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/CPNet Res34, 5 CP

CPNet Res34, 5 CP

Reported on 9 benchmarks across 3 tasks · 1 paper · 5 SOTA

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

Robots3 results

  • Activity RecognitiononJester (Gesture Recognition)
    Val· 2019-05-20
    96.7
    best: 98.15 (DirecFormer)
    SOTA
    Learning Video Representations from Correspondence ProposalsarXiv:1905.07853
  • Activity RecognitiononSomething-Something V2
    Top-1 Accuracy· 2019-05-20
    57.65
    best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
    Learning Video Representations from Correspondence ProposalsarXiv:1905.07853
  • Activity RecognitiononSomething-Something V2
    Top-5 Accuracy· 2019-05-20
    83.95
    best: 96.3 (DejaVid)
    Learning Video Representations from Correspondence ProposalsarXiv:1905.07853

Time Series3 results

  • Action RecognitiononJester (Gesture Recognition)
    Val· 2019-05-20
    96.7
    best: 98.15 (DirecFormer)
    SOTA
    Learning Video Representations from Correspondence ProposalsarXiv:1905.07853
  • Action RecognitiononSomething-Something V2
    Top-1 Accuracy· 2019-05-20
    57.65
    best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
    Learning Video Representations from Correspondence ProposalsarXiv:1905.07853
  • Action RecognitiononSomething-Something V2
    Top-5 Accuracy· 2019-05-20
    83.95
    best: 96.3 (DejaVid)
    Learning Video Representations from Correspondence ProposalsarXiv:1905.07853

Computer Vision3 results

  • Action Recognition In VideosonJester (Gesture Recognition)
    Val· 2019-05-20
    96.7
    SOTA
    Learning Video Representations from Correspondence ProposalsarXiv:1905.07853
  • Action Recognition In VideosonSomething-Something V2
    Top-1 Accuracy· 2019-05-20
    57.65
    best: 64.2 (STM (16 frames, ImageNet pretraining))
    SOTA
    Learning Video Representations from Correspondence ProposalsarXiv:1905.07853
  • Action Recognition In VideosonSomething-Something V2
    Top-5 Accuracy· 2019-05-20
    83.95
    best: 89.8 (STM (16 frames, ImageNet pretraining))
    SOTA
    Learning Video Representations from Correspondence ProposalsarXiv:1905.07853