Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[NeurIPS 2024] An official implementation of "ShareGPT4Video: Improving Video Understanding and Generation with Better Captions"
| Date | Stars |
|---|---|
| 2026-07-24 | 1092 |
| 2026-07-25 | 1092 |
| 2026-07-28 | 1092 |
| 2026-07-30 | 1092 |
| 2026-08-06 | 1092 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# <img src="https://raw.githubusercontent.com/ShareGPT4V/ShareGPT4V-Resources/master/images/share4video_tight.png" style="vertical-align: -10px;" :height="50px" width="50px"> ShareGPT4Video: Improving Video Understanding and Generation with Better Captions ⭐️ **Our series works:** [[**MMStar**](https://mmstar-benchmark.github.io/)] [[**ShareGPT4V**](https://sharegpt4v.github.io/)] [[**ShareGPT4Omni**](https://sharegpt4omni.github.io/)] --- 🚀🚀🚀 Official implementation of **ShareGPT4Video: Improving Video Understanding and Generation with Better Captions**. Here is a video for introducing ShareGPT4Video clearly: [![video]](https://user-images.githubusercontent.com/56393454/334307144-1b106612-447b-4e35-bb9f-9b904fa3a464.mp4) - **Authors**: [Lin Chen*](https://lin-chen.site), [Xilin Wei*]() [Jinsong Li*](https://li-jinsong.github.io/), [Xiaoyi Dong](https://scholar.google.com/citations?user=FscToE0AAAAJ&hl=en), [Pan Zhang](https://panzhang0212.github.io/), [Yuhang Zang](https://yuhangzang.github.io/), [Zehui Chen](https://lovesnowbest.site/), [Haodong Duan](https://kennymckormick.github.io/), [Bin Lin](https://scholar.google.com.hk/citations?user=GCOVDKoAAAAJ&hl=en), [Zhenyu Tang](), [Li Yuan](https://yuanli2333.github.io/), [Yu Qiao](https://scholar.google.co.uk/citations?user=gFtI-8QAAAAJ&hl=en), [Dahua Lin](http://dahua.site/), [Feng Zhao📧](https://scholar.google.com/citations?hl=en&user=r6CvuOUAAAAJ), [Jiaqi Wang 📧](https://myownskyw7.github.io/) - **Institutes**: University of Science and Technology of China; The Chinese University of Hong Kong; Peking University; Shanghai AI Laboratory - **Resources**: [[Paper](https://arxiv.org/abs/2406.04325v1)] [[Project Page](https://sharegpt4video.github.io/)] [[ShareGPT4Video Dataset](https://huggingface.co/datasets/ShareGPT4Video/ShareGPT4Video)] [[Colab](https://github.com/camenduru/ShareGPT4Video-jupyter)] - **Models**: [[🤗ShareGPT4Video-8B](https://huggingface.co/Lin-Chen/sharegpt4video-8b)] [[🤗ShareCaptioner-Video](https://huggingface.co/Lin-Chen/ShareCaptioner-Video)] - **Demo**: [[🤗ShareGPT4Video-8B](https://huggingface.co/spaces/Lin-Chen/ShareGPT4Video-8B)] [[🤗ShareCaptioner-Video](https://huggingface.co/spaces/Lin-Chen/ShareCaptioner-Video)] ## 💡 Highlights - 🔥 A **large-scale** **highly descriptive** video-text dataset, **40K** GPT4-Vision-generated video captions, around **400K** implicit video split captions. - 🔥 A **general video captioner for various video durations, resolutions, and aspect ratios**, approaching GPT4-Vision's caption capability, featuring two inference modes targeted for quality and efficiency, separately. - 🔥 A superior large video-language model **ShareGPT4Video-8B**, lasting **5 hours** on 8xA100 GPUs of training respectively. - 🔥 **Improving Text-to-Video performance** with high-quality video captions generated by our ShareCaptioner-Video. Thanks to [Open-Sora-Plan](https://github.com/PKU-YuanGroup/Open-Sora-Plan). ## 📜 News **[2024/10/1]** ShareGPT4Video was accepted by NeurIPS 2024 D&B track! **[2024/7/1]** The code about batch-inference of ShareCaptioner-Video is available now! **[2024/6/11]** The web demo and local demo of ShareCaptioner-Video are available now! **[2024/6/11]** The web demo and local demo of ShareGPT4Video-8B are available now! **[2024/6/7]** Our paper has been featured as [HuggingFace Daily Papers](https://huggingface.co/papers?date=2024-06-07) and ranked 1st in 6.7. **[2024/5/27]** The [ShareGPT4Video-8B](https://huggingface.co/Lin-Chen/sharegpt4video-8b) model is released! **[2024/5/26]** The [ShareGPT4Video dataset](https://huggingface.co/datasets/ShareGPT4Video/ShareGPT4Video) and [project page](https://sharegpt4video.github.io/) are released! ## 👨💻 Todo - [x] Training code for ShareGPT4Video-8B - [x] Batch inference code for ShareCaptioner-Video - [x] Web demo and local demo of ShareCaptioner-Video - [x] Web demo and local demo of ShareGPT4Video-8B - [x] Checkpoints of ShareGPT4Video-8B ## Quick Usage
Excerpt of 7,572 characters
Read on GitHub
LinChen · University of Science and Technology of China
37
Jinsong Li · The Chinese University of Hong Kong · Hong Kong
3
loveSnowBest · USTC · China
2
2
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:dc6e73be7d4d6fef, topic:large-language-models, topic:gpt
matched fp:dc6e73be7d4d6fef, topic:text-to-video, readme:text-to-video
matched fp:dc6e73be7d4d6fef, topic:chatgpt