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/TimeSformer

TimeSformer

Reported on 11 benchmarks across 5 tasks · 1 paper · 1 SOTA

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

Robots3 results

  • Activity RecognitiononDiving-48
    Accuracy· 2021-02-09
    75
    best: 94.9 (LVMAE)
    Is Space-Time Attention All You Need for Video Understanding?arXiv:2102.05095
  • Activity RecognitiononSomething-Something V2
    Top-1 Accuracy· uses extra data· 2021-02-09
    59.5
    best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
    Is Space-Time Attention All You Need for Video Understanding?arXiv:2102.05095
  • Activity RecognitiononLoTE-Animal
    Accuracy (Top-1)
    70.24
    best: 79.39 (SlowOnly r50)

Time Series3 results

  • Action RecognitiononDiving-48
    Accuracy· 2021-02-09
    75
    best: 94.9 (LVMAE)
    Is Space-Time Attention All You Need for Video Understanding?arXiv:2102.05095
  • Action RecognitiononSomething-Something V2
    Top-1 Accuracy· uses extra data· 2021-02-09
    59.5
    best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
    Is Space-Time Attention All You Need for Video Understanding?arXiv:2102.05095
  • Action RecognitiononLoTE-Animal
    Accuracy (Top-1)
    70.24
    best: 79.39 (SlowOnly r50)

Computer Vision2 results

  • VideoonKinetics-400
    Acc@1· 2021-02-09
    78
    best: 93.6 (OmniVec2)
    Is Space-Time Attention All You Need for Video Understanding?arXiv:2102.05095
  • VideoonKinetics-400
    Acc@5· 2021-02-09
    93.7
    best: 98.9 (TubeViT-H (ImageNet-1k))
    Is Space-Time Attention All You Need for Video Understanding?arXiv:2102.05095

Methodology2 results

  • Anomaly DetectiononUBnormal
    RBDC· uses extra data· 2021-02-09
    0.04
    best: 25.63 (SSMTL++v1)
    Is Space-Time Attention All You Need for Video Understanding?arXiv:2102.05095
  • Anomaly DetectiononUBnormal
    TBDC· uses extra data· 2021-02-09
    0.05
    best: 63.53 (SSMTL++v1)
    Is Space-Time Attention All You Need for Video Understanding?arXiv:2102.05095

Reasoning1 result

  • Video Question AnsweringonHowto100M-QA
    Accuracy· 2021-02-09
    62.1
    SOTA
    Is Space-Time Attention All You Need for Video Understanding?arXiv:2102.05095