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/SegLink

SegLink

Reported on 8 benchmarks across 1 task · 2 papers · 7 SOTA

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

Computer Vision8 results

  • Scene Text DetectiononICDAR 2013
    Recall· 2017-03-19
    83
    best: 93.1 (CRAFT)
    SOTA
    Detecting Oriented Text in Natural Images by Linking SegmentsarXiv:1703.06520
  • Scene Text DetectiononMSRA-TD500
    F-Measure· 2017-03-19
    77
    best: 89.4 (MixNet)
    SOTA
    Detecting Oriented Text in Natural Images by Linking SegmentsarXiv:1703.06520
  • Scene Text DetectiononMSRA-TD500
    Precision· 2017-03-19
    86
    best: 92.1 (FAST-B-736)
    SOTA
    Detecting Oriented Text in Natural Images by Linking SegmentsarXiv:1703.06520
  • Scene Text DetectiononMSRA-TD500
    Recall· 2017-03-19
    70
    best: 88.1 (MixNet)
    SOTA
    Detecting Oriented Text in Natural Images by Linking SegmentsarXiv:1703.06520
  • Scene Text DetectiononICDAR 2015
    F-Measure· 2016-04-14
    75
    best: 92.23 (TextFuseNet (ResNeXt-101))
    SOTA
    Multi-Oriented Text Detection with Fully Convolutional NetworksarXiv:1604.04018
  • Scene Text DetectiononICDAR 2015
    Precision· 2016-04-14
    73.1
    best: 93.96 (TextFuseNet (ResNeXt-101))
    SOTA
    Multi-Oriented Text Detection with Fully Convolutional NetworksarXiv:1604.04018
  • Scene Text DetectiononICDAR 2015
    Recall· 2016-04-14
    76.8
    best: 91.98 (CharNet H-88 (single-scale))
    SOTA
    Multi-Oriented Text Detection with Fully Convolutional NetworksarXiv:1604.04018
  • Scene Text DetectiononICDAR 2013
    Precision· 2017-03-19
    87.7
    best: 97.4 (CRAFT)
    Detecting Oriented Text in Natural Images by Linking SegmentsarXiv:1703.06520