Weihan Wang, Zhen Yang, Bin Xu, Juanzi Li, Yankui Sun. ViLTA: Enhancing Vision-Language Pre-training through Textual Augmentation. In IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023. pages 3135-3146, IEEE, 2023. [doi]
Abstract is missing.