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/CAST(ViT-B/16)

CAST(ViT-B/16)

Reported on 9 benchmarks across 3 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 RecognitiononEPIC-KITCHENS-100
    Action@1· 2023-11-30
    49.3
    best: 58.3 (LLaVAction)
    CAST: Cross-Attention in Space and Time for Video Action RecognitionarXiv:2311.18825
  • Activity RecognitiononEPIC-KITCHENS-100
    Noun@1· 2023-11-30
    60.9
    best: 69 (LLaVAction)
    CAST: Cross-Attention in Space and Time for Video Action RecognitionarXiv:2311.18825
  • Activity RecognitiononEPIC-KITCHENS-100
    Verb@1· 2023-11-30
    72.5
    best: 76.2 (TIM)
    CAST: Cross-Attention in Space and Time for Video Action RecognitionarXiv:2311.18825
  • Activity RecognitiononSomething-Something V2
    Top-1 Accuracy· 2023-11-30
    71.6
    best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
    CAST: Cross-Attention in Space and Time for Video Action RecognitionarXiv:2311.18825

Time Series4 results

  • Action RecognitiononEPIC-KITCHENS-100
    Action@1· 2023-11-30
    49.3
    best: 58.3 (LLaVAction)
    CAST: Cross-Attention in Space and Time for Video Action RecognitionarXiv:2311.18825
  • Action RecognitiononEPIC-KITCHENS-100
    Noun@1· 2023-11-30
    60.9
    best: 69 (LLaVAction)
    CAST: Cross-Attention in Space and Time for Video Action RecognitionarXiv:2311.18825
  • Action RecognitiononEPIC-KITCHENS-100
    Verb@1· 2023-11-30
    72.5
    best: 76.2 (TIM)
    CAST: Cross-Attention in Space and Time for Video Action RecognitionarXiv:2311.18825
  • Action RecognitiononSomething-Something V2
    Top-1 Accuracy· 2023-11-30
    71.6
    best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
    CAST: Cross-Attention in Space and Time for Video Action RecognitionarXiv:2311.18825

Computer Vision1 result

  • VideoonKinetics-400
    Acc@1· 2023-11-30
    85.3
    best: 93.6 (OmniVec2)
    CAST: Cross-Attention in Space and Time for Video Action RecognitionarXiv:2311.18825