AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Handwritten Text Recognition: A Survey

Carlos Garrido-Munoz, Antonio Ríos-Vila, Jorge Calvo-Zaragoza

TPAMI 2025 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 65 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
integrate language models and lexiconsline-level HTR · IAM line levelCER: 18.2 -> 5.1Improved
scale model size from TrOCR small to largeTrOCR · IAM line levelCER: 4.2 -> 2.9Improved
CTC loss in beyond-line recognition replacing earlier attention approachJLSAT vs SAAR · IAM paragraph levelCER: 16.2 -> 6.8Improved
independent re-implementation of TrOCR (M) vs reportedTrOCR (M) · IAM line levelCER: 3.4 -> 7.3Hurt
independent re-implementation of Transformer vs reportedTransformer 2020 · IAM line levelCER: 4.6 -> 7.6Hurt
large-scale synthetic pre-training with Transformer-CTCTransformer-CTC 2021 · IAM line levelCER: 4.9 -> 2.8Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy