- Task 1 - Detection
- Task 2 - Detection-Linking
- Task 3 - Detection-Recognition
- Task 4 - Detection-Recognition-Linking
method: dino_mvit2024-04-29
Authors: Rajat Kumar Singh, Himani Shrotriya, Shivshankar Reddy, Himanshu Bhatt
Affiliation: American Express
Email: rajatks@outlook.com
Description: We trained MViTv2 for Rumsey Map and Mask DINO for IGN map. To further improve the performance, we crop the image into 4 equal parts, we predict on original image and all 4 cropped images and combine the output.
method: dino_map2024-04-29
Authors: Rajat Kumar Singh, Himani Shrotriya, Shivshankar Reddy, Himanshu Bhatt
Affiliation: American Express
Email: rajatks@outlook.com
Description: We trained Mask DINO for both the maps. To further improve the performance, we crop the image into 4 parts with some overlap, we predict on original image and all 4 cropped images and combine the output.
method: MapTest2024-04-29
Authors: Hongen Liu
Affiliation: Tianjin University
Date | Method | Quality | F-score | Tightness | Precision | Recall | |||
---|---|---|---|---|---|---|---|---|---|
2024-04-29 | dino_mvit | 64.75% | 89.73% | 72.16% | 88.68% | 90.81% | |||
2024-04-29 | dino_map | 64.75% | 89.73% | 72.16% | 88.68% | 90.81% | |||
2024-04-29 | MapTest | 64.22% | 91.91% | 69.87% | 90.83% | 93.02% | |||
2024-04-27 | ensem | 52.05% | 72.87% | 71.43% | 90.79% | 60.86% | |||
2024-03-26 | DS-LP | 44.08% | 67.78% | 65.03% | 64.85% | 71.00% | |||
2024-05-06 | MapText Detection Strong Pipeline | 42.33% | 61.10% | 69.29% | 82.51% | 48.51% | |||
2024-04-29 | MapDet | 35.73% | 54.70% | 65.33% | 70.13% | 44.84% | |||
2024-03-26 | Baseline TESTR Checkpoint | 20.56% | 29.19% | 70.46% | 86.38% | 17.56% |