2022年3月20日
U-ViusalBERT --- Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions
摘要： Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions 2022-03-20 17:34:51 Paper: https://arxiv.org/pdf/2010.12831.pdf Cod 阅读全文
posted @ 2022-03-20 17:38 AHU-WangXiao 阅读(121) 评论(0) 推荐(0) 编辑
Visualbert --- A simple and performant baseline for vision and language
摘要： Visualbert: A simple and performant baseline for vision and language 2022-03-20 15:19:04 Paper: https://arxiv.org/pdf/1908.03557 1. Background and Mot 阅读全文
posted @ 2022-03-20 15:27 AHU-WangXiao 阅读(351) 评论(0) 推荐(0) 编辑