SurgViVQA-weights

maurodrago/SurgViVQA-weights

SurgViVQA-weights is a visual question answering model from maurodrago. Use it for the visual question answering task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.

license: mit pipelinetag: visual-question-answering libraryname: transformers tags: - surgical-video - video-question-answering - visual-question-answering - medical-ai --- ---

Downloads · 30 days

Access

Public

Updated Aug 11, 2026

Repo size

2.7 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.zip2.7 GB · 100%

At a glance

Task: Visual Question Answering
Library: transformers
License: mit
Access: Public
Created: Aug 11, 2026
Updated: Aug 11, 2026
SHA: 9812c48f

Model card

From the Hugging Face model README

license: mit pipeline_tag: visual-question-answering library_name: transformers tags:

surgical-video
video-question-answering
visual-question-answering
medical-ai

license: mit

SurgViVQA Pre-trained Weights

This repository contains the pre-trained model weights for SurgViVQA: Temporally Grounded Video Question Answering for Surgical Scene Understanding.

The weights are provided for use with the SurgViVQA project.

Available Weights

File	Dataset
`surgvivqa_gpt2_endovis.zip`	EndoVis
`surgvivqa_gpt2_realcolon.zip`	RealColon

Usage

Download the appropriate pre-trained weights and follow the instructions in the SurgViVQA repository for installation and usage.

Citation

If you use SurgViVQA in your research, please cite:

@article{Drago2026SurgViVQA,
  title   = {SurgViVQA: Temporally Grounded Video Question Answering for Surgical Scene Understanding},
  author  = {Drago, Mauro Orazio and Carlini, Luca and Balyemez, Pelinsu Celebi and Pierantozzi, Dennis and Lena, Chiara and Hassan, Cesare and Stoyanov, Danail and De Momi, Elena and Bano, Sophia and Hoque, Mobarak I.},
  journal = {International Journal of Computer Assisted Radiology and Surgery},
  year    = {2026},
  issn    = {1861-6429},
  doi     = {10.1007/s11548-026-03695-z},
  url     = {https://doi.org/10.1007/s11548-026-03695-z}
}