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/DeepSolo (ViTAEv2-S, TextOCR)

DeepSolo (ViTAEv2-S, TextOCR)

Reported on 7 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 Vision7 results

  • Text SpottingonInverse-Text
    F-measure (%) - Full Lexicon· 2023-05-31
    75.8
    SOTA
    DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text SpottingarXiv:2305.19957
  • Text SpottingonInverse-Text
    F-measure (%) - No Lexicon· 2023-05-31
    68.8
    SOTA
    DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text SpottingarXiv:2305.19957
  • Text SpottingonTotal-Text
    F-measure (%) - Full Lexicon· uses extra data· 2022-11-19
    89.6
    SOTA
    DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text SpottingarXiv:2211.10772
  • Text SpottingonTotal-Text
    F-measure (%) - No Lexicon· uses extra data· 2022-11-19
    83.6
    SOTA
    DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text SpottingarXiv:2211.10772
  • Text SpottingonICDAR 2015
    F-measure (%) - Generic Lexicon· 2022-11-19
    79.5
    best: 80.3 (UNITS)
    SOTA
    DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text SpottingarXiv:2211.10772
  • Text SpottingonICDAR 2015
    F-measure (%) - Strong Lexicon· 2022-11-19
    88.1
    best: 89 (UNITS)
    SOTA
    DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text SpottingarXiv:2211.10772
  • Text SpottingonICDAR 2015
    F-measure (%) - Weak Lexicon· 2022-11-19
    83.9
    best: 84.1 (UNITS)
    SOTA
    DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text SpottingarXiv:2211.10772