GIT: A Generative Image-to-text Transformer for Vision and Language
Paper
•
2205.14100
•
Published
•
1
GIT
GIT (Generative Image-to-text Transformer) is a model useful for vision-language tasks such as image/video captioning and question answering.
-
-
microsoft/git-base
Image-to-Text • Updated • 479k • 46 -
microsoft/git-large
Image-to-Text • Updated • 17k • 13 -
microsoft/git-base-vqav2
Visual Question Answering • Updated • 497 • 10 -
microsoft/git-large-coco
Image-to-Text • Updated • 5.45k • 93 -
microsoft/git-base-coco
Image-to-Text • Updated • 5.44k • 15 -
microsoft/git-large-r-textcaps
Image-to-Text • Updated • 1.38k • 10 -
microsoft/git-large-textcaps
Image-to-Text • Updated • 2.18k • 29 -
microsoft/git-base-vatex
Text Generation • Updated • 10.6k • 4 -
microsoft/git-base-textcaps
Image-to-Text • Updated • 4.82k • 5 -
microsoft/git-large-r-coco
Image-to-Text • Updated • 1.33k • 8 -
microsoft/git-base-textvqa
Visual Question Answering • Updated • 1.26k • 6 -
microsoft/git-large-vqav2
Visual Question Answering • Updated • 248 • 16 -
microsoft/git-base-msrvtt-qa
Image-to-Text • Updated • 78 • 1 -
microsoft/git-large-vatex
Text Generation • Updated • 328 -
microsoft/git-large-textvqa
Visual Question Answering • Updated • 149 • 4 -
microsoft/git-large-r
Image-to-Text • Updated • 47 • 2 -
microsoft/git-large-msrvtt-qa
Image-to-Text • Updated • 16 • 2