Picture for Son Train

Son Train

MLIM: Vision-and-Language Model Pre-training with Masked Language and Image Modeling

Add code
Sep 24, 2021
Figure 1 for MLIM: Vision-and-Language Model Pre-training with Masked Language and Image Modeling
Figure 2 for MLIM: Vision-and-Language Model Pre-training with Masked Language and Image Modeling
Figure 3 for MLIM: Vision-and-Language Model Pre-training with Masked Language and Image Modeling
Viaarxiv icon