EndoVis-18-VQLA

EndoVis-18-VQLA dataset is a public dataset with 14 video sequences on robotics surgery procedures. It is combined with the bounding box on tissue-instrument interaction detection tasks and the question-answer pairs from surgical VQA classification tasks.

Data and Resources

Cite this as

Long Bai, Mobarakol Islam, Lalithkumar Seenivasan, Hongliang Ren (2024). Dataset: EndoVis-18-VQLA. https://doi.org/10.57702/vqqsm8px

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Long Bai
More Authors
Mobarakol Islam
Lalithkumar Seenivasan
Hongliang Ren