Metraipolis › archive › dc_cd6b163166b7

Frame-Level Temporal Alignment for Human-to-Robot Visual Adaptation — arXiv:2610.04372

Source
arXiv
Original
https://arxiv.org/abs/2610.04372
License (as archived)
CC0-1.0
Archived
2026-10-06T05:32:06.144Z
SHA-256 of the archived text
f0cd0add7eb9895fb56a755e5152c31e4da1e447da3c4ba2f68c630c2b7a1f1f
Stable URL of this page
https://metraipolis.com/documento/dc_cd6b163166b7

How to cite

Frame-Level Temporal Alignment for Human-to-Robot Visual Adaptation — arXiv:2610.04372 — arXiv, https://arxiv.org/abs/2610.04372 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd6b163166b7 (Metraipolis archive dc_cd6b163166b7, sha256 f0cd0add7eb9895fb56a755e5152c31e4da1e447da3c4ba2f68c630c2b7a1f1f)
BibTeX
@misc{dccd6b163166b7,
  title = {Frame-Level Temporal Alignment for Human-to-Robot Visual Adaptation — arXiv:2610.04372},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04372},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd6b163166b7; sha256 f0cd0add7eb9895fb56a755e5152c31e4da1e447da3c4ba2f68c630c2b7a1f1f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04372. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Transferring visual representations pretrained on human videos to robot manipulation requires learning reliable correspondences between human and robot demonstrations. However, paired demonstrations can differ in execution rate and in the proportion of non-key frames that do not directly reflect task progress. Frames at the same relative timestamp may therefore represent different task stages, which can cause correspondence learning to fail. To address these issues, we propose Frame-Level Temporal Alignment (FLTA), a framework that uses two temporal priors to adapt visual encoders pretrained on human videos for robot manipulation. It learns shared task-progress representations without frame-level correspondence annotations, allowing frames at different relative temporal positions to match. A global progress prior combines normalized temporal positions with visual similarity to construct a soft correspondence target. A local temporal order prior penalizes backward transitions while allowing stays and varying forward rates to accommodate execution-rate differences. With ResNet-50 and ViT encoders, our method achieves relative improvements of 46.93% and 65.96%, respectively, over the best baselines in average simulation success rates and achieves higher task success rates on real-world manipulation tasks. These results also suggest that effective human-robot adaptation depends less on the number of parameters updated than on which parameters are selected. Our project page is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.04372 — 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 2026-10-06T05:27:05.961Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).