Codesota · Models · DPNet (ResNet-50, 736px)Fang et al.3 results · 1 benchmarks
Model card

DPNet (ResNet-50, 736px).

Fang et al.open-sourceUnknown paramsResNet-50 + Channel Enhanced Self-Attention Module (CESAM) + Spatial Enhanced Self-Attention Module (SESAM)

Dual Perspective CNN-Transformer for scene text detection. Integrates CESAM and SESAM into ResNet backbone. 736×736 input. PLOS ONE 2024. DOI:10.1371/journal.pone.0309286.

§ 01 · Benchmarks

Every benchmark DPNet (ResNet-50, 736px) has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01msra-td500Computer Vision · Scene Text Detectionf-measure86.7%#9/242024-10-15source ↗
02msra-td500Computer Vision · Scene Text Detectionprecision91.4%#10/232024-10-15source ↗
03msra-td500Computer Vision · Scene Text Detectionrecall82.5%#11/242024-10-15source ↗
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 DPNet (ResNet-50, 736px) actually performs.

Computer Vision
1
benchmark
avg rank #10.0
§ 03 · Papers

1 paper with results for DPNet (ResNet-50, 736px).

  1. 2024-10-15· Computer Vision· 3 results

    DPNet: Scene Text Detection Based on Dual Perspective CNN-Transformer

§ 04 · Related models

Other Fang et al. models scored on Codesota.

ABINet-LV
Unknown params · 0 results
§ 05 · Sources & freshness

Where these numbers come from.

arxiv
3
results
3 of 3 rows marked verified.