Metraipolis › archive › dc_95108ef79446

Single-Query Person-Centric Bimanual Hand-Object Interaction Detection — arXiv:2609.12155

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12155
License (as archived)
CC0-1.0
Archived
2026-10-16T03:57:30.568Z
SHA-256 of the archived text
77c2847d0fc2fd66375260a9ffd3dde5a3e6fe940459243bcd9b5732f415e6e3
Stable URL of this page
https://metraipolis.com/documento/dc_95108ef79446

How to cite

Single-Query Person-Centric Bimanual Hand-Object Interaction Detection — arXiv:2609.12155 — arXiv (en), https://arxiv.org/abs/2609.12155 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_95108ef79446 (Metraipolis archive dc_95108ef79446, sha256 77c2847d0fc2fd66375260a9ffd3dde5a3e6fe940459243bcd9b5732f415e6e3)
BibTeX
@misc{dc95108ef79446,
  title = {Single-Query Person-Centric Bimanual Hand-Object Interaction Detection — arXiv:2609.12155},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12155},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_95108ef79446; sha256 77c2847d0fc2fd66375260a9ffd3dde5a3e6fe940459243bcd9b5732f415e6e3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12155. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Understanding person-level bi-manual interactions requires not only detecting hands, but also identifying which two hands belong to the same person and what each hand interacts with. Existing hand--object interaction methods are mostly hand-centric: they treat each hand as an independent instance, which can lead to ambiguous ownership in multi-person scenes. We propose a person-centric formulation in which a single query predicts a structured output for one person, including the human box, body pose, hand boxes and states, and interaction targets. We introduce part-aware deformable attention to allocate attention across human, hand, and pose-specific reference regions, enabling one query to capture the full person structure. We further unify detection and interaction reasoning with a hand-to-query relationship matrix, where each hand selects its interaction target from the detected query set plus a learnable off token, directly recovering the target's box and class without separate object regression. We build a COCO-based dataset with person-centric bi-manual interaction annotations and define structured metrics for evaluating hand states and complete hand--object tuples. Experiments with a transformer-based detector show that our formulation improves person-level bi-manual interaction parsing and provides an effective unified framework for joint detection, pose estimation, and hand reasoning.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-14 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.12155 — 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 2026-10-16T03:44:26.224Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).