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/SignBERT+

SignBERT+

Reported on 6 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision6 results

  • Sign Language RecognitiononMSASL-1000
    P-C Top-1 Accuracy· uses extra data· 2023-05-08
    70.77
    best: 76.97 (Uni-Sign)
    SOTA
    SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language UnderstandingarXiv:2305.04868
  • Sign Language RecognitiononMSASL-1000
    P-I Top-1 Accuracy· uses extra data· 2023-05-08
    73.71
    best: 78.16 (Uni-Sign)
    SOTA
    SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language UnderstandingarXiv:2305.04868
  • Sign Language TranslationonRWTH-PHOENIX-Weather 2014 T
    BLEU-4· 2023-05-08
    25.7
    best: 29.03 (MSKA-SLT)
    SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language UnderstandingarXiv:2305.04868
  • Sign Language RecognitiononWLASL
    Top-1 Accuracy· 2023-05-08
    55.59
    best: 61.17 (StepNet)
    SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language UnderstandingarXiv:2305.04868
  • Sign Language RecognitiononRWTH-PHOENIX-Weather 2014
    Word Error Rate (WER)· 2023-05-08
    20
    best: 18.3 (SlowFastSign)
    SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language UnderstandingarXiv:2305.04868
  • Sign Language RecognitiononRWTH-PHOENIX-Weather 2014 T
    Word Error Rate (WER)· 2023-05-08
    19.9
    best: 18.7 (SlowFastSign)
    SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language UnderstandingarXiv:2305.04868