Can Commonsense Knowledge Improve CLIP’s Performance in Cross-Domain VQA?
Published in ICVGIP, 2024
Recommended citation: Mohamad Hassan N C, Ankit Jha, Moloud Abdar, and Biplab Banerjee. 2025. Can Commonsense Knowledge Improve CLIP's Performance in Cross-Domain VQA?✱ In Proceedings of the Fifteenth Indian Conference on Computer Vision Graphics and Image Processing (ICVGIP ' 24). Association for Computing Machinery, New York, NY, USA, Article 15, 1–10. https://doi.org/10.1145/3702250.370226
Download Paper