Datasets › COCO-Text
COCO-Text
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) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| 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
9 shown of 9 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 89. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model | 1 | 2 | 23 May 2023 | ran 3 of 10 samples (7 unverified) |
| 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 | ran 5 of 8 samples (3 unverified) |
| 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 | ran 5 of 6 samples (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