Papers › Multi-Granularity Prediction for Scene Text Recognition

Multi-Granularity Prediction for Scene Text Recognition

8 Sep 2022arXiv:2209.03592archive 2025-07-28

Peng Wang, Cheng Da, Cong Yao

Scene text recognition (STR) has been an active research topic in computer vision for years. To tackle this challenging problem, numerous innovative methods have been successively proposed and incorporating linguistic knowledge into STR models has recently become a prominent trend. In this work, we first draw inspiration from the recent progress in Vision Transformer (ViT) to construct a conceptually simple yet powerful vision STR model, which is built upon ViT and outperforms previous state-of-the-art models for scene text recognition, including both pure vision models and language-augmented methods. To integrate linguistic knowledge, we further propose a Multi-Granularity Prediction strategy to inject information from the language modality into the model in an implicit way, i.e. , subword representations (BPE and WordPiece) widely-used in NLP are introduced into the output space, in addition to the conventional character level representation, while no independent language model (LM) is adopted. The resultant algorithm (termed MGP-STR) is able to push the performance envelop of STR to an even higher level. Specifically, it achieves an average recognition accuracy of 93.35% on standard benchmarks. Code is available at https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/OCR/MGP-STR.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

alibabaresearch/advancedliteratemachinery officialmentioned in papermentioned on GitHubpytorch report
topdu/openocr pytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage ModellingOptical Character Recognition (OCR)PredictionScene Text Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Text Recognition COCO-Text MGP-STR 1:1 Accuracy 81.7 #2 of 4 Archive leaderboard report
Scene Text Recognition CUTE80 MGP-STR Accuracy 99.31 #4 of 18 Archive leaderboard report
Scene Text Recognition IC19-Art MGP-STR Accuracy (%) 85.5 #4 of 5 Archive leaderboard report
Scene Text Recognition ICDAR2013 MGP-STR Accuracy 98.5 #4 of 38 Archive leaderboard report
Scene Text Recognition ICDAR2015 MGP-STR Accuracy 90.9 #5 of 27 Archive leaderboard report
Scene Text Recognition IIIT5k MGP-STR Accuracy 98.8 #8 of 17 Archive leaderboard report
Scene Text Recognition SVT MGP-STR Accuracy 98.6 #4 of 37 Archive leaderboard report
Scene Text Recognition SVTP MGP-STR Accuracy 98.3 #2 of 17 Archive leaderboard report
Scene Text Recognition Uber-Text MGP-STR Accuracy (%) 91.0 #2 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections