BohaoWu/Ukiyoe_MNERG

Ukiyo-e MNERG Dataset

Moved. The dataset, with the five-fold splits, region features and knowledge cache used in the article, is now at datasets/BohaoWu/Ukiyoe_MNERG, and the trained weights are at BohaoWu/NERGL. This repository is kept unchanged for existing links.

Introduction

The model and dataset for Multimodal Named Entity Recognition and Grounding (MNERG) of ukiyo-e artworks have been uploaded.

The dataset contains the following annotations:

• XML folder: Contains bounding box annotations for ukiyo-e artworks. Each filename corresponds to a unique ukiyo-e artwork ID.
• TXT folder: Contains named entity recognition (NER) annotations, divided into training, validation, and test sets.

Reference Projects

1. Art Research Center, Ritsumeikan University – Ukiyo-e Database
2. NUSTM/GMNER

Citation

If you use this dataset or model in your research, please cite the following paper:

Wu, B., & Maeda, A. (2026). NERGL: Named Entity Recognition and Grounding with Large Language Models for Ukiyo-E Artworks. In New Trends in Theory and Practice of Digital Libraries (pp. 3–13). Springer Nature Switzerland.

BibTeX

@InProceedings{Wu2026NERGL,
  author    = {Wu, Bohao and Maeda, Akira},
  editor    = {Balke, Wolf-Tilo and Golub, Koraljka and
               Manolopoulos, Yannis and Stefanidis, Kostas and
               Zhang, Zheying and Aalberg, Trond and Manghi, Paolo},
  title     = {NERGL: Named Entity Recognition and Grounding
               with Large Language Models for Ukiyo-E Artworks},
  booktitle = {New Trends in Theory and Practice of Digital Libraries},
  year      = {2026},
  publisher = {Springer Nature Switzerland},
  address   = {Cham},
  pages     = {3--13},
  isbn      = {978-3-032-06136-2},
  doi       = {10.1007/978-3-032-06136-2_1}
}

License

This dataset is released under the Apache License 2.0.