- Task 1 - Character Recognition
- Task 2 - Text Line Recognition
- Task 3 - Text Line Detection
- Task 4 - End-to-End Text Spotting
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）
method: SCUT-UOA-HW2019-09-17
Authors: Canjie Luo, Yuliang Liu, Tianwei Wang, Tong He, Lianwen Jin, Chunhua Shen, Liangwei Wang
Affiliation: South China University of Techonologe, University of Adelaide, Huawei
Description: The paper is in preparation.
| Date | Method | Recall | Precision | Hmean | 1-NED | |||
|---|---|---|---|---|---|---|---|---|
| 2023-04-14 | AAIG-OCR-NLP | 93.11% | 93.98% | 93.54% | 83.60% | |||
| 2019-10-12 | NSTD-MCEM-iFLYTEK | 93.16% | 93.63% | 93.40% | 81.96% | |||
| 2019-09-17 | SCUT-UOA-HW | 93.97% | 92.76% | 93.36% | 81.62% | |||
| 2019-04-29 | Tencent-DPPR Team | 92.49% | 93.49% | 92.99% | 81.45% | |||
| 2019-04-30 | SANHL_v1 | 93.86% | 91.98% | 92.91% | 81.43% | |||
| 2019-04-30 | HUST_VLRGROUP | 92.36% | 91.87% | 92.12% | 79.38% | |||
| 2022-04-11 | BDN + GCAN-RE | 87.89% | 95.72% | 91.64% | 79.01% | |||
| 2024-02-01 | p2n | 90.07% | 91.84% | 90.95% | 78.31% | |||
| 2023-03-24 | DeepSolo (ResNet-50) | 89.01% | 92.55% | 90.74% | 78.29% | |||
| 2022-10-27 | ESTextSpotter | 91.31% | 94.11% | 92.69% | 78.14% | |||
| 2019-04-26 | baseline_0.7 | 93.62% | 87.22% | 90.30% | 76.60% | |||
| 2021-12-11 | ABINet++ | 89.20% | 92.72% | 90.93% | 76.45% | |||
| 2019-04-30 | SECAI | 90.99% | 89.59% | 90.28% | 74.35% | |||
| 2019-04-30 | Task4-re3 | 90.80% | 90.26% | 90.53% | 73.43% | |||
| 2019-04-30 | pursuer | 86.12% | 92.73% | 89.30% | 72.76% | |||
| 2019-04-30 | HUST_e2e | 91.54% | 90.28% | 90.91% | 71.89% | |||
| 2020-10-13 | AE TextSpotter | 89.98% | 93.38% | 91.65% | 71.83% | |||
| 2019-04-29 | CLTDR | 88.89% | 88.92% | 88.91% | 71.81% | |||
| 2019-04-30 | MCEM v3 | 84.64% | 89.56% | 87.03% | 71.10% | |||
| 2022-03-24 | test | 93.50% | 84.41% | 88.72% | 70.51% | |||
| 2021-11-26 | test1126 | 89.08% | 86.84% | 87.95% | 66.93% | |||
| 2021-09-20 | ABCNetv2 | 87.91% | 92.89% | 90.33% | 63.94% | |||
| 2022-03-23 | ABCNet | 88.76% | 92.07% | 90.39% | 61.27% | |||
| 2022-03-24 | text pt | 77.09% | 80.88% | 78.94% | 52.82% | |||
| 2019-04-30 | submit2 | 69.49% | 89.52% | 78.24% | 50.36% | |||
| 2019-04-30 | CRAFT + TPS-ResNet v3 | 75.89% | 78.44% | 77.14% | 41.68% | |||
| 2022-03-25 | test | 68.69% | 66.67% | 67.66% | 37.14% |