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/TSA (Kmeans)

TSA (Kmeans)

Reported on 10 benchmarks across 2 tasks · 1 paper · 6 SOTA

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

Computer Vision10 results

  • Action LocalizationonBreakfast
    F1· 2023-04-13
    58
    SOTA
    Leveraging triplet loss for unsupervised action segmentationarXiv:2304.06403
  • Action LocalizationonBreakfast
    mIoU· 2023-04-13
    53.3
    SOTA
    Leveraging triplet loss for unsupervised action segmentationarXiv:2304.06403
  • Action LocalizationonYoutube INRIA Instructional
    F1· 2023-04-13
    55.3
    SOTA
    Leveraging triplet loss for unsupervised action segmentationarXiv:2304.06403
  • Action SegmentationonBreakfast
    F1· 2023-04-13
    58
    SOTA
    Leveraging triplet loss for unsupervised action segmentationarXiv:2304.06403
  • Action SegmentationonBreakfast
    mIoU· 2023-04-13
    53.3
    SOTA
    Leveraging triplet loss for unsupervised action segmentationarXiv:2304.06403
  • Action SegmentationonYoutube INRIA Instructional
    F1· 2023-04-13
    55.3
    SOTA
    Leveraging triplet loss for unsupervised action segmentationarXiv:2304.06403
  • Action LocalizationonBreakfast
    Acc· 2023-04-13
    63.7
    best: 78 (AdaFocus (newly extracted I3D-features, LT-Context model))
    Leveraging triplet loss for unsupervised action segmentationarXiv:2304.06403
  • Action LocalizationonYoutube INRIA Instructional
    Acc· 2023-04-13
    59.7
    best: 62.4 (TSA (FINCH))
    Leveraging triplet loss for unsupervised action segmentationarXiv:2304.06403
  • Action SegmentationonBreakfast
    Acc· 2023-04-13
    63.7
    best: 78 (AdaFocus (newly extracted I3D-features, LT-Context model))
    Leveraging triplet loss for unsupervised action segmentationarXiv:2304.06403
  • Action SegmentationonYoutube INRIA Instructional
    Acc· 2023-04-13
    59.7
    best: 62.4 (TSA (FINCH))
    Leveraging triplet loss for unsupervised action segmentationarXiv:2304.06403