摘要: Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers 2020-12-23 11:54:13 Paper: https://arxiv.org/pdf/2004.00849 预训练模型如火如荼,多模态 阅读全文
posted @ 2020-12-23 11:55 AHU-WangXiao 阅读(1192) 评论(0) 推荐(0) 编辑