Home

Awesome

Awesome Comics Understanding Awesome

This repository contains a curated list of research papers and resources focusing on Comics Understanding.

arXiv

πŸ”₯ One missing piece in Vision and Language: A Survey on Comics Understanding πŸ”₯

Authors: Emanuele Vivoli, Andrey Barsky, Mohamed Ali Souibgui, Artemis LlabrΓ©s, Marco Bertini, Dimosthenis Karatzas

πŸ“£ Latest News πŸ“£

πŸ“š Table of Contents

Overview of Vision-Language Tasks of the Layers of Comics Understanding. The ranking is based on input and output modalities and dimensions, as illustrated in the paper.

<p align="center"> <img src="imgs/locu.png" style="max-width:1000px"> </p>

Layers of Comics Understanding

Every survey worthy of the name includes illustrative visuals to enhance understanding. We've followed this approach by providing examples for each task in the Layer of Comics Understanding.
Go check every Layer's tasks image ⬇️.

Layer 1: Tagging and Augmentation

Layer 2: Grounding, Analysis and Segmentation

Layer 3: Retrieval and Modification

Layer 4: Understanding

Layer 5: Generation and Synthesis

Datasets & Benchmarks πŸ“‚πŸ“Ž

</details>

Venues

</details>

How to Contribute πŸš€

You can contribute in two ways:

  1. The easiest is to open an Issue (see an example in issue #1) and we can discuss if there are missing papers, wrong associations or links, or misspelled venues.
  2. The second one is making a pull request with the implemented changes, following the steps:
    1. Fork this repository and clone it locally.
    2. Create a new branch for your changes: git checkout -b feature-name.
    3. Make your changes and commit them: git commit -m 'Description of the changes'.
    4. Push to your fork: git push origin feature-name.
    5. Open a pull request on the original repository by providing a description of your changes.

This project is in constant development, and we welcome contributions to include the latest research papers in the field or report issues πŸ’₯πŸ’₯.

Star History ⭐

Star History Chart

Acknowledge

Many thanks to my co-authors for taking the time to help me with the various refactoring of the survey. Thanks to Beppe Folder for its Awesome Human Visual Attention repo that inspired the ✨style✨ of this repository.