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/SPTS

SPTS

Reported on 7 benchmarks across 1 task · 1 paper · 2 SOTA

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

Computer Vision7 results

  • Text SpottingonSCUT-CTW1500
    F-Measure (%) - Full Lexicon· 2021-12-15
    83.8
    SOTA
    SPTS: Single-Point Text SpottingarXiv:2112.07917
  • Text SpottingonSCUT-CTW1500
    F-measure (%) - No Lexicon· 2021-12-15
    63.6
    best: 64.4 (A3S)
    SOTA
    SPTS: Single-Point Text SpottingarXiv:2112.07917
  • Text SpottingonInverse-Text
    F-measure (%) - Full Lexicon· 2021-12-15
    46.2
    best: 75.8 (DeepSolo (ViTAEv2-S, TextOCR))
    SPTS: Single-Point Text SpottingarXiv:2112.07917
  • Text SpottingonInverse-Text
    F-measure (%) - No Lexicon· 2021-12-15
    38.3
    best: 68.8 (DeepSolo (ViTAEv2-S, TextOCR))
    SPTS: Single-Point Text SpottingarXiv:2112.07917
  • Text SpottingonICDAR 2015
    F-measure (%) - Generic Lexicon· 2021-12-15
    65.8
    best: 80.3 (UNITS)
    SPTS: Single-Point Text SpottingarXiv:2112.07917
  • Text SpottingonICDAR 2015
    F-measure (%) - Strong Lexicon· 2021-12-15
    77.5
    best: 89 (UNITS)
    SPTS: Single-Point Text SpottingarXiv:2112.07917
  • Text SpottingonICDAR 2015
    F-measure (%) - Weak Lexicon· 2021-12-15
    70.2
    best: 84.1 (UNITS)
    SPTS: Single-Point Text SpottingarXiv:2112.07917