ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language TasksViLBERT: Pretraining Task-Agnostic Visiolinguist
阅读背景：
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
来源：互联网
分享到：
