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.
Official repository for "VideoPrism: A Foundational Visual Encoder for Video Understanding" (ICML 2024)
| Date | Stars |
|---|---|
| 2026-07-24 | 388 |
| 2026-07-25 | 388 |
| 2026-07-28 | 388 |
| 2026-07-30 | 388 |
| 2026-08-06 | 388 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# VideoPrism: A Foundational Visual Encoder for Video Understanding [](https://arxiv.org/abs/2402.13217) [](https://research.google/blog/videoprism-a-foundational-visual-encoder-for-video-understanding/) [](https://colab.research.google.com/github/google-deepmind/videoprism/blob/main/videoprism/colabs/videoprism_video_encoder_demo.ipynb) [](https://colab.research.google.com/github/google-deepmind/videoprism/blob/main/videoprism/colabs/videoprism_video_text_demo.ipynb) [](https://colab.research.google.com/github/google-deepmind/videoprism/blob/main/videoprism/colabs/videoprism_video_classification_demo.ipynb) [](https://huggingface.co/collections/google/videoprism-686e823d6070ec6ad9e4b1f2) [](https://opensource.org/licenses/Apache-2.0) [VideoPrism](https://arxiv.org/abs/2402.13217) is a general-purpose video encoder designed to handle a wide spectrum of video understanding tasks, including classification, retrieval, localization, captioning, and question answering. It is pre-trained on a massive and diverse dataset: 1 billion image-text pairs from [WebLI](https://arxiv.org/abs/2209.06794), 36 million high-quality video-text pairs, and 582 million video clips with noisy or machine-generated parallel text (subject to data wipeout). The pre-training approach is designed for these hybrid data, to learn both from video-text pairs and the videos themselves. VideoPrism is fairly easy to adapt to new video understanding tasks, and achieves state-of-the-art performance on 31 out of 33 public video understanding benchmarks using a single frozen model. This repository releases the model weight checkpoints and hosts [JAX](https://github.com/jax-ml/jax)/[Flax](https://github.com/google/flax) utility functions for checkpoint loading and model inference. ## Updates * **[Mar-13-26]:** Added video classification fine-tuning with the frozen backbone [[`Colab notebook`](https://colab.research.google.com/github/google-deepmind/videoprism/blob/main/videoprism/colabs/videoprism_video_classification_demo.ipynb)]. :fire::fire: * **[Jul-16-25]:** Released VideoPrism video-text encoders for cross-modal retrieval [[`Colab notebook`](https://colab.research.google.com/github/google-deepmind/videoprism/blob/main/videoprism/colabs/videoprism_video_text_demo.ipynb)]. :fire::fire: * **[Jun-15-25]:** Added models to [[`Hugging Face`](https://huggingface.co/collections/google/videoprism-686e823d6070ec6ad9e4b1f2)]. * **[Jun-05-25]:** Added video encoder demo [[`Colab notebook`](https://colab.research.google.com/github/google-deepmind/videoprism/blob/main/videoprism/colabs/videoprism_video_encoder_demo.ipynb)]. * **[Jun-03-25]:** Released VideoPrism video encoders (Base and Large) [[`Blog`](https://research.google/blog/videoprism-a-foundational-visual-encoder-for-video-understanding/)] [[`Paper`](https://arxiv.org/abs/2402.13217)]. :fire::fire: ## TODOs - [ ] Add PyTorch model support. ## Getting started You will need Python 3.9 or later. Download the code from GitHub and run: ```shell $ git clone https://github.com/google-deepmind/videoprism.git $ cd videoprism $ pip install . ``` Please get started with the following example code for model checkpoint loading and inference or use the [Colab notebook for video encoders](https://colab.resear
Excerpt of 12,732 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:40800f7d64015029, topic:vision-language-model, readme:cross-modal