logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Spatial context-based Self-Supervised Learning for Handwritten Text Recognition

delete2025-06-09
delete0
delete
OA
AI
C
Carlos Penarrubia
C
Carlos Garrido-Munoz
J
Jose J. Valero-Mas
J
Jorge Calvo-Zaragoza
DOI：10.1016/j.patrec.2025.05.014delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• We investigate the performance of existing spatial context-based SSL methods for HTR. • We propose new methods within this family of SSL. • We advance the state of the art in SSL for HTR. • We highlight that HTR contains rich spatial information due to font and stroke style.
Keywords:
68T10
68T45
Self-Supervised Learning
Handwritten text recognition
Spatial Context

Journal

Pattern Recognition Letters cover
Pattern Recognition Letters
IF:
3.3
Papers:
7.8K
Citations:
1.6W

Organization

No organization information available