Metraipolis › archive › dc_ba801febc69b

MIS-VQA: An Annotation-Driven Surgical Vision-Language Dataset for Complex Surgical Understanding — arXiv:2610.34210

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.34210
License (as archived)
CC0-1.0
Archived
2026-10-27T08:12:41.349Z
SHA-256 of the archived text
353111b458a4cdbdac133246a6b95189898e0d2a3105a0799d5ef8a62b918a12
Stable URL of this page
https://metraipolis.com/documento/dc_ba801febc69b

How to cite

MIS-VQA: An Annotation-Driven Surgical Vision-Language Dataset for Complex Surgical Understanding — arXiv:2610.34210 — arXiv (en), https://arxiv.org/abs/2610.34210 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ba801febc69b (Metraipolis archive dc_ba801febc69b, sha256 353111b458a4cdbdac133246a6b95189898e0d2a3105a0799d5ef8a62b918a12)
BibTeX
@misc{dcba801febc69b,
  title = {MIS-VQA: An Annotation-Driven Surgical Vision-Language Dataset for Complex Surgical Understanding — arXiv:2610.34210},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.34210},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ba801febc69b; sha256 353111b458a4cdbdac133246a6b95189898e0d2a3105a0799d5ef8a62b918a12},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34210. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern surgical AI increasingly requires multimodal understanding rather than isolated perception, yet existing datasets remain largely limited to single-task supervision such as recognition or templated question answering. Current medical VQA resources often rely on synthetic templates, lack natural descriptive supervision, or provide sparse annotations that hinder reasoning about spatial relations and procedural context. We introduce MIS-VQA, a surgical vision-language dataset generated through an annotation-driven pipeline that converts heterogeneous surgical annotations into structured textual scene representations. Using EndoVis18 and CholecT50, we transform phase, instrument, interaction, triplet, and segmentation labels into unified contexts that guide large language models to generate clinically coherent question-answer pairs. MIS-VQA supports four response types-concise and detailed descriptions, perception-level grounding, and multi-step reasoning-enabling hierarchical evaluation from atomic visual grounding to compositional reasoning. To address annotation sparsity, we incorporate confidence-filtered segmentation and cross-annotation consistency checks, enabling spatially grounded supervision at scale. MIS-VQA establishes a unified benchmark for surgical vision-language understanding with spatial supervision and multi-tier reasoning evaluation. To demonstrate its utility, we introduce LLaVA-SurgXpert, a family of surgical vision-language models with visual encoders to analyze how visual representations influence multimodal reasoning. Experiments show consistent improvements over existing surgical VQA baselines while revealing capability gaps between perceptual grounding and higher-level reasoning hidden in prior benchmarks.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.34210 — 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 2026-10-27T07:56:00.303Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).