Enregistré dans:
Détails bibliographiques
Auteur principal: Wang, Douglass
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2603.02805
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917309226942464
author Wang, Douglass
author_facet Wang, Douglass
contents Digital ink -- the coordinate stream captured from stylus or touch input -- lacks a unified representation. Continuous vector representations produce long sequences and suffer from training instability, while existing token representations require large vocabularies, face out-of-vocabulary issues, and underperform vectors on recognition. We propose ScribeTokens, a tokenization that decomposes pen movement into unit pixel steps. Together with two pen-state tokens, this fixed 10-token base vocabulary suffices to represent any digital ink and enables aggressive BPE compression. On handwritten text generation, ScribeTokens dramatically outperforms vectors (17.33% vs. 70.29% CER), showing tokens are far more effective for generation. On recognition, ScribeTokens is the only token representation to outperform vectors without pretraining. We further introduce next-ink-token prediction as a self-supervised pretraining strategy, which consistently improves recognition across all token-based models and accelerates convergence by up to 83x. With pretraining, ScribeTokens achieves the best recognition results across all representations on both datasets (8.27% CER on IAM, 9.83% on DeepWriting).
format Preprint
id arxiv_https___arxiv_org_abs_2603_02805
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ScribeTokens: Fixed-Vocabulary Tokenization of Digital Ink
Wang, Douglass
Computer Vision and Pattern Recognition
Digital ink -- the coordinate stream captured from stylus or touch input -- lacks a unified representation. Continuous vector representations produce long sequences and suffer from training instability, while existing token representations require large vocabularies, face out-of-vocabulary issues, and underperform vectors on recognition. We propose ScribeTokens, a tokenization that decomposes pen movement into unit pixel steps. Together with two pen-state tokens, this fixed 10-token base vocabulary suffices to represent any digital ink and enables aggressive BPE compression. On handwritten text generation, ScribeTokens dramatically outperforms vectors (17.33% vs. 70.29% CER), showing tokens are far more effective for generation. On recognition, ScribeTokens is the only token representation to outperform vectors without pretraining. We further introduce next-ink-token prediction as a self-supervised pretraining strategy, which consistently improves recognition across all token-based models and accelerates convergence by up to 83x. With pretraining, ScribeTokens achieves the best recognition results across all representations on both datasets (8.27% CER on IAM, 9.83% on DeepWriting).
title ScribeTokens: Fixed-Vocabulary Tokenization of Digital Ink
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.02805