https://github.com/microsoft/XPretrain

Multi-modality pre-training
https://github.com/microsoft/XPretrain

computer-vision multimedia multimodal-learning nlp pre-training

Last synced: about 2 months ago
JSON representation

Multi-modality pre-training

• Host: GitHub
• URL: https://github.com/microsoft/XPretrain
• Owner: microsoft
• License: other
• Created: 2022-03-15T07:56:36.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2024-05-08T02:03:57.000Z (8 months ago)
• Last Synced: 2024-08-01T13:29:13.684Z (5 months ago)
• Topics: computer-vision, multimedia, multimodal-learning, nlp, pre-training
• Language: Python
• Homepage:
• Size: 3.59 MB
• Stars: 458
• Watchers: 14
• Forks: 35
• Open Issues: 16
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Code of conduct: CODE_OF_CONDUCT.md
  • Security: SECURITY.md
  • Support: SUPPORT.md

Awesome Lists containing this project

README

        
# XPretrain

This repo includes some recent research works in **multi-modality learning**, especially with **pre-training** method from [MSM group](https://www.microsoft.com/en-us/research/group/multimedia-search-and-mining/) of Microsoft Research. 

## Multi-modality Learning

### ***** Video & Language *****

#### Dataset

> [**HD-VILA-100M dataset**](https://github.com/microsoft/XPretrain/tree/main/hd-vila-100m): high-resolution and diversified video-language dataset

#### Pre-training model

> [**HD-VILA (CVPR 2022)**](https://github.com/microsoft/XPretrain/tree/main/hd-vila): high-resolution and diversified video-language pre-training model

> [**LF-VILA (NeurIPS 2022)**](https://github.com/microsoft/XPretrain/tree/main/LF-VILA): long-form video-language pre-training model

> [**CLIP-ViP (ICLR 2023)**](https://github.com/microsoft/XPretrain/tree/main/CLIP-ViP): adapting image-language pre-training to video-language pretraining model

### ***** Image & Language *****

#### Pre-training model

> [**Pixel-BERT**](https://arxiv.org/pdf/2004.00849.pdf): end-to-end image and language pre-training model

> [**SOHO (CVPR 2021 oral)**](https://github.com/researchmm/soho): improved end-to-end image and language pre-training model with quantized visual tokens

> [**VisualParsing (NeurIPS 2021)**](https://github.com/microsoft/XPretrain/tree/main/visualparsing): Transformer-based end-to-end image and language pre-training model

## News

- :smiley:**March, 2023: the code of [**CLIP-ViP**](https://github.com/microsoft/XPretrain/tree/main/CLIP-ViP) and [**LF-VILA**](https://github.com/microsoft/XPretrain/tree/main/LF-VILA) was released.**

- January, 2023: our paper [**CLIP-ViP**](https://github.com/microsoft/XPretrain/tree/main/CLIP-ViP) to adapt image-language pre-training model to video-language pretraining was accepted by ICLR 2023.

- September, 2022: our paper [**LF-VILA**](https://github.com/microsoft/XPretrain/tree/main/LF-VILA) on long-form video-language pre-training was accepted by NeurIPS 2022. 

- September, 2022: the code of [**HD-VILA**](https://github.com/microsoft/XPretrain/tree/main/hd-vila) was released.

- March, 2022: [**HD-VILA-100M dataset**](https://github.com/microsoft/XPretrain/tree/main/hd-vila-100m) was released publicly.

- March, 2022: [**HD-VILA**](https://github.com/microsoft/XPretrain/tree/main/hd-vila) was accepted by CVPR 2022.

## Contributing

This project welcomes contributions and suggestions.  Most contributions require you to agree to a

Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us

the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide

a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions

provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).

For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or

contact [[email protected]](mailto:[email protected]) with any additional questions or comments.

## Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft 

trademarks or logos is subject to and must follow 

[Microsoft's Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks/usage/general).

Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship.

Any use of third-party trademarks or logos are subject to those third-party's policies.

## Contact Information

For help or issues using the pre-trained models, please submit an issue. 

For other communications, please contact [Bei Liu]() (`[email protected]`) and [Jianlong Fu]() (`[email protected]`).