- Task 1 - Text Localization
- Task 2 - Script identification
- Task 3 - Joint text detection and script identification
method: TH2020-04-16
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.
method: Sogou_OCR2019-11-08
Authors: Xudong Rao, Lulu Xu, Long Ma, Xuefeng Su
Description: An arbitrary-shaped text detection method based on Mask R-CNN, we use resnext-152 as our backbone, multi-scale training and testing are adopted to get the final results.
method: AntAI-Cognition2020-04-22
Authors: Qingpei Guo, Yudong Liu, Pengcheng Yang, Yonggang Li, Yongtao Wang, Jingdong Chen, Wei Chu
Affiliation: Ant Group & PKU
Email: qingpei.gqp@antgroup.com
Description: We are from Ant Group & PKU. Our approach is an ensemble method with three text detection models. The text detection models mainly follow the MaskRCNN framework[1], with different backbones(ResNext101-64x4d[2], CBNet[3], ResNext101-32x32d_wsl[4]) used. GBDT[5] is trained to normalize confidence scores and select quadrilateral boxes with the highest quality from all text detection models' outputs. Multi-scale training and testing are adopted for all basic models. For the training set, we also add ICDAR19 MLT datasets, both training & validation sets are used to get the final result.
[1] He K, Gkioxari G, Dollár P, et al. Mask r-cnn[C]//Proceedings of the IEEE international conference on computer vision. 2017: 2961-2969. [2] Xie S, Girshick R, Dollár P, et al. Aggregated residual transformations for deep neural networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 1492-1500. [3] Liu Y, Wang Y, Wang S, et al. Cbnet: A novel composite backbone network architecture for object detection[J]. arXiv preprint arXiv:1909.03625, 2019. [4] Mahajan D, Girshick R, Ramanathan V, et al. Exploring the limits of weakly supervised pretraining[C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 181-196. [5] Ke G, Meng Q, Finley T, et al. Lightgbm: A highly efficient gradient boosting decision tree[C]//Advances in neural information processing systems. 2017: 3146-3154.
Date | Method | Hmean | Precision | Recall | Average Precision | |||
---|---|---|---|---|---|---|---|---|
2020-04-16 | TH | 59.17% | 44.09% | 89.91% | 79.49% | |||
2019-11-08 | Sogou_OCR | 57.05% | 42.33% | 87.46% | 68.55% | |||
2020-04-22 | AntAI-Cognition | 56.68% | 41.26% | 90.51% | 74.90% | |||
2019-03-29 | GNNets (single scale) | 52.80% | 39.41% | 79.97% | 47.89% | |||
2018-11-20 | Pixel-Anchor | 52.70% | 39.01% | 81.16% | 42.19% | |||
2019-08-08 | JDAI | 52.31% | 37.11% | 88.60% | 73.66% | |||
2019-05-30 | PMTD | 51.69% | 36.90% | 86.29% | 75.91% | |||
2019-05-08 | Baidu-VIS | 51.66% | 37.18% | 84.62% | 30.96% | |||
2019-03-23 | PMTD | 51.22% | 36.71% | 84.73% | 69.90% | |||
2019-06-02 | NJU-ImagineLab | 50.41% | 35.04% | 89.81% | 75.59% | |||
2019-06-11 | 4Paradigm-Data-Intelligence | 47.35% | 32.46% | 87.48% | 28.06% | |||
2019-05-23 | 4Paradigm-Data-Intelligence | 47.34% | 32.51% | 87.05% | 28.48% | |||
2018-10-29 | Amap-CVLab | 46.39% | 32.63% | 80.22% | 66.26% | |||
2019-07-15 | stela | 46.09% | 32.67% | 78.26% | 57.95% | |||
2018-05-18 | PSENet_NJU_ImagineLab (single-scale) | 45.98% | 32.86% | 76.53% | 25.15% | |||
2017-11-09 | EAST++ | 44.21% | 30.80% | 78.34% | 27.79% | |||
2019-12-13 | BDN | 43.62% | 29.16% | 86.52% | 25.00% | |||
2018-11-28 | CRAFT | 43.46% | 31.91% | 68.09% | 22.40% | |||
2018-11-15 | USTC-NELSLIP | 43.44% | 29.18% | 84.97% | 69.13% | |||
2017-06-28 | SCUT_DLVClab1 | 43.07% | 31.35% | 68.79% | 47.05% | |||
2018-12-04 | SPCNet_TongJi & UESTC (multi scale) | 41.71% | 28.26% | 79.62% | 22.37% | |||
2018-03-12 | ATL Cangjie OCR | 40.05% | 26.58% | 81.19% | 64.38% | |||
2019-01-08 | ALGCD_CP | 39.92% | 26.57% | 80.24% | 24.09% | |||
2018-12-05 | EPTN-SJTU | 38.53% | 25.66% | 77.32% | 21.78% | |||
2019-05-30 | Thesis-SE | 37.74% | 25.09% | 76.08% | 21.23% | |||
2017-06-29 | SARI_FDU_RRPN_v1 | 34.74% | 22.99% | 71.06% | 51.15% | |||
2018-12-03 | SPCNet_TongJi & UESTC (single scale) | 31.65% | 19.72% | 80.12% | 15.98% | |||
2017-06-28 | SARI_FDU_RRPN_v0 | 29.58% | 18.86% | 68.59% | 35.58% | |||
2017-06-30 | TH-DL | 29.11% | 20.54% | 49.94% | 30.05% | |||
2017-06-30 | Sensetime OCR | 16.23% | 9.03% | 80.09% | 47.00% | |||
2017-06-30 | linkage-ER-Flow | 4.81% | 2.95% | 13.05% | 0.99% |