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/MGP-STR

MGP-STR

Reported on 27 benchmarks across 3 tasks · 1 paper · 27 SOTA

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

Computer Vision18 results

  • Scene ParsingonSVT
    Accuracy· uses extra data· 2022-09-08
    98.6
    best: 99.1 (CLIP4STR-H (DFN-5B))
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • Scene ParsingonSVTP
    Accuracy· uses extra data· 2022-09-08
    98.3
    best: 98.6 (DTrOCR 105M)
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • Scene ParsingonCUTE80
    Accuracy· uses extra data· 2022-09-08
    99.31
    best: 99.7 (CPPD)
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • Scene ParsingonUber-Text
    Accuracy (%)· uses extra data· 2022-09-08
    91
    best: 92.2 (CLIP4STR-L (DataComp-1B))
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • Scene ParsingonCOCO-Text
    1:1 Accuracy· uses extra data· 2022-09-08
    81.7
    best: 81.9 (CLIP4STR-L)
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • Scene ParsingonIC19-Art
    Accuracy (%)· uses extra data· 2022-09-08
    85.5
    best: 86.4 (CLIP4STR-L (DataComp-1B))
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • Scene ParsingonICDAR2015
    Accuracy· uses extra data· 2022-09-08
    90.9
    best: 93.5 (DTrOCR 105M)
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • Scene ParsingonIIIT5k
    Accuracy· uses extra data· 2022-09-08
    98.8
    best: 99.6 (CLIP4STR-L (DataComp-1B))
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • Scene ParsingonICDAR2013
    Accuracy· uses extra data· 2022-09-08
    98.5
    best: 99.42 (CLIP4STR-L*)
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • Scene Text RecognitiononSVT
    Accuracy· uses extra data· 2022-09-08
    98.6
    best: 99.1 (CLIP4STR-H (DFN-5B))
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • Scene Text RecognitiononSVTP
    Accuracy· uses extra data· 2022-09-08
    98.3
    best: 98.6 (DTrOCR 105M)
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • Scene Text RecognitiononCUTE80
    Accuracy· uses extra data· 2022-09-08
    99.31
    best: 99.7 (CPPD)
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • Scene Text RecognitiononUber-Text
    Accuracy (%)· uses extra data· 2022-09-08
    91
    best: 92.2 (CLIP4STR-L (DataComp-1B))
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • Scene Text RecognitiononCOCO-Text
    1:1 Accuracy· uses extra data· 2022-09-08
    81.7
    best: 81.9 (CLIP4STR-L)
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • Scene Text RecognitiononIC19-Art
    Accuracy (%)· uses extra data· 2022-09-08
    85.5
    best: 86.4 (CLIP4STR-L (DataComp-1B))
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • Scene Text RecognitiononICDAR2015
    Accuracy· uses extra data· 2022-09-08
    90.9
    best: 93.5 (DTrOCR 105M)
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • Scene Text RecognitiononIIIT5k
    Accuracy· uses extra data· 2022-09-08
    98.8
    best: 99.6 (CLIP4STR-L (DataComp-1B))
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • Scene Text RecognitiononICDAR2013
    Accuracy· uses extra data· 2022-09-08
    98.5
    best: 99.42 (CLIP4STR-L*)
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592

Audio9 results

  • 2D Semantic SegmentationonSVT
    Accuracy· uses extra data· 2022-09-08
    98.6
    best: 99.1 (CLIP4STR-H (DFN-5B))
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • 2D Semantic SegmentationonSVTP
    Accuracy· uses extra data· 2022-09-08
    98.3
    best: 98.6 (DTrOCR 105M)
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • 2D Semantic SegmentationonCUTE80
    Accuracy· uses extra data· 2022-09-08
    99.31
    best: 99.7 (CPPD)
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • 2D Semantic SegmentationonUber-Text
    Accuracy (%)· uses extra data· 2022-09-08
    91
    best: 92.2 (CLIP4STR-L (DataComp-1B))
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • 2D Semantic SegmentationonCOCO-Text
    1:1 Accuracy· uses extra data· 2022-09-08
    81.7
    best: 81.9 (CLIP4STR-L)
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • 2D Semantic SegmentationonIC19-Art
    Accuracy (%)· uses extra data· 2022-09-08
    85.5
    best: 86.4 (CLIP4STR-L (DataComp-1B))
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • 2D Semantic SegmentationonICDAR2015
    Accuracy· uses extra data· 2022-09-08
    90.9
    best: 93.5 (DTrOCR 105M)
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • 2D Semantic SegmentationonIIIT5k
    Accuracy· uses extra data· 2022-09-08
    98.8
    best: 99.6 (CLIP4STR-L (DataComp-1B))
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592
  • 2D Semantic SegmentationonICDAR2013
    Accuracy· uses extra data· 2022-09-08
    98.5
    best: 99.42 (CLIP4STR-L*)
    SOTA
    Multi-Granularity Prediction for Scene Text RecognitionarXiv:2209.03592