PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection
Researchers introduce PANORAMA, a vision-language model grounding caption phrases in pixel masks, alongside the PanoCaps benchmark and gPQ metric.
1 stories, newest first · one card per story
Researchers introduce PANORAMA, a vision-language model grounding caption phrases in pixel masks, alongside the PanoCaps benchmark and gPQ metric.
Today 1.6K readers · 2.5K views · 780 reads · all time 189K views