Metraipolis › archive › dc_8e12acbb41ef

A Hierarchy-Aware Video-Language Model Evaluation and Hyperbolic Baseline for Surgery — arXiv:2609.27139

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27139
License (as archived)
CC0-1.0
Archived
2026-10-08T09:12:12.804Z
SHA-256 of the archived text
27e8e95ade03f138874b3adff6fa65c72e903567b40b0b00619ec28e7f1e4fc4
Stable URL of this page
https://metraipolis.com/documento/dc_8e12acbb41ef

How to cite

A Hierarchy-Aware Video-Language Model Evaluation and Hyperbolic Baseline for Surgery — arXiv:2609.27139 — arXiv (en), https://arxiv.org/abs/2609.27139 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8e12acbb41ef (Metraipolis archive dc_8e12acbb41ef, sha256 27e8e95ade03f138874b3adff6fa65c72e903567b40b0b00619ec28e7f1e4fc4)
BibTeX
@misc{dc8e12acbb41ef,
  title = {A Hierarchy-Aware Video-Language Model Evaluation and Hyperbolic Baseline for Surgery — arXiv:2609.27139},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27139},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8e12acbb41ef; sha256 27e8e95ade03f138874b3adff6fa65c72e903567b40b0b00619ec28e7f1e4fc4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27139. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Surgical procedures follow a phase-to-step hierarchy, yet the video-language models used to recognize them are evaluated with flat per-level metrics that ignore cross-level coherence and error structure. In this paper we make two contributions to address this problem, (i) we introduce SurgHiBench, the first hierarchy-aware evaluation suite for surgical video understanding, with three tasks measuring recognition, consistency, and severity across granularity levels. We evaluate a general-purpose CLIP model, a Euclidean surgical model, and, as second contribution: (ii) HyperSurg, a new hyperbolic model that enforces phase-step containment via entailment cones, across four (existing) datasets spanning three procedure types. The suite reveals that two models with the same accuracy can produce predictions of very different error severity, ranging from sibling confusions within the correct phase to unrelated cross-phase predictions. Hyperbolic geometry shifts predictions toward the correct procedural neighborhood, and these gains scale with the tree-likeness of each dataset's annotation hierarchy, providing a principled indicator when hierarchy-aware geometry helps.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.27139 — 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 2026-10-08T08:13:26.621Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).