Datasets › COCO-Text

COCO-Text

Introduced by Andreas Veit et al. in COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images1 Jan 2016 archive 2025-07-28

The COCO-Text dataset is a dataset for text detection and recognition. It is based on the MS COCO dataset, which contains images of complex everyday scenes. The COCO-Text dataset contains non-text images, legible text images and illegible text images. In total there are 22184 training images and 7026 validation images with at least one instance of legible text.

Source: Improving Text Proposals for Scene Images with Fully Convolutional Networks Image Source: https://vision.cornell.edu/se3/coco-text-2/

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Scene Text Detection COCO-Text Corner-based Region Proposals F-Measure 59.1 Detecting Multi-Oriented Text with Corner-based Region Proposals xhzdeng/crpn 6 Compare
Scene Text Recognition COCO-Text CLIP4STR-L 1:1 Accuracy 81.9 CLIP4STR: A Simple Baseline for Scene Text Recognition... VamosC/CLIP4STR 4 Compare

Papers archive 2025-07-28

papers with a benchmark row: 9 · with a code link: 7 · where Syntology ran a sample: 3 (2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (3 of 9 with a benchmark row: 2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 9 of 9 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 89. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A 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” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (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. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model 1 2 23 May 2023 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 (2 pointer-only for licence)
Multi-Granularity Prediction for Scene Text Recognition 3 1 8 Sep 2022 not harvested
Scene Text Recognition with Permuted Autoregressive Sequence Models 2 1 14 Jul 2022 official (archive's flag): 5 ran · 5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 5 samples that ran constructed an object rather than computing a result
Detecting Multi-Oriented Text with Corner-based Region Proposals 1 1 8 Apr 2018 not harvested
TextBoxes++: A Single-Shot Oriented Scene Text Detector 3 1 9 Jan 2018 not harvested
Single Shot Text Detector with Regional Attention 1 1 1 Sep 2017 not harvested
WordSup: Exploiting Word Annotations for Character based Text Detection 0 1 22 Aug 2017 not harvested
EAST: An Efficient and Accurate Scene Text Detector 31 1 11 Apr 2017 5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified (1 pointer-only for licence)
Scene Text Detection via Holistic, Multi-Channel Prediction 0 1 29 Jun 2016 not harvested

Dataset loaders archive 2025-07-28

2 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Creative Commons Attribution 4.0 License

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • COCO-Text

1 variant name, as the archive lists them.

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