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/
Variants: COCO-Text
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Scene Text Recognition | CLIP4STR-L | CLIP4STR: A Simple Baseline for … | 2023-05-23 |
| Scene Text Recognition | CLIP4STR-B | CLIP4STR: A Simple Baseline for … | 2023-05-23 |
| Scene Text Recognition | MGP-STR | Multi-Granularity Prediction for Scene Text … | 2022-09-08 |
| Scene Text Recognition | PARSeq | Scene Text Recognition with Permuted … | 2022-07-14 |
| Scene Text Detection | Corner-based Region Proposals | Detecting Multi-Oriented Text with Corner-based … | 2018-04-08 |
| Scene Text Detection | TextBoxes++_MS | TextBoxes++: A Single-Shot Oriented Scene … | 2018-01-09 |
| Scene Text Detection | SSTD | Single Shot Text Detector with … | 2017-09-01 |
| Scene Text Detection | WordSup (VGG16-synth-coco) | WordSup: Exploiting Word Annotations for … | 2017-08-22 |
| Scene Text Detection | EAST + VGG16 | EAST: An Efficient and Accurate … | 2017-04-11 |
| Scene Text Detection | Yao et al. | Scene Text Detection via Holistic, … | 2016-06-29 |
Recent papers with results on this dataset: