method: HUST(GSPA)2019-01-19
Authors: Changxu Cheng
Description: Convolution layers followed by 2 branches: Global Squeezer (GS) and Patch Aggregator (PA). Other process is the same as in HUST (GS). The paper will be available soon.
Confusion Matrix
| Detection | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Arabic | Latin | Chinese | Japanese | Korean | Bangla | Symbols | Mixed | None | ||
| GT | Arabic | 4807 | 263 | 8 | 22 | 24 | 9 | 9 | 0 | 0 |
| Latin | 404 | 58627 | 118 | 425 | 632 | 128 | 203 | 0 | 0 | |
| Chinese | 27 | 344 | 3383 | 872 | 97 | 5 | 22 | 0 | 0 | |
| Japanese | 90 | 2117 | 596 | 4911 | 382 | 26 | 35 | 0 | 0 | |
| Korean | 69 | 1614 | 175 | 349 | 10735 | 35 | 15 | 0 | 0 | |
| Bangla | 6 | 224 | 6 | 23 | 23 | 2260 | 3 | 0 | 0 | |
| Symbols | 110 | 664 | 7 | 70 | 65 | 15 | 2565 | 0 | 0 | |
| Mixed | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | |
| None | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | |