ViTAE-Transformer/SAMText

The official repo for the technical report "Scalable Mask Annotation for Video Text Spotting"

14
/ 100
Experimental

This project helps content analysts, data annotators, or AI model trainers to accurately outline and track text in video frames. It takes existing video clips with text (like captions, signs, or logos) and produces precise, pixel-level mask annotations for each text instance. This significantly improves the detail compared to traditional rectangular boxes.

No commits in the last 6 months.

Use this if you need to create highly accurate, detailed mask annotations for text appearing in videos to train or evaluate advanced video text spotting models.

Not ideal if you only need basic bounding box annotations for text, as this tool focuses on more granular, pixel-level detail.

video-annotation text-recognition data-labeling computer-vision content-analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

16

Forks

Language

License

Last pushed

May 03, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ViTAE-Transformer/SAMText"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.