maelic/relsgg-vits16plus
Image-Text-to-Text • Updated • 414 • 15
RelateAnything
Real-time open-vocabulary relation prediction from any regions: the released relation prediction models.
-
-
maelic/relsgg-vits16
Image-Text-to-Text • Updated • 33 • 2 -
maelic/relsgg-vitb16
Image-Text-to-Text • Updated • 27 • 2 -
maelic/RA-4M
Viewer • Updated • 497k • 1.55k • 7 -
maelic/relsgg-convnext-tiny
Updated • 35 -
maelic/relsgg-convnext-small
Updated • 18 -
maelic/relsgg-convnext-base
Updated • 28 -
maelic/relsgg-convnext-large
Updated • 25 • 1 -
maelic/OV-SGG-Bench
Preview • Updated • 377