emanuelevivoli / awesome-comics-understanding

The official repo of the Comics Survey: "A missing piece in Vision and Language: A Survey on Comics Understanding"
53 stars 2 forks source link

[add papers] new 2024 papers #1

Open emanuelevivoli opened 1 week ago

emanuelevivoli commented 1 week ago

In the ICDAR 2024, a bunch of papers on comics/manga understanding, analysis, and synthesis have been published. In particular, the MANPU workshop accepted papers are listed below. Some links to arxiv, while the once with no arxiv links to the ICDAR-MANPU proceedings. I kept the arxiv because not everyone can access/download the proceeding...

Accessible papers.

Year Conference / Journal Title Authors Links
2024 MANPU Comics Datasets Framework: Mix of Comics datasets for detection benchmarking Vivoli, Emanuele et al. πŸ“œ Paper, πŸ‘¨β€πŸ’» Code
2024 MANPU Toward accessible comics for blind and low vision readers Rigaud, Christophe et al. πŸ“œ Paper
2024 MANPU A Comprehensive Gold Standard and Benchmark for Comics Text Detection and Recognition Soykan, GΓΌrkan et al. πŸ“œ Paper, πŸ‘¨β€πŸ’» Code
2024 MANPU ComicBERT: A Transformer Model and Pre-training Strategy for Contextual Understanding in Comics Soykan, GΓΌrkan et al. πŸ“œ Paper, πŸ‘¨β€πŸ’» Code
2024 MANPU Investigating Neural Networks and Transformer Models for Enhanced Comic Decoding Kouletou, Eleanna et al. πŸ“œ Paper
2024 MANPU Spatially Augmented Speech Bubble to Character Association via Comic Multi-Task Learning Soykan, GΓΌrkan et al. πŸ“œ Paper
2024 MANPU Quantitative evaluation based on CLIP for methods inhibiting imitation of painting styles Iwata, Motoi et al. πŸ“œ Paper
2024 MANPU Retrieving and Analyzing Translations of American Newspaper Comics with Visual Evidence Murel, Jacob et al. πŸ“œ Paper

What next?

Subsequent comments to this issue will propose where to locate the papers based on the task they tackle or propose.

emanuelevivoli commented 3 days ago

Conference proceedings are out here, let's close this issue, Lele!

emanuelevivoli commented 1 day ago

Additional paper:

Year Conference / Journal Title Authors Links
2024 Arxiv (IEEE?) MangaUB: A Manga Understanding Benchmark for Large Multimodal Models Ikuta, Hikaru et al. πŸ“œ Paper