ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks 论文

2019Neural Information Processing Systems引用 907
Multimodal Machine Learning ApplicationsDomain Adaptation and Few-Shot LearningTopic Modeling
人工智能Domain Adaptation and Few-Shot LearningTopic ModelingMultimodal Machine Learning Applications
相关技术:Topic ModelingMultimodal Machine Learning ApplicationsDomain Adaptation and Few-Shot Learning
关系图谱

ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks · 相关文章

暂无数据