1.0
Archived
2026-10-19T04:04:27.947Z
SHA-256 of the archived text
b8e728a40987bec2680ec41f2c2274bfbe537c1cdb17482b51f54844900814a4
Stable URL of this page
https://metraipolis.com/documento/dc_f379dc80aa39

How to cite

Zero-Shot Skeleton-Based Action Anticipation — arXiv:2608.14243 — arXiv (en), https://arxiv.org/abs/2608.14243 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f379dc80aa39 (Metraipolis archive dc_f379dc80aa39, sha256 b8e728a40987bec2680ec41f2c2274bfbe537c1cdb17482b51f54844900814a4)
BibTeX
@misc{dcf379dc80aa39,
  title = {Zero-Shot Skeleton-Based Action Anticipation — arXiv:2608.14243},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14243},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f379dc80aa39; sha256 b8e728a40987bec2680ec41f2c2274bfbe537c1cdb17482b51f54844900814a4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14243. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Action anticipation (AA) aims to recognize ongoing human or humanoids actions from partial observations, enabling robots to predict intentions before the actions are completed. Although skeleton-based AA offers efficiency advantages, existing approaches assume that all action classes are seen during training, which limits their deployment in real-world scenarios where novel actions inevitably arise. To address this gap, we study the new task of Zero-Shot Skeleton-Based Action Anticipation (ZS-SkAA). This task requires recognizing unseen action classes using only limited early-stage skeleton sequences, combining the challenges of partial observations, temporal dynamics, and zero-shot generalization. To establish foundational research for ZS-SkAA, we introduce:(1) A baseline model comprising a spatio-temporal feature extractor and a mutual information estimation and maximization module. This baseline model explicitly aligns partial visual features with semantic class embeddings across modalities by estimating and maximizing their mutual information, enhancing generalization to unseen classes.(2) A benchmark protocol using the NTU RGB+D dataset, which is adapted for rigorous ZS-SkAA evaluation. Experiments demonstrate the effectiveness of our model as a strong baseline for ZS-SkAA, achieving high zero-shot accuracy on NTU RGB+D. This work establishes ZS-SkAA as a vital research direction for real-world systems requiring generalization to novel actions.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-17 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.14243 — 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 2026-10-19T03:57:57.946Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).