2022年3月18日
Fusion of Detected Objects in Text for Visual Question Answering
摘要： Fusion of Detected Objects in Text for Visual Question Answering 2022-03-18 16:29:58 Paper: https://aclanthology.org/D19-1219/ Code: https://github.co 阅读全文
posted @ 2022-03-18 16:31 AHU-WangXiao 阅读(75) 评论(0) 推荐(0) 编辑
Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
摘要： Align before Fuse: Vision and Language Representation Learning with Momentum Distillation 2022-03-18 10:04:06 Paper: https://proceedings.neurips.cc/pa 阅读全文
posted @ 2022-03-18 10:13 AHU-WangXiao 阅读(1212) 评论(0) 推荐(0) 编辑