Browse State-of-the-Art › Scene Text Recognition

Scene Text Recognition

146 papers with code · 15 benchmarks · 29 datasets archive 2025-07-28

Computer Vision

See Scene Text Detection for leaderboards in this task.

Description from the archive archive 2025-07-28; Papers-with-Code links inside it are rewritten to this site.

Benchmarks archive 2025-07-28

15 leaderboard tables shown for this task, 15 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 15 until expanded.

Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): SVT (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
ICDAR2013 (38 rows) CLIP4STR-L* An Empirical Study of Scaling Law for OCR code — Compare
SVT (37 rows) CLIP4STR-H (DFN-5B) CLIP4STR: A Simple Baseline for Scene Text Recognition with... code Syntology 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified Compare
ICDAR2015 (27 rows) DTrOCR 105M DTrOCR: Decoder-only Transformer for Optical Character Recognition code — Compare
CUTE80 (18 rows) CPPD Context Perception Parallel Decoder for Scene Text Recognition code — Compare
IIIT5k (17 rows) CLIP4STR-L (DataComp-1B) CLIP4STR: A Simple Baseline for Scene Text Recognition with... code Syntology 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified Compare
SVTP (17 rows) DTrOCR 105M DTrOCR: Decoder-only Transformer for Optical Character Recognition code — Compare
ICDAR 2003 (12 rows) Yet Another Text Recognizer Why You Should Try the Real Data for the Scene Text Recognition code — Compare
IC19-Art (5 rows) CLIP4STR-L (DataComp-1B) CLIP4STR: A Simple Baseline for Scene Text Recognition with... code Syntology 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified Compare
WOST (5 rows) CLIP4STR-H (DFN-5B) CLIP4STR: A Simple Baseline for Scene Text Recognition with... code Syntology 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified Compare
COCO-Text (4 rows) CLIP4STR-L CLIP4STR: A Simple Baseline for Scene Text Recognition with... code Syntology 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified Compare
HOST (3 rows) CLIP4STR-L CLIP4STR: A Simple Baseline for Scene Text Recognition with... code Syntology 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified Compare
Uber-Text (3 rows) CLIP4STR-L (DataComp-1B) CLIP4STR: A Simple Baseline for Scene Text Recognition with... code Syntology 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified Compare
MSDA (2 rows) MetaSelf-Learning Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmark code — Compare
IC13 (1 row) ABINet-LV+TPS++ TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition code — Compare
SVT-P (1 row) ABINet-LV+TPS++ TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

29 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 269 · with a code link: 146 · where Syntology ran a sample: 27 (26 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (27 of 269 tagged: 26 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 3: papers 1 to 100 of 269, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 24 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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