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}
}