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 • 2.01M • 71 -
microsoft/git-large
Image-to-Text • Updated • 286 • 14 -
microsoft/git-base-vqav2
Visual Question Answering • Updated • 630 • 15 -
microsoft/git-large-coco
Image-to-Text • Updated • 7.82k • • 97 -
microsoft/git-base-coco
Image-to-Text • Updated • 6.13k • 16 -
microsoft/git-large-r-textcaps
Image-to-Text • Updated • 335 • 10 -
microsoft/git-large-textcaps
Image-to-Text • Updated • 1.54k • 29 -
microsoft/git-base-vatex
Image-Text-to-Text • Updated • 3.06k • 4 -
microsoft/git-base-textcaps
Image-to-Text • Updated • 3.8k • • 7 -
microsoft/git-large-r-coco
Image-to-Text • Updated • 914 • 11 -
microsoft/git-base-textvqa
Visual Question Answering • Updated • 724 • 6 -
microsoft/git-large-vqav2
Visual Question Answering • Updated • 889 • 17 -
microsoft/git-base-msrvtt-qa
Image-to-Text • Updated • 60 • 1 -
microsoft/git-large-vatex
Image-Text-to-Text • Updated • 54 -
microsoft/git-large-textvqa
Visual Question Answering • Updated • 203 • 4 -
microsoft/git-large-r
Image-to-Text • Updated • 107 • 2 -
microsoft/git-large-msrvtt-qa
Image-to-Text • Updated • 36 • 2