Model card
pil_maskrcnn.
ICT, Chinese Academy of Sciencesopen-sourceUnknown paramsMask R-CNN based scene text detector
Winner of ICDAR 2019 ArT text detection task. Team from Institute of Computing Technology, CAS.
§ 01 · Benchmarks
Every benchmark pil_maskrcnn has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | ICDAR 2019 ArT | Computer Vision · Scene Text Detection | f-measure | 82.7% | #1 | 2019-09-16 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Papers
1 paper with results for pil_maskrcnn.
- 2019-09-16· Computer Vision· 1 result
ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
1
result
1 of 1 rows marked verified.