j-min/VL-T5

PyTorch code for "Unifying Vision-and-Language Tasks via Text Generation" (ICML 2021)

46
/ 100
Emerging

This project helps researchers and developers working with AI to connect what an image shows with relevant text. It takes an image and a question or prompt about it, then generates a text-based answer, description, or translation. It's used by machine learning researchers and AI engineers to build and evaluate models for tasks like visual question answering or image captioning.

374 stars. No commits in the last 6 months.

Use this if you are an AI researcher or developer building or evaluating models that need to understand both images and text together.

Not ideal if you are looking for a ready-to-use application for everyday tasks like generating marketing copy or summarizing documents.

AI-research computer-vision natural-language-processing multimodal-AI machine-learning-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

374

Forks

57

Language

Python

License

MIT

Last pushed

Jul 29, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/j-min/VL-T5"

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