Panorama-grounding/PANORAMA-2B
Image-Text-to-Text • 3B • Updated • 2
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection
Official models and datasets for the paper. Panoptic grounded captioning: a full-scene caption in which every mentioned entity, things and stuff alike, is grounded to pixel-level masks.