# TextileNet: Towards Zero-shot Text-style Segmentation of Manuscripts

arXiv: https://arxiv.org/abs/2607.09299 · HTML: https://mlsanity.com/paper/2607.09299/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 29 references that are in the map.
- First posted on arXiv 10 Jul 2026.

## Builds on (most cited first, 8 of 8)

- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition](https://mlsanity.com/paper/1406.2227/) (2014)
- [TorMentor: Deterministic dynamic-path, data augmentations with fractals](https://mlsanity.com/paper/2204.03776/) (2022)
- [ICFHR 2020 Competition on Image Retrieval for Historical Handwritten Fragments](https://mlsanity.com/paper/2010.10197/) (2020)
- [Offline Writer Identification Using Convolutional Neural Network Activation Features](https://mlsanity.com/paper/2402.17029/) (2024)
- [Self-Supervised Vision Transformers for Writer Retrieval](https://mlsanity.com/paper/2409.00751/) (2024)
- [Visual Script and Language Identification](https://mlsanity.com/paper/1601.01885/) (2016)
- [Sparse Radial Sampling LBP for Writer Identification](https://mlsanity.com/paper/1504.06133/) (2015)

## Abstract (arXiv)

Automatic writer identification systems have progressed remarkably in recent years, yet their deployment in archival paleography remains limited by the scarcity of labeled training data, open scribe sets, and degraded image quality. We present TextileNet, a fully convolutional multi-task network trained exclusively on synthetic data to produce dense pixel-level texture embeddings, which we transfer zeroshot to historical manuscript analysis. As an original contribution to evaluation methodology, we designed a paleographic visual quiz of 80 pair and triplet questions and administered it to a range from lay participants to senior paleographers under strict anonymity, establishing to our knowledge for the first time a human baseline for script-style discrimination on late medieval text. We employ TextileNet embeddings to perform zero-shot retrieval on sub-word granularity for hand and gender identification. Our experimental results help in building the credibility of TextileNet in the paleographic domain, but more than that demonstrate in experimental terms that the question of gender in handwriting needs to be treated with caution.