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/MANGO

MANGO

Reported on 7 benchmarks across 1 task · 1 paper · 5 SOTA

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

Computer Vision7 results

  • Text SpottingonTotal-Text
    F-measure (%) - Full Lexicon· 2020-12-08
    83.6
    best: 89.6 (DeepSolo (ViTAEv2-S, TextOCR))
    SOTA
    MANGO: A Mask Attention Guided One-Stage Scene Text SpotterarXiv:2012.04350
  • Text SpottingonTotal-Text
    F-measure (%) - No Lexicon· 2020-12-08
    72.9
    best: 83.6 (DeepSolo (ViTAEv2-S, TextOCR))
    SOTA
    MANGO: A Mask Attention Guided One-Stage Scene Text SpotterarXiv:2012.04350
  • Text SpottingonSCUT-CTW1500
    F-Measure (%) - Full Lexicon· 2020-12-08
    78.7
    best: 83.8 (SPTS)
    SOTA
    MANGO: A Mask Attention Guided One-Stage Scene Text SpotterarXiv:2012.04350
  • Text SpottingonSCUT-CTW1500
    F-measure (%) - No Lexicon· 2020-12-08
    58.9
    best: 64.4 (A3S)
    SOTA
    MANGO: A Mask Attention Guided One-Stage Scene Text SpotterarXiv:2012.04350
  • Text SpottingonICDAR 2015
    F-measure (%) - Weak Lexicon· 2020-12-08
    78.9
    best: 84.1 (UNITS)
    SOTA
    MANGO: A Mask Attention Guided One-Stage Scene Text SpotterarXiv:2012.04350
  • Text SpottingonICDAR 2015
    F-measure (%) - Generic Lexicon· 2020-12-08
    67.3
    best: 80.3 (UNITS)
    MANGO: A Mask Attention Guided One-Stage Scene Text SpotterarXiv:2012.04350
  • Text SpottingonICDAR 2015
    F-measure (%) - Strong Lexicon· 2020-12-08
    81.8
    best: 89 (UNITS)
    MANGO: A Mask Attention Guided One-Stage Scene Text SpotterarXiv:2012.04350