Verified record · from the answer index
tao-generate-image-grounding
skilltested · static-verifiedscore 51/100signed passport ✓1,608 uses
Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them to pixel-space bounding boxes via a VLM. Use when the user wants to ground captions to bboxes, generate phrase-grounded annotatio
Declared tools (1)
tao-generate-image-grounding
skill:nvidia/skills/tao-generate-image-grounding · published by nvidia · source repository