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/ISTA-Net

ISTA-Net

Reported on 25 benchmarks across 8 tasks · 1 paper · 4 SOTA

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

Computer Vision11 results

  • Human Interaction RecognitiononNTU RGB+D 120
    Accuracy (Cross-Setup)· 2023-07-14
    91.7
    best: 93.2 (SkateFormer)
    SOTA
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • Human Interaction RecognitiononNTU RGB+D 120
    Accuracy (Cross-Subject)· 2023-07-14
    90.5
    best: 92.3 (SkateFormer)
    SOTA
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • VideoonAssembly101
    Actions Top-1· 2023-07-14
    28.07
    best: 41.06 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • VideoonAssembly101
    Object Top-1· 2023-07-14
    31.69
    best: 51.17 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • VideoonAssembly101
    Verbs Top-1· 2023-07-14
    62.66
    best: 69.23 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • Temporal Action LocalizationonAssembly101
    Actions Top-1· 2023-07-14
    28.07
    best: 41.06 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • Temporal Action LocalizationonAssembly101
    Object Top-1· 2023-07-14
    31.69
    best: 51.17 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • Temporal Action LocalizationonAssembly101
    Verbs Top-1· 2023-07-14
    62.66
    best: 69.23 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • Action LocalizationonAssembly101
    Actions Top-1· 2023-07-14
    28.07
    best: 41.06 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • Action LocalizationonAssembly101
    Object Top-1· 2023-07-14
    31.69
    best: 51.17 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • Action LocalizationonAssembly101
    Verbs Top-1· 2023-07-14
    62.66
    best: 69.23 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469

Robots4 results

  • Activity RecognitiononH2O (2 Hands and Objects)
    Actions Top-1· 2023-07-14
    89.09
    best: 93.39 (HandFormer-B/21x8)
    SOTA
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • Activity RecognitiononAssembly101
    Actions Top-1· 2023-07-14
    28.07
    best: 41.06 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • Activity RecognitiononAssembly101
    Object Top-1· 2023-07-14
    31.69
    best: 51.17 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • Activity RecognitiononAssembly101
    Verbs Top-1· 2023-07-14
    62.66
    best: 69.23 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469

Time Series4 results

  • Action RecognitiononH2O (2 Hands and Objects)
    Actions Top-1· 2023-07-14
    89.09
    best: 93.39 (HandFormer-B/21x8)
    SOTA
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • Action RecognitiononAssembly101
    Actions Top-1· 2023-07-14
    28.07
    best: 41.06 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • Action RecognitiononAssembly101
    Object Top-1· 2023-07-14
    31.69
    best: 51.17 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • Action RecognitiononAssembly101
    Verbs Top-1· 2023-07-14
    62.66
    best: 69.23 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469

Methodology3 results

  • Zero-Shot LearningonAssembly101
    Actions Top-1· 2023-07-14
    28.07
    best: 41.06 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • Zero-Shot LearningonAssembly101
    Object Top-1· 2023-07-14
    31.69
    best: 51.17 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • Zero-Shot LearningonAssembly101
    Verbs Top-1· 2023-07-14
    62.66
    best: 69.23 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469

Natural Language Processing3 results

  • 3D Action RecognitiononAssembly101
    Actions Top-1· 2023-07-14
    28.07
    best: 41.06 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • 3D Action RecognitiononAssembly101
    Object Top-1· 2023-07-14
    31.69
    best: 51.17 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469
  • 3D Action RecognitiononAssembly101
    Verbs Top-1· 2023-07-14
    62.66
    best: 69.23 (HandFormer-B/21)
    Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv:2307.07469