- Task 1 - Text Localization
- Task 2 - Script identification
- Task 3 - Joint text detection and script identification
- Task 4 - End-to-End text detection and recognition
method: CPN (multi-scale)2024-05-30
Authors: Longhuang Wu, Shangxuan Tian, Youxin Wang, Pengfei Xiong
Email: wlonghuang@gmail.com
Description: We propose a Complementary Proposal Network (CPN) that seamlessly and parallelly integrates semantic and geometric information for superior performance. This Result is achieved with single Swin-L backbone and multi-scale testing policy. No model ensemble is used.
method: SituTech_OCR2021-03-11
Authors: Kui Lyu, Chuanhe Liu
Affiliation: Beijing Situ Vision Technologies Co. Ltd
Email: lvkui@situdata.com
Description: In this work, we design an elegant text detection model. Our detector is similar to DBNet, but there are some difference. More specifically, we have introduced an advanced detector backbone, a classic network EfficientDet, with flexible scales and stronger ability to extract features. Another breakthrough is that we optimized the label generation strategy in DBNet. In the original work, the positive area generation and the expansion of the positive area to the bounding box used the Vatti clipping algorithm, which is less robust with different area perimeter ratios. We optimized this function to make the label transform between positive area and bounding box more reasonable.
If you have any questions, please contact us.
SituAIgorithm Team, Beijing Situ Vision Technologies Co. Ltd
method: TH2020-04-19
Authors: Tsinghua University and Hyundai Motor Group AIRS Company
Email: Shanyu Xiao: xiaosy19@mails.tsinghua.edu.cn
Description: We have built an end-to-end scene text spotter based on Mask R-CNN & Transformer. The ResNeXt-101 backbone and multiscale training/testing are used.
| Date | Method | Hmean | Precision | Recall | Average Precision | |||
|---|---|---|---|---|---|---|---|---|
| 2024-05-30 | CPN (multi-scale) | 85.97% | 89.08% | 83.06% | 80.78% | |||
| 2021-03-11 | SituTech_OCR | 84.80% | 93.41% | 77.64% | 72.43% | |||
| 2020-04-19 | TH | 84.67% | 89.54% | 80.30% | 77.90% | |||
| 2019-11-11 | Sogou_OCR | 83.72% | 89.60% | 78.57% | 76.23% | |||
| 2019-06-04 | Tencent-DPPR Team | 83.61% | 87.52% | 80.05% | 77.33% | |||
| 2019-06-04 | Tencent-DPPR Team (Method_v0.3) | 83.61% | 87.57% | 79.99% | 77.28% | |||
| 2019-06-04 | multi-stage_text_detector_v4 | 83.59% | 87.75% | 79.80% | 70.00% | |||
| 2019-06-03 | Tencent-DPPR Team (Method_v0.2) | 83.55% | 87.78% | 79.72% | 77.05% | |||
| 2019-06-04 | multi-stage_text_detector_v2 | 83.32% | 87.04% | 79.91% | 69.51% | |||
| 2019-06-04 | multi-stage_text_detector_v3 | 83.30% | 87.15% | 79.78% | 69.49% | |||
| 2019-06-03 | multi-stage_text_detector | 83.25% | 87.47% | 79.42% | 69.44% | |||
| 2019-06-03 | NJU-ImagineLab(v3) | 83.07% | 87.85% | 78.79% | 76.21% | |||
| 2019-05-30 | PMTD | 82.53% | 87.47% | 78.12% | 75.80% | |||
