domains / families / data / tao-generate-referring-expressions
tao-generate-referring-expressions
separate
"Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region
When to use
- Transform `(image, KITTI labels)` pairs into a unified `annotations.jsonl` containing rich, grounded referring expressions. The VLM acts as a "teacher" annotator: Steps 0-1 see the image; Step 2 groups Step 0 outputs into grouping phrases…
Skill page
Source
| Repository | Path |
|---|
| NVIDIA/skills | skills/tao-generate-referring-expressions/SKILL.md |