MVPTR: Multi-Level Semantic Alignment for Vision-Language Pre-Training via Multi-Stage Learning.

Zejun Li Zhihao Fan Huaixiao Tou Jingjing Chen 0001 Zhongyu Wei Xuanjing Huang 0001 MVPTR: Multi-Level Semantic Alignment for Vision-Language Pre-Training via Multi-Stage Learning. 4395-4405 2022 ACM Multimedia https://doi.org/10.1145/3503161.3548341 https://www.wikidata.org/entity/Q130867178 conf/mm/2022 db/conf/mm/mm2022.html#LiFTCWH22