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/Prob-Distill

Prob-Distill

Reported on 8 benchmarks across 2 tasks · 1 paper

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

Robots4 results

  • Activity RecognitiononHMDB-51
    Average accuracy of 3 splits· 2019-04-05
    72
    best: 88.7 (VideoMAE V2-g)
    Attention Distillation for Learning Video RepresentationsarXiv:1904.03249
  • Activity RecognitiononSomething-Something V2
    Top-1 Accuracy· 2019-04-05
    49.9
    best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
    Attention Distillation for Learning Video RepresentationsarXiv:1904.03249
  • Activity RecognitiononSomething-Something V2
    Top-5 Accuracy· 2019-04-05
    79.1
    best: 96.3 (DejaVid)
    Attention Distillation for Learning Video RepresentationsarXiv:1904.03249
  • Activity RecognitiononUCF101
    3-fold Accuracy· 2019-04-05
    95.7
    best: 99.7 (FTP-UniFormerV2-L/14)
    Attention Distillation for Learning Video RepresentationsarXiv:1904.03249

Time Series4 results

  • Action RecognitiononHMDB-51
    Average accuracy of 3 splits· 2019-04-05
    72
    best: 88.7 (VideoMAE V2-g)
    Attention Distillation for Learning Video RepresentationsarXiv:1904.03249
  • Action RecognitiononSomething-Something V2
    Top-1 Accuracy· 2019-04-05
    49.9
    best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
    Attention Distillation for Learning Video RepresentationsarXiv:1904.03249
  • Action RecognitiononSomething-Something V2
    Top-5 Accuracy· 2019-04-05
    79.1
    best: 96.3 (DejaVid)
    Attention Distillation for Learning Video RepresentationsarXiv:1904.03249
  • Action RecognitiononUCF101
    3-fold Accuracy· 2019-04-05
    95.7
    best: 99.7 (FTP-UniFormerV2-L/14)
    Attention Distillation for Learning Video RepresentationsarXiv:1904.03249