ChenyunWu/PhraseCutDataset

Dataset API for "PhraseCut: Language-based Image Segmentation in the Wild"

44
/ 100
Emerging

This project provides a comprehensive dataset for training and evaluating models that can identify specific objects or regions within an image based on a descriptive phrase. You input an image and a natural language phrase, and the output is a precise mask highlighting the described region. It's designed for researchers and developers working on advanced image understanding and human-computer interaction.

113 stars.

Use this if you are developing or evaluating computer vision models that need to accurately segment image regions guided by natural language descriptions.

Not ideal if you need a dataset for general object detection or image classification without specific phrase-based regional identification.

image segmentation visual grounding computer vision research natural language image search referring expression comprehension
No License No Package No Dependents
Maintenance 13 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

113

Forks

14

Language

Jupyter Notebook

License

Last pushed

Mar 28, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ChenyunWu/PhraseCutDataset"

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