Metraipolis › archive › dc_f41aa6a7af76

EgoGeneralist: Unifying Egocentric Action-Video Tasks through Video-Native Modeling — arXiv:2611.08477

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08477
License (as archived)
CC0-1.0
Archived
2026-11-06T14:53:48.668Z
SHA-256 of the archived text
586ced9973f6b4ca6c164fd65a63d503299d485019155edd9a3d5a4868774180
Stable URL of this page
https://metraipolis.com/documento/dc_f41aa6a7af76

How to cite

EgoGeneralist: Unifying Egocentric Action-Video Tasks through Video-Native Modeling — arXiv:2611.08477 — arXiv (en), https://arxiv.org/abs/2611.08477 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f41aa6a7af76 (Metraipolis archive dc_f41aa6a7af76, sha256 586ced9973f6b4ca6c164fd65a63d503299d485019155edd9a3d5a4868774180)
BibTeX
@misc{dcf41aa6a7af76,
  title = {EgoGeneralist: Unifying Egocentric Action-Video Tasks through Video-Native Modeling — arXiv:2611.08477},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08477},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f41aa6a7af76; sha256 586ced9973f6b4ca6c164fd65a63d503299d485019155edd9a3d5a4868774180},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08477. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern video models possess strong visual priors, yet do not natively represent human action in metric 3D space. We present EgoGeneralist, which adapts pretrained video generators to unify action-conditioned egocentric video generation, pose estimation, and joint action-video generation. Our role-adaptive action renderer provides video-native representations for multidirectional action-video learning, making metric motion usable as both a spatial control signal and a recoverable generation target. Cross-stream action-video coupling establishes close correspondence between metric motion and visual dynamics through lightweight adaptation while preserving the pretrained visual prior. Together, these designs establish a generalist framework spanning five action-video tasks. Despite adaptation only on controlled laboratory recordings, EgoGeneralist generalizes to diverse unseen scenes and interactions with effective action control and visual quality, bridging pretrained visual knowledge and metric 3D human motion.

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/2611.08477 — 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 2026-11-06T14:25:42.631Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).