| 2019-05-27 | Tencent-DPPR Team (Method_v0.1) | 81.88% | 89.41% | 75.52% | 72.87% | |||
| 2019-05-29 | maskrcnn++ result | 80.35% | 82.64% | 78.19% | 64.64% | |||
| 2019-05-29 | IC_RL | 80.11% | 82.97% | 77.44% | 64.29% | |||
| 2022-11-02 | ESTextSpotter | 79.24% | 83.37% | 75.50% | 72.52% | |||
| 2019-06-02 | A two-stage text detector based on cascade rcnn(using total 10000 images of mlt19) | 78.38% | 82.26% | 74.85% | 71.27% | |||
| 2019-05-31 | A two-stage text detector based on cascade rcnn | 78.11% | 82.89% | 73.85% | 70.31% | |||
| 2021-02-04 | NCU_MSP | 78.00% | 83.08% | 73.51% | 60.82% | |||
| 2019-06-03 | mm-maskrcnn_v2 | 76.79% | 84.73% | 70.21% | 67.44% | |||
| 2019-06-04 | TH-DL-v2 | 76.64% | 84.55% | 70.09% | 64.44% | |||
| 2019-06-03 | TH-DL-v1 | 76.59% | 84.51% | 70.03% | 64.35% | |||
| 2019-05-27 | TH-DL | 76.53% | 84.70% | 69.80% | 64.07% | |||
| 2023-05-22 | DeepSolo++ (ResNet-50) | 76.31% | 86.69% | 68.16% | 66.13% | |||
| 2020-05-30 | NCU | 75.80% | 78.54% | 73.25% | 57.06% | |||
| 2020-10-16 | Drew | 75.42% | 83.71% | 68.63% | 65.03% | |||
| 2019-05-26 | two stage text detector | 75.04% | 82.61% | 68.74% | 65.29% | |||
| 2019-06-03 | sot | 74.24% | 79.96% | 69.28% | 65.94% | |||
| 2023-05-30 | TD-PPIoU | 74.06% | 75.61% | 72.56% | 68.64% | |||
| 2019-06-02 | DISTILLED CRAFT | 72.94% | 81.22% | 66.19% | 59.16% | |||
| 2019-06-03 | text-mountain | 71.95% | 72.12% | 71.77% | 51.90% | |||
| 2019-06-03 | CRAFTS | 70.86% | 81.42% | 62.73% | 56.63% | |||
| 2019-06-04 | Unicamp-SRBR-MLT2019-PELEETEXT | 70.81% | 81.58% | 62.54% | 59.01% | |||
| 2019-06-03 | RRPN | 69.56% | 77.71% | 62.95% | 58.07% | |||
| 2019-06-04 | Unicamp-SRBR-MLT2019-FUSION-PSENET-PELEETEXT | 68.56% | 77.00% | 61.79% | 56.03% | |||
| 2019-05-28 | CRAFTS(Initial) | 68.11% | 79.51% | 59.56% | 54.50% | |||
| 2019-06-04 | Lomin OCR | 67.65% | 71.62% | 64.09% | 57.95% | |||
| 2019-06-03 | NXB OCR | 65.96% | 70.59% | 61.90% | 43.72% | |||
| 2019-05-24 | PSENet_v1 | 65.83% | 73.52% | 59.59% | 52.73% | |||
| 2019-05-27 | MLT2019 ETD | 64.36% | 78.71% | 54.44% | 42.93% | |||
| 2019-05-27 | CLTDR | 63.53% | 77.20% | 53.97% | 41.63% | |||
| 2020-10-23 | MEAST_V3_23_Oct | 61.64% | 70.02% | 55.04% | 39.81% | |||
| 2020-10-07 | MEAST_V2_8_oct | 61.49% | 70.45% | 54.55% | 39.66% | |||
| 2019-05-27 | NXB OCR | 61.31% | 71.84% | 53.48% | 38.48% | |||
| 2019-06-03 | TP | 58.01% | 77.59% | 46.32% | 37.26% | |||
| 2019-05-28 | Unicamp-SRBR-MLT2019-S1 | 51.00% | 75.22% | 38.58% | 35.30% | |||
| 2019-06-04 | Cyberspace | 47.09% | 69.48% | 35.61% | 26.17% | |||
| 2019-05-28 | PydBox-TextDetector | 29.79% | 59.56% | 19.86% | 11.83% | |||
| 2020-12-15 | DSIT-UOA | 23.43% | 28.42% | 19.93% | 7.83% | |||
| 2019-05-05 | AAAA | 0.02% | 0.07% | 0.01% | 0.00% | |||
| 2019-05-27 | Unicamp-SRBR-MLT2019-S1 | 0.00% | 0.03% | 0.00% | 0.00% | |||
| 2019-06-01 | tsinghuaee51_MLT2019 | 0.00% | 0.04% | 0.00% | 0.00% | |||
| 2019-05-27 | 4Paradigm-Data-Intelligence | 0.00% | 0.00% | 0.00% | 0.00% |