TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection

TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection Chaoya Jiang author Haiyang Xu author Chenliang Li author Ming Yan author Wei Ye author Shikun Zhang author Bin Bi author Songfang Huang author 2022-12 text Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing Yoav Goldberg editor Zornitsa Kozareva editor Yue Zhang editor Association for Computational Linguistics Abu Dhabi, United Arab Emirates conference publication jiang-etal-2022-trips 10.18653/v1/2022.emnlp-main.273 https://aclanthology.org/2022.emnlp-main.273/ 2022-12 4084 4096