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/HDM-BG

HDM-BG

Reported on 17 benchmarks across 8 tasks

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

Computer Vision6 results

  • VideoonUPenn Action
    Accuracy
    93.4
    best: 97.9 (UNIK)
  • VideoonGaming 3D (G3D)
    Accuracy
    92
    best: 96 (CNN)
  • Temporal Action LocalizationonUPenn Action
    Accuracy
    93.4
    best: 97.9 (UNIK)
  • Temporal Action LocalizationonGaming 3D (G3D)
    Accuracy
    92
    best: 96 (CNN)
  • Action LocalizationonUPenn Action
    Accuracy
    93.4
    best: 97.9 (UNIK)
  • Action LocalizationonGaming 3D (G3D)
    Accuracy
    92
    best: 96 (CNN)

Time Series4 results

  • Action DetectiononUPenn Action
    Accuracy
    93.4
    best: 97.9 (UNIK)
  • Action DetectiononGaming 3D (G3D)
    Accuracy
    92
    best: 96 (CNN)
  • Action RecognitiononUPenn Action
    Accuracy
    93.4
    best: 97.9 (UNIK)
  • Action RecognitiononGaming 3D (G3D)
    Accuracy
    92
    best: 96 (CNN)

Robots3 results

  • Activity RecognitiononUPenn Action
    Accuracy
    93.4
    best: 97.9 (UNIK)
  • Activity RecognitiononGaming 3D (G3D)
    Accuracy
    92
    best: 96 (CNN)
  • Activity RecognitiononUTD-MHAD
    Accuracy (CS)
    92.8
    best: 94.5 (PoseMap)

Methodology2 results

  • Zero-Shot LearningonUPenn Action
    Accuracy
    93.4
    best: 97.9 (UNIK)
  • Zero-Shot LearningonGaming 3D (G3D)
    Accuracy
    92
    best: 96 (CNN)

Natural Language Processing2 results

  • 3D Action RecognitiononUPenn Action
    Accuracy
    93.4
    best: 97.9 (UNIK)
  • 3D Action RecognitiononGaming 3D (G3D)
    Accuracy
    92
    best: 96 (CNN)