https://github.com/adithya-s-k/vivid

https://github.com/adithya-s-k/vivid

Last synced: 6 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/adithya-s-k/vivid
• Owner: adithya-s-k
• License: mit
• Created: 2024-07-01T17:30:06.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-11-08T08:52:22.000Z (11 months ago)
• Last Synced: 2025-03-25T10:37:39.134Z (6 months ago)
• Language: JavaScript
• Homepage: https://adithya-s-k.github.io/ViViD/
• Size: 529 KB
• Stars: 1
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          


ViViD





Vision Language model for Unified Visual Understanding of Documents



---

ViViD integrates multiple document analysis tasks into a single model, reducing the need for multiple specialized models and enhancing efficiency for complex document understanding.

### Citation

If you find ViViD useful in your work, please consider citing it as follows:

```

@article{AdithyaSKolavi2024ViViD,

  title     = {ViViD: Vision Language Model for Unified Visual Understanding of Documents},

  author    = {Adithya S Kolavi},

  year      = {2024},

  url       = {https://github.com/adithya-s-k/ViViD},

  abstract  = {

      "ViViD integrates multiple document analysis tasks into a single model, reducing the need for multiple specialized models and enhancing efficiency for complex document understanding."

  }

}

```