Home Projects MovieChat
MovieChat
Python

MovieChat

[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

by wenhaochai · GitHub
Stars
Forks
Created
Last commit
Language
Likely
Self-hostable
computer-visiondatasetlarge-language-modelsBSD-3-ClausePythonSelf-hostable
View on GitHub
In plain words

Analyze long videos with over 10,000 frames using advanced memory techniques.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
MovieChat — GitHub preview card
📈 Star history
707704
2026-07-202026-08-31
📈 Track MovieChat

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

MovieChat has 706 stars on GitHub. It has been forked 44 times. MovieChat is written mainly in Python. It has been in active development since 2023. MovieChat is available under the BSD-3-Clause license. Its main topics are computer-vision, dataset, large-language-models, llama.

Frequently asked questions

What is MovieChat?

[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

Is MovieChat open source?

MovieChat is an open-source project. It is released under the BSD-3-Clause license.

Is MovieChat free?

Yes. MovieChat is free and open source — you can use, modify and self-host it.

What license does MovieChat use?

MovieChat is available under the BSD-3-Clause license.

What language is MovieChat written in?

MovieChat is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — MovieChat

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=wenhaochai-moviechat)](https://olud.ai/project/wenhaochai-moviechat.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.