AI & Machine Learning

Image Grounding Pipeline

Generates pixel-space bounding boxes for referring expressions in image captions using a vision language model.

Publisher / source

NVIDIA Skills (Verified)

Upstream record

NVIDIA/skills

Version

Version 4

Published

2026-06-21

Publication review

Approved for publication · recorded passed scan 2026-10-16

Content fingerprint

9ddbd9f12aa7d6e2ecee873636cd1e805b5c28826e515ff1156e814bb3e9cc96