Research map / Video / Video-language understanding
EndoSCOP-V: A Multi-Turn Video Understanding Evaluation Framework for Multimodal Models in Endoscopy Reporting and Clinical Reasoning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces EndoSCOP-V, a multi-turn video understanding evaluation framework for multimodal models on endoscopy reporting and clinical reasoning.
Problem
Existing endoscopy multimodal benchmarks evaluate only static images or single-disease videos, missing the temporal and clinical reasoning demands of real-world endoscopic diagnosis across full procedure videos.
Approach
A multi-turn video evaluation framework built around native endoscopy videos that tests reasoning over location, morphology, severity, and intervention for findings encountered during continuous organ traversal.
Experimental setup
Benchmarks: EndoSCOP-V
Closest papers by meaning
- EndoBench: A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy Analysis (NeurIPS 2025 · similarity 0.91)
- MedHorizon: Towards Long-context Medical Video Understanding in the Wild (NeurIPS 2026 · similarity 0.88)
- Multi-view Masked Contrastive Representation Learning for Endoscopic Video Analysis (NeurIPS 2024 · similarity 0.87)
- Gastric-X: A Multimodal Multi-Phase Benchmark Dataset for Advancing Vision-Language Models in Gastric Cancer Analysis (CVPR 2026 · similarity 0.86)
- SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark (CVPR 2026 · similarity 0.85)
- Medical thinking with multiple images (ICLR 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.