SurgViVQA: Temporally-Grounded Video Question Answering for Surgical Scene Understanding

TL;DR

SurgViVQA introduces a novel temporally-grounded VideoQA model for surgical scenes, leveraging a Masked Video--Text Encoder and a large language model to improve understanding of dynamic intraoperative events.

Contribution

The paper presents SurgViVQA, a new model and dataset for temporally-aware surgical VideoQA, enhancing dynamic scene understanding over existing static image-based approaches.

Findings

Outperforms existing image-based VQA models in keyword accuracy.

Achieves +11% and +9% improvements on REAL-Colon-VQA and EndoVis18-VQA datasets.

Demonstrates robustness to question phrasing variations.

Abstract

Video Question Answering (VideoQA) in the surgical domain aims to enhance intraoperative understanding by enabling AI models to reason over temporally coherent events rather than isolated frames. Current approaches are limited to static image features, and available datasets often lack temporal annotations, ignoring the dynamics critical for accurate procedural interpretation. We propose SurgViVQA, a surgical VideoQA model that extends visual reasoning from static images to dynamic surgical scenes. It uses a Masked Video--Text Encoder to fuse video and question features, capturing temporal cues such as motion and tool--tissue interactions, which a fine-tuned large language model (LLM) then decodes into coherent answers. To evaluate its performance, we curated REAL-Colon-VQA, a colonoscopic video dataset that includes motion-related questions and diagnostic attributes, as well as out-of-template questions with rephrased or semantically altered formulations to assess model robustness. Experimental validation on REAL-Colon-VQA and the public EndoVis18-VQA dataset shows that SurgViVQA outperforms existing image-based VQA benchmark models, particularly in keyword accuracy, improving over PitVQA by +11\% on REAL-Colon-VQA and +9\% on EndoVis18-VQA. A perturbation study on the questions further confirms improved generalizability and robustness to variations in question phrasing. SurgViVQA and the REAL-Colon-VQA dataset provide a framework for temporally-aware understanding in surgical VideoQA, enabling AI models to interpret dynamic procedural contexts more effectively. Code and dataset available at https://github.com/madratak/SurgViVQA.