# mbzuai-oryx/video-chatgpt

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/mbzuai-oryx-video-chatgpt).**

1,504 stars · 129 forks · Python · CC-BY-4.0

## Links

- GitHub: https://github.com/mbzuai-oryx/Video-ChatGPT
- Homepage: https://mbzuai-oryx.github.io/Video-ChatGPT
- awesome-repositories: https://awesome-repositories.com/repository/mbzuai-oryx-video-chatgpt.md

## Topics

`chatbot` `clip` `gpt-4` `llama` `llava` `mulit-modal` `vicuna` `video-chatboat` `video-conversation` `vision-language` `vision-language-pretraining`

## Description

[ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.

## Tags

### Part of an Awesome List

- [Multimodal Datasets](https://awesome-repositories.com/f/awesome-lists/ai/multimodal-datasets.md) — Quantitative evaluation framework for video-based dialogue.
- [Video Understanding Models](https://awesome-repositories.com/f/awesome-lists/ai/video-understanding-models.md) — Detailed video understanding via vision-language integration.
- [Pre-training Datasets](https://awesome-repositories.com/f/awesome-lists/data/pre-training-datasets.md) — High-quality video instruction dataset for detailed understanding.