# ICFHR 2020 Competition on Image Retrieval for Historical Handwritten Fragments

arXiv: https://arxiv.org/abs/2010.10197 · HTML: https://mlsanity.com/paper/2010.10197/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Oct 2020.

## Built on by (most cited first, 9 of 9)

- [A Survey of Historical Document Image Datasets](https://mlsanity.com/paper/2203.08504/) (2022)
- [GR-RNN: Global-Context Residual Recurrent Neural Networks for Writer Identification](https://mlsanity.com/paper/2104.05036/) (2021)
- [SAGHOG: Self-Supervised Autoencoder for Generating HOG Features for Writer Retrieval](https://mlsanity.com/paper/2404.17221/) (2024)
- [Feature Mixing for Writer Retrieval and Identification on Papyri Fragments](https://mlsanity.com/paper/2306.12939/) (2023)
- [Explainable Coarse-to-Fine Ancient Manuscript Duplicates Discovery](https://mlsanity.com/paper/2505.03836/) (2025)
- [Towards the Influence of Text Quantity on Writer Retrieval](https://mlsanity.com/paper/2506.07566/) (2025)
- [NeuroPapyri: A Deep Attention Embedding Network for Handwritten Papyri Retrieval](https://mlsanity.com/paper/2408.07785/) (2024)
- [Beyond the Pipeline: Analyzing Key Factors in End-to-End Deep Learning for Historical Writer Identification](https://mlsanity.com/paper/2510.18671/) (2025)
- [TextileNet: Towards Zero-shot Text-style Segmentation of Manuscripts](https://mlsanity.com/paper/2607.09299/) (2026)

## Abstract (arXiv)

This competition succeeds upon a line of competitions for writer and style analysis of historical document images. In particular, we investigate the performance of large-scale retrieval of historical document fragments in terms of style and writer identification. The analysis of historic fragments is a difficult challenge commonly solved by trained humanists. In comparison to previous competitions, we make the results more meaningful by addressing the issue of sample granularity and moving from writer to page fragment retrieval. The two approaches, style and author identification, provide information on what kind of information each method makes better use of and indirectly contribute to the interpretability of the participating method. Therefore, we created a large dataset consisting of more than 120 000 fragments. Although the most teams submitted methods based on convolutional neural networks, the winning entry achieves an mAP below 40%.