https://github.com/showlab/VLog
[CVPR 2025] Video Narration as Vocabulary & Video as Long Document
https://github.com/showlab/VLog
chatgpt langchain large-language-model video-language vocabulary whisper
Last synced: 17 days ago
JSON representation
[CVPR 2025] Video Narration as Vocabulary & Video as Long Document
- Host: GitHub
- URL: https://github.com/showlab/VLog
- Owner: showlab
- Created: 2023-04-20T13:43:25.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2025-03-13T04:51:30.000Z (about 1 month ago)
- Last Synced: 2025-04-04T09:05:27.886Z (20 days ago)
- Topics: chatgpt, langchain, large-language-model, video-language, vocabulary, whisper
- Language: Python
- Homepage:
- Size: 10.8 MB
- Stars: 566
- Watchers: 8
- Forks: 28
- Open Issues: 8
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-chatgpt - VLog - Convert videos to documents. (Web apps / Hosted and self-hosted)
- Awesome-Multimodal-Chatbot - [code
- awesome-chatgpt - VLog - Convert videos to documents. (Web apps / Hosted and self-hosted)
- awesome-llms-for-video-understanding - **VLog: Video as a Long Document** - | (😎 Vid-LLMs: Models / 🗒️ Taxonomy 2)
README
# [VLog](https://arxiv.org/abs/2503.09402)
VLog aims to seek a new perspective on video-language understanding.
👇 Click the branch to see more instructions.
| | [VLog (CVPR'25)](./VLog) |[VLog-Agent](./VLog-agent/)|
|-----------|-----------|-----------|
|**TL;DR**| Video Narration as Vocabulary|Video as Long Document|
|| 
| 
|
|**Method**|A novel, efficient video narrator (GPT2-based) with Narration Vocabulary via Generative Retrieval.|Given a video, we turn it into a textual document containing visual + audio info. By sending this doc to LLM, we can chat over the video!|
## 🎓 BibTeX
If you find our work helpful, please kindly consider citing our paper.
```
@misc{lin2025vlog,
title={VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary},
author={Kevin Qinghong Lin and Mike Zheng Shou},
year={2025},
eprint={2503.09402},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2503.09402},
}
```