PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection
PANORAMA grounds vision-language caption phrases in pixel-level masks via mask proposal selection, achieving state-of-the-art grounding on the new PanoCaps benchmark.
25
Product
PanoCaps
- Mentions · 7d0
- Mentions · 30d0
- All mentions2
- First seenSep 15, 2026
- Last mentionedSep 16, 2026
Timeline
2 articles · newest firstPANORAMA: 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.
42
Appears with
- PANORAMAproduct · 2
- ENS Willoworganization · 1
- PANORAMAai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.