FaD-VLP: Fashion Vision-and-Language Pre-training towards Unified Retrieval and Captioning

30053

Knowledge Triples

Source Entity	Relationship	Target Entity
Cross Modal Retrieval Task	partOf	Multimodal Understanding Task
Fashion Retrieval Task	partOf	Multimodal Understanding Task
Multimodal Categorization Task	partOf	Multimodal Understanding Task
Pretraining Framework Method	enhances	Triplet Based Tasks Method
Relative Image Captioning Task	partOf	Multimodal Understanding Task