Results for “box”

3 skills

tao-generate-image-grounding

Generates phrase-grounded bounding box annotations from image-caption pairs using a VLM, producing cleaned captions, referring expressions, and pixel-space bounding boxes.

More results

create-technical-spike

Create time-boxed technical spike documents for researching and resolving critical development decisions before implementation.

tao-train-mask-auto-label

Trains, evaluates, and runs inference for Mask Auto-Label (MAL) weakly-supervised segmentation models using ViT-MAE backbones with minimal point or box annotations.