Papers with Code · CC BY-SA 4.0

ICDAR2013

아카이브 평가 38건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
CLIP4STR-L*	Accuracy 99.42	An Empirical Study of Scaling Law for OCR 2023-12-29	코드 1
DTrOCR 105M	Accuracy 99.4	DTrOCR: Decoder-only Transformer for Optical Character Recognition 2023-08-30	코드 1
CLIP4STR-L (DataComp-1B)	Accuracy 99.0	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model 2023-05-23	코드 1
MGP-STR	Accuracy 98.5	Multi-Granularity Prediction for Scene Text Recognition 2022-09-08	코드 1 · 코드 2 · 코드 3
CLIP4STR-L	Accuracy 98.5	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model 2023-05-23	코드 1
PARSeq	Accuracy 98.4±0.2	Scene Text Recognition with Permuted Autoregressive Sequence Models 2022-07-14	코드 1 · 코드 2
CCD-ViT-Base(ARD_2.8M)	Accuracy 98.3	Self-supervised Character-to-Character Distillation for Text Recognition 2022-11-01	코드 1
CCD-ViT-Small(ARD_2.8M)	Accuracy 98.3	Self-supervised Character-to-Character Distillation for Text Recognition 2022-11-01	코드 1
CLIP4STR-B	Accuracy 98.3	CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model 2023-05-23	코드 1
MATRN	Accuracy 97.9	Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features 2021-11-30	코드 1 · 코드 2 · 코드 3
S-GTR	Accuracy 97.8	Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition 2021-12-24	코드 1
SIGA_T	Accuracy 97.8	Self-supervised Implicit Glyph Attention for Text Recognition 2022-03-07	코드 1
DPAN	Accuracy 97.7	Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition 2021-08-01	코드 1 · 코드 2
CDistNet (Ours)	Accuracy 97.67	CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition 2021-11-22	코드 1 · 코드 2 · 코드 3
CCD-ViT-Tiny(ARD_2.8M)	Accuracy 97.5	Self-supervised Character-to-Character Distillation for Text Recognition 2022-11-01	코드 1
SVTR-L (Large)	Accuracy 97.2	SVTR: Scene Text Recognition with a Single Visual Model 2022-04-30	코드 1 · 코드 2 · 코드 3 · 코드 4
SVTR-B (Base)	Accuracy 97.1	SVTR: Scene Text Recognition with a Single Visual Model 2022-04-30	코드 1 · 코드 2 · 코드 3 · 코드 4
DiffusionSTR	Accuracy 97.1	DiffusionSTR: Diffusion Model for Scene Text Recognition 2023-06-29	연결 없음
Yet Another Text Recognizer	Accuracy 96.8	Why You Should Try the Real Data for the Scene Text Recognition 2021-07-29	코드 1
SVTR-T (Tiny)	Accuracy 96.3	SVTR: Scene Text Recognition with a Single Visual Model 2022-04-30	코드 1 · 코드 2 · 코드 3 · 코드 4
SVTR-S (Small)	Accuracy 95.7	SVTR: Scene Text Recognition with a Single Visual Model 2022-04-30	코드 1 · 코드 2 · 코드 3 · 코드 4
SRN	Accuracy 95.5	Towards Accurate Scene Text Recognition with Semantic Reasoning Networks 2020-03-27	코드 1 · 코드 2 · 코드 3
RCEED	Accuracy 94.7	Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition 2021-06-13	코드 1
SATRN	Accuracy 94.1	On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention 2019-10-10	코드 1 · 코드 2
DAN	Accuracy 93.9	Decoupled Attention Network for Text Recognition 2019-12-21	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
CSTR	Accuracy 93.2	Revisiting Classification Perspective on Scene Text Recognition 2021-02-22	코드 1
TextScanner	Accuracy 92.9	TextScanner: Reading Characters in Order for Robust Scene Text Recognition 2019-12-28	연결 없음
SEED	Accuracy 92.8	SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition 2020-05-22	코드 1 · 코드 2 · 코드 3
SAFL	Accuracy 92.8	SAFL: A Self-Attention Scene Text Recognizer with Focal Loss 2022-01-01	코드 1
ViTSTR	Accuracy 92.4	Vision Transformer for Fast and Efficient Scene Text Recognition 2021-05-18	코드 1 · 코드 2 · 코드 3