Codesota · Models · RMIPNZheng et al.3 results · 1 benchmarks
Model card

RMIPN.

Zheng et al.open-sourceUnknown paramsRegion Multiple Information Perception plug-and-play module on DB baseline

Text Region Multiple Information Perception Network. Plug-and-play module enhancing segmentation-based text detectors. ICASSP 2024. arxiv:2401.10017.

§ 01 · Benchmarks

Every benchmark RMIPN has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01msra-td500Computer Vision · Scene Text Detectionf-measure87.5%#5/242024-01-18source ↗
02msra-td500Computer Vision · Scene Text Detectionprecision92.1%#5/232024-01-18source ↗
03msra-td500Computer Vision · Scene Text Detectionrecall83.4%#6/242024-01-18source ↗
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.
§ 02 · Strengths by area

Where RMIPN actually performs.

Computer Vision
1
benchmark
avg rank #5.3
§ 03 · Papers

1 paper with results for RMIPN.

  1. 2024-01-18· Computer Vision· 3 results

    Text Region Multiple Information Perception Network for Scene Text Detection

§ 04 · Related models

Other Zheng et al. models scored on Codesota.

BPDO
Unknown params · 0 results
§ 05 · Sources & freshness

Where these numbers come from.

arxiv
3
results
3 of 3 rows marked verified.