TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/FOTS

FOTS

Reported on 8 benchmarks across 2 tasks · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision8 results

  • Text SpottingonICDAR 2015
    F-measure (%) - Generic Lexicon· 2018-01-05
    62.2
    best: 80.3 (UNITS)
    SOTA
    FOTS: Fast Oriented Text Spotting with a Unified NetworkarXiv:1801.01671
  • Text SpottingonICDAR 2015
    F-measure (%) - Strong Lexicon· 2018-01-05
    83.6
    best: 89 (UNITS)
    SOTA
    FOTS: Fast Oriented Text Spotting with a Unified NetworkarXiv:1801.01671
  • Text SpottingonICDAR 2015
    F-measure (%) - Weak Lexicon· 2018-01-05
    74.5
    best: 84.1 (UNITS)
    SOTA
    FOTS: Fast Oriented Text Spotting with a Unified NetworkarXiv:1801.01671
  • Scene Text DetectiononICDAR 2017 MLT
    Precision· 2018-01-05
    80.95
    best: 84.42 (PMTD*)
    FOTS: Fast Oriented Text Spotting with a Unified NetworkarXiv:1801.01671
  • Scene Text DetectiononICDAR 2017 MLT
    Recall· 2018-01-05
    57.51
    best: 76.44 (SBD)
    FOTS: Fast Oriented Text Spotting with a Unified NetworkarXiv:1801.01671
  • Scene Text DetectiononICDAR 2015
    F-Measure· 2018-01-05
    87.99
    best: 92.23 (TextFuseNet (ResNeXt-101))
    FOTS: Fast Oriented Text Spotting with a Unified NetworkarXiv:1801.01671
  • Scene Text DetectiononICDAR 2015
    Precision· 2018-01-05
    91
    best: 93.96 (TextFuseNet (ResNeXt-101))
    FOTS: Fast Oriented Text Spotting with a Unified NetworkarXiv:1801.01671
  • Scene Text DetectiononICDAR 2015
    Recall· 2018-01-05
    85.17
    best: 91.98 (CharNet H-88 (single-scale))
    FOTS: Fast Oriented Text Spotting with a Unified NetworkarXiv:1801.01671