# An Approach to Enriching Surgical Video Datasets for Fine-Grained Spatial-Temporal Understanding of Vision-Language Models

arXiv: https://arxiv.org/abs/2604.00784 · HTML: https://mlsanity.com/paper/2604.00784/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 19 of 19)

- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos](https://mlsanity.com/paper/1602.03012/) (2016)
- [Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos](https://mlsanity.com/paper/2109.03223/) (2021)
- [Surgical Data Science: Enabling Next-Generation Surgery](https://mlsanity.com/paper/1701.06482/) (2017)
- [Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures](https://mlsanity.com/paper/2307.15220/) (2023)
- [Surgical-VQA: Visual Question Answering in Surgical Scenes using Transformer](https://mlsanity.com/paper/2206.11053/) (2022)
- [Pixel-Wise Recognition for Holistic Surgical Scene Understanding](https://mlsanity.com/paper/2401.11174/) (2024)
- [SurgicalGPT: End-to-End Language-Vision GPT for Visual Question Answering in Surgery](https://mlsanity.com/paper/2304.09974/) (2023)
- [Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery](https://mlsanity.com/paper/2305.11692/) (2023)
- [HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition](https://mlsanity.com/paper/2405.10075/) (2024)
- [Advancing Surgical VQA with Scene Graph Knowledge](https://mlsanity.com/paper/2312.10251/) (2023)
- [EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery](https://mlsanity.com/paper/2501.11347/) (2025)
- [MATIS: Masked-Attention Transformers for Surgical Instrument Segmentation](https://mlsanity.com/paper/2303.09514/) (2023)
- [Text Promptable Surgical Instrument Segmentation with Vision-Language Models](https://mlsanity.com/paper/2306.09244/) (2023)
- [Surgical-VQLA++: Adversarial Contrastive Learning for Calibrated Robust Visual Question-Localized Answering in Robotic Surgery](https://mlsanity.com/paper/2408.04958/) (2024)
- [SurgLaVi: Large-Scale Hierarchical Dataset for Surgical Vision-Language Representation Learning](https://mlsanity.com/paper/2509.10555/) (2025)
- [Surgical-LLaVA: Toward Surgical Scenario Understanding via Large Language and Vision Models](https://mlsanity.com/paper/2410.09750/) (2024)
- [SurgVidLM: Towards Multi-grained Surgical Video Understanding with Large Language Model](https://mlsanity.com/paper/2506.17873/) (2025)
- [ProstaTD: Bridging Surgical Triplet from Classification to Fully Supervised Detection](https://mlsanity.com/paper/2506.01130/) (2025)

## Built on by (most cited first, 1 of 1)

- [From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation](https://mlsanity.com/paper/2605.08712/) (2026)

## Abstract (arXiv)

Surgical video understanding is a crucial prerequisite for advancing Computer-Assisted Surgery. While vision-language models (VLMs) have recently been applied to the surgical domain, existing surgical vision-language datasets lack in capturing and evaluating complex, interleaved spatial-temporal dynamics. Creating large scale datasets that accurately represent fine-grained spatial-temporal relationships in surgical videos is challenging due to costly manual annotations or error-prone generation using large language models. To address this gap, we introduce the SurgSTU-Pipeline, a deterministic generation pipeline featuring temporal and spatial continuity filtering to reliably create surgical datasets for fine-grained spatial-temporal multimodal understanding. Applying this pipeline to publicly available surgical datasets, we create the SurgSTU dataset, comprising 6711 video clips densely extended with 150k fine-grained spatial-temporal question-answer samples. Our comprehensive evaluation shows that while state-of-the-art generalist VLMs struggle in zero-shot settings, their spatial-temporal capabilities can be improved through in-context learning. A fine-tuned VLM on the SurgSTU training dataset achieves highest performance among all spatial-temporal tasks, validating the dataset's efficacy to improve spatial-temporal understanding of VLMs in surgical videos. The project is available here: https://lennart-maack.github.io/SurgSTU-project