Metraipolis › archive › dc_2bf20259aa75

FineHOI: Part-Aware Dense Representations for Zero-Shot Human-Object Interaction Detection — arXiv:2609.05959

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.05959
License (as archived): CC0-1.0
Archived: 2026-10-16T15:06:44.072Z
SHA-256 of the archived text: 4684e1ce9b12f8cf1d3e18a72dc5405793a59f8be06ff3b3f7695b9ef3f6b893
Stable URL of this page: https://metraipolis.com/documento/dc_2bf20259aa75

How to cite

FineHOI: Part-Aware Dense Representations for Zero-Shot Human-Object Interaction Detection — arXiv:2609.05959 — arXiv (en), https://arxiv.org/abs/2609.05959 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2bf20259aa75 (Metraipolis archive dc_2bf20259aa75, sha256 4684e1ce9b12f8cf1d3e18a72dc5405793a59f8be06ff3b3f7695b9ef3f6b893)

BibTeX

@misc{dc2bf20259aa75,
  title = {FineHOI: Part-Aware Dense Representations for Zero-Shot Human-Object Interaction Detection — arXiv:2609.05959},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05959},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2bf20259aa75; sha256 4684e1ce9b12f8cf1d3e18a72dc5405793a59f8be06ff3b3f7695b9ef3f6b893},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05959. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Human-Object Interaction (HOI) detection aims to localize humans and objects in images and classify their interactions. Zero-shot HOI focuses on recognizing interactions that are not observed during training, requiring models to generalize beyond seen verb-object compositions. Recent approaches leverage Vision-Language Models (VLMs), benefiting from rich semantic representations. However, they often rely on global or detector-centric features that compress interaction cues and hinder fine-grained spatial reasoning. To overcome this limitation, we propose FineHOI, a zero-shot HOI framework that explicitly models interactions from dense patch-level features. Our approach is motivated by the observation that human-object interactions are defined by localized spatial relationships, which are not preserved by global and detector-centric representations. To this end, we introduce an Adaptive Part-Level Attention module that decomposes humans and objects into semantically coherent parts via unsupervised clustering, and re-weights them based on their interaction relevance. These representations are then integrated through a Region-Aware Interaction Transformer that integrates part-aware and global features and produces the final HOI embedding. Extensive experiments demonstrate that FineHOI consistently outperforms existing zero-shot HOI methods, achieving particularly strong gains on unseen interactions. Code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.05959 — 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 2026-10-16T14:49:57.025Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).