AI Paper Atlas

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

SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition

Yongkun Du, Zhineng Chen, Hongtao Xie, Caiyan Jia, Yu-Gang Jiang

ICCV 2025 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 46 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
add multi-size resizing instead of fixed 32x128 resizing (ablation)SVTRv2 · U14M irregular text (R1 aspect-ratio group)word accuracy: 72.1 -> 87.4Improved
add multi-size resizing instead of fixed 32x128 resizing (ablation)SVTRv2 · U14M irregular text (R2 aspect-ratio group)word accuracy: 83.1 -> 88.3Improved
use multi-size resizing instead of larger fixed 64x256 (ablation)SVTRv2 · U14M avgword accuracy: 79.03 -> 83.86Improved
add horizontal feature rearranging (ablation)SVTRv2 · U14M Multi-Orientedword accuracy: 83.73 -> 85.76Improved
add vertical feature rearranging (ablation)SVTRv2 · U14M Multi-Orientedword accuracy: 83.73 -> 84.44Improved
add full feature rearranging module (H and V) (ablation)SVTRv2 · U14M Multi-Orientedword accuracy: 83.73 -> 86.19Improved
replace FRM with one Transformer block (ablation)SVTRv2 · U14M avgword accuracy: 82.94 -> 82.49Hurt
add semantic guidance module (ablation)SVTRv2 · OST avgword accuracy: 74.92 -> 80.03Improved
add semantic guidance module (ablation)SVTRv2 · U14M avgword accuracy: 83.86 -> 86.14Improved
add semantic guidance module (ablation)SVTRv2 · Com avgword accuracy: 96.16 -> 96.57Improved
use SGM instead of PARSeq language model during training (ablation)SVTRv2 · OST avgword accuracy: 76.55 -> 80.03Improved
remove rectification module TPS from SVTR (ablation)SVTR · LTB long textword accuracy: 0.0 -> 45.1Improved

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