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 • 0.2B • Updated • 8.79k • 106 -
microsoft/git-large
Image-to-Text • Updated • 241 • 17 -
microsoft/git-base-vqav2
Visual Question Answering • 0.2B • Updated • 323 • 20 -
microsoft/git-large-coco
Image-to-Text • 0.4B • Updated • 3.69k • 104 -
microsoft/git-base-coco
Image-to-Text • Updated • 4.56k • 20 -
microsoft/git-large-r-textcaps
Image-to-Text • Updated • 12 • 10 -
microsoft/git-large-textcaps
Image-to-Text • Updated • 900 • 30 -
microsoft/git-base-vatex
Image-Text-to-Text • 0.2B • Updated • 141 • 4 -
microsoft/git-base-textcaps
Image-to-Text • Updated • 24 • 8 -
microsoft/git-large-r-coco
Image-to-Text • Updated • 65 • 10 -
microsoft/git-base-textvqa
Visual Question Answering • 0.2B • Updated • 535 • 6 -
microsoft/git-large-vqav2
Visual Question Answering • 0.4B • Updated • 51 • 18 -
microsoft/git-base-msrvtt-qa
Image-to-Text • 0.2B • Updated • 11 • 2 -
microsoft/git-large-vatex
Image-Text-to-Text • Updated • 106 • 1 -
microsoft/git-large-textvqa
Visual Question Answering • 0.4B • Updated • 15 • 5 -
microsoft/git-large-r
Image-to-Text • 0.4B • Updated • 4 • 2 -
microsoft/git-large-msrvtt-qa
Image-to-Text • Updated • 14 • 2