TheShadow29/zsgnet-pytorch

Official implementation of ICCV19 oral paper Zero-Shot grounding of Objects from Natural Language Queries (https://arxiv.org/abs/1908.07129)

41
/ 100
Emerging

This project helps computer vision researchers and AI developers train models that can identify specific objects within an image based on a natural language description, even if the model hasn't seen that exact object before. You input images and text queries, and it outputs the precise location (bounding box) of the described object in the image. This is designed for those building advanced computer vision systems for tasks like image search or intelligent assistance.

No commits in the last 6 months.

Use this if you are a computer vision researcher or AI developer working on models that need to locate objects in images based on descriptive text, especially for 'zero-shot' scenarios where the object might be novel.

Not ideal if you need a pre-trained, ready-to-use application for everyday image analysis and are not comfortable with machine learning model training and development.

computer-vision natural-language-processing object-detection machine-learning-research image-understanding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

72

Forks

12

Language

Python

License

MIT

Last pushed

Apr 22, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/TheShadow29/zsgnet-pytorch"

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