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/AdaFocus (newly extracted I3D-features, LT-Context model)

AdaFocus (newly extracted I3D-features, LT-Context model)

Reported on 12 benchmarks across 2 tasks · 1 paper · 10 SOTA

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

Computer Vision12 results

  • Action LocalizationonBreakfast
    Acc· 2023-11-28
    78
    SOTA
    Towards Weakly Supervised End-to-end Learning for Long-video Action RecognitionarXiv:2311.17118
  • Action LocalizationonBreakfast
    Average F1· 2023-11-28
    76.2
    SOTA
    Towards Weakly Supervised End-to-end Learning for Long-video Action RecognitionarXiv:2311.17118
  • Action LocalizationonBreakfast
    F1@10%· 2023-11-28
    82.1
    SOTA
    Towards Weakly Supervised End-to-end Learning for Long-video Action RecognitionarXiv:2311.17118
  • Action LocalizationonBreakfast
    F1@25%· 2023-11-28
    79
    SOTA
    Towards Weakly Supervised End-to-end Learning for Long-video Action RecognitionarXiv:2311.17118
  • Action LocalizationonBreakfast
    F1@50%· 2023-11-28
    67.5
    SOTA
    Towards Weakly Supervised End-to-end Learning for Long-video Action RecognitionarXiv:2311.17118
  • Action SegmentationonBreakfast
    Acc· 2023-11-28
    78
    SOTA
    Towards Weakly Supervised End-to-end Learning for Long-video Action RecognitionarXiv:2311.17118
  • Action SegmentationonBreakfast
    Average F1· 2023-11-28
    76.2
    SOTA
    Towards Weakly Supervised End-to-end Learning for Long-video Action RecognitionarXiv:2311.17118
  • Action SegmentationonBreakfast
    F1@10%· 2023-11-28
    82.1
    SOTA
    Towards Weakly Supervised End-to-end Learning for Long-video Action RecognitionarXiv:2311.17118
  • Action SegmentationonBreakfast
    F1@25%· 2023-11-28
    79
    SOTA
    Towards Weakly Supervised End-to-end Learning for Long-video Action RecognitionarXiv:2311.17118
  • Action SegmentationonBreakfast
    F1@50%· 2023-11-28
    67.5
    SOTA
    Towards Weakly Supervised End-to-end Learning for Long-video Action RecognitionarXiv:2311.17118
  • Action LocalizationonBreakfast
    Edit· 2023-11-28
    78.3
    best: 79.7 (FACT (efficient hybrid of convolution and transformer model))
    Towards Weakly Supervised End-to-end Learning for Long-video Action RecognitionarXiv:2311.17118
  • Action SegmentationonBreakfast
    Edit· 2023-11-28
    78.3
    best: 79.7 (FACT (efficient hybrid of convolution and transformer model))
    Towards Weakly Supervised End-to-end Learning for Long-video Action RecognitionarXiv:2311.17118