method: CPN (multi-scale)2024-05-30

Authors: Longhuang Wu, Jianqiang Liu, Hanfei Xu, Bin Zheng, Youxin Wang, Shangxuan Tian, Pengfei Xiong

Email: wlonghuang@gmail.com

Description: Detector adopts CPN and recognizer adopts PARSeq.

Wu L, Tian S, Wang Y, et al. CPN: Complementary Proposal Network for Unconstrained Text Detection[J]. arXiv preprint arXiv:2402.11540, 2024.

Bautista D, Atienza R. Scene text recognition with permuted autoregressive sequence models[C]//European conference on computer vision. Cham: Springer Nature Switzerland, 2022: 178-196.

method: AAIG-OCR-NLP2023-04-14

Authors: Liu Yang, Yang Fan, Lin Junyu, Tang Bin, Jin Xuan, Yuan Bo, He Yuan, Huang Longtao

Affiliation: Alibaba Artificial Intelligence Governance Research Center (AAIG)

Description: We used a regression-based text detector, a ViT-based text recognizer and a transformer-based NLP semantic correction module to complete End-to-End Text Spotting task. First, we got pre-trained models on training set including LSVT, RCTW, MLT, ArT etc. Then we fine-tuned models on ReCTS training set to obtain final models. We used single scale and no ensemble mechanism to obtain final results.

method: NSTD-MCEM-iFLYTEK2019-10-12

Authors: iFLYTEK

Affiliation: iFLYTEK

Description: Natural scene text detector(NSTD-iFLYTEK) is based on MaskRcnn with resnet-101. Only ICDAR2019 datasets are used for training, including Rects, LSVT, MLT and Art. Multi-scale training and single-scale testing are used to generate the final result, no model ensemble. Recognition ensemble model is based on attention-based text recognizer. The final results are fused with different channel information on different models.
Xiangxiang Wang （王翔翔） iFLYTEK （科大讯飞）
Jian Dong（董健） iFLYTEK（科大讯飞）
Fengren Wang（王烽人） iFLYTEK（科大讯飞）
Jiajia Wu（吴嘉嘉） iFLYTEK（科大讯飞）
Yin Lin（林垠） iFLYTEK（科大讯飞）
Lou Shun（娄舜） iFLYTEK（科大讯飞）
Jinshui Hu（胡金水） iFLYTEK（科大讯飞）

Ranking Table

Description Paper Source Code
DateMethodRecallPrecisionHmean1-NED
2024-05-30CPN (multi-scale)94.50%94.61%94.56%84.95%
2023-04-14AAIG-OCR-NLP93.11%93.98%93.54%83.60%
2019-10-12NSTD-MCEM-iFLYTEK93.16%93.63%93.40%81.96%
2019-09-17SCUT-UOA-HW93.97%92.76%93.36%81.62%
2019-04-29Tencent-DPPR Team92.49%93.49%92.99%81.45%
2019-04-30SANHL_v193.86%91.98%92.91%81.43%
2019-04-30HUST_VLRGROUP92.36%91.87%92.12%79.38%
2022-04-11BDN + GCAN-RE87.89%95.72%91.64%79.01%
2024-02-01p2n90.07%91.84%90.95%78.31%
2023-03-24DeepSolo (ResNet-50)89.01%92.55%90.74%78.29%
2022-10-27ESTextSpotter91.31%94.11%92.69%78.14%
2019-04-26baseline_0.793.62%87.22%90.30%76.60%
2021-12-11ABINet++89.20%92.72%90.93%76.45%
2019-04-30SECAI90.99%89.59%90.28%74.35%
2019-04-30Task4-re390.80%90.26%90.53%73.43%
2019-04-30pursuer86.12%92.73%89.30%72.76%
2019-04-30HUST_e2e91.54%90.28%90.91%71.89%
2020-10-13AE TextSpotter89.98%93.38%91.65%71.83%
2019-04-29CLTDR88.89%88.92%88.91%71.81%
2019-04-30MCEM v384.64%89.56%87.03%71.10%
2022-03-24test93.50%84.41%88.72%70.51%
2021-11-26test112689.08%86.84%87.95%66.93%
2021-09-20ABCNetv287.91%92.89%90.33%63.94%
2022-03-23ABCNet88.76%92.07%90.39%61.27%
2022-03-24text pt77.09%80.88%78.94%52.82%
2019-04-30submit269.49%89.52%78.24%50.36%
2019-04-30CRAFT + TPS-ResNet v375.89%78.44%77.14%41.68%
2022-03-25test68.69%66.67%67.66%37.14%

Ranking Graphic

Ranking Graphic