- Task 1 - Detection
- Task 2 - Detection-Linking
- Task 3 - Detection-Recognition
- Task 4 - Detection-Recognition-Linking
method: MapTest2024-04-29
Authors: Hongen Liu
Affiliation: Tianjin University
method: DS-LP2024-03-26
Authors: hsy
Affiliation: BUPT
Description: Four tasks unified submission
DeepSolo, Multi-Polygon NMS (word detection and recognition) -> LayoutPointer (word linking)
method: MapText Detection and Recognition Strong Pipeline2024-05-06
Authors: Yu Xie, Jielei Zhang, Ziyue Wang, Yuchen He, Yihan Meng, Weihang Wang, Peiyi Li, Longwen Gao
Affiliation: Bilibili Inc.
Description: In the end-to-end task of MapText, we used ViTAE-v 2 to extract global features, utilizing an encoder-decoder network architecture (DeepSolo). Data augmentation techniques such as cropping, scaling, saturation, and contrast adjustment were applied. Pre-training was conducted using available real datasets (TextOCR, TotalText, IC15, MLT2017). The model was fine-tuned on the MapText dataset, and post-processing methods were employed.
Zhang, Q., Xu, Y., Zhang, J., & Tao, D. (2023). Vitaev2: Vision transformer advanced by exploring inductive bias for image recognition and beyond. International Journal of Computer Vision, 131(5), 1141-1162.
Ye, M., Zhang, J., Zhao, S., Liu, J., Liu, T., Du, B., & Tao, D. (2023). Deepsolo: Let transformer decoder with explicit points solo for text spotting. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 19348-19357).
| Date | Method | Quality | F-score | Tightness | Recall | Precision | |||
|---|---|---|---|---|---|---|---|---|---|
| 2024-04-29 | MapTest | 40.06% | 56.65% | 70.71% | 57.34% | 55.98% | |||
| 2024-03-26 | DS-LP | 26.06% | 39.69% | 65.66% | 41.57% | 37.97% | |||
| 2024-05-06 | MapText Detection and Recognition Strong Pipeline | 8.65% | 12.18% | 70.98% | 9.67% | 16.45% | |||
| 2024-03-26 | Baseline TESTR Checkpoint | 2.18% | 2.92% | 74.71% | 1.75% | 8.63% |