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/MMNet (RGB + Pose)

MMNet (RGB + Pose)

Reported on 16 benchmarks across 8 tasks

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

Time Series6 results

  • Action DetectiononN-UCLA
    Accuracy· uses extra data
    93.7
    best: 99.1 (DSCNet (RGB + Pose))
  • Action RecognitiononNTU RGB+D
    Accuracy (CS)· uses extra data
    96
    best: 97.4 (DSCNet (RGB + Pose))
  • Action RecognitiononNTU RGB+D
    Accuracy (CV)· uses extra data
    98.8
    best: 99.6 (PoseC3D (RGB + Pose))
  • Action RecognitiononNTU RGB+D 120
    Accuracy (Cross-Setup)· uses extra data
    94.4
    best: 96.7 (DSCNet (RGB + Pose))
  • Action RecognitiononNTU RGB+D 120
    Accuracy (Cross-Subject)· uses extra data
    92.9
    best: 95.6 (DSCNet (RGB + Pose))
  • Action RecognitiononN-UCLA
    Accuracy· uses extra data
    93.7
    best: 99.1 (DSCNet (RGB + Pose))

Robots5 results

  • Activity RecognitiononNTU RGB+D
    Accuracy (CS)· uses extra data
    96
    best: 97.4 (DSCNet (RGB + Pose))
  • Activity RecognitiononNTU RGB+D
    Accuracy (CV)· uses extra data
    98.8
    best: 99.6 (PoseC3D (RGB + Pose))
  • Activity RecognitiononNTU RGB+D 120
    Accuracy (Cross-Setup)· uses extra data
    94.4
    best: 96.7 (DSCNet (RGB + Pose))
  • Activity RecognitiononNTU RGB+D 120
    Accuracy (Cross-Subject)· uses extra data
    92.9
    best: 95.6 (DSCNet (RGB + Pose))
  • Activity RecognitiononN-UCLA
    Accuracy· uses extra data
    93.7
    best: 99.1 (DSCNet (RGB + Pose))

Computer Vision3 results

  • VideoonN-UCLA
    Accuracy· uses extra data
    93.7
    best: 99.1 (DSCNet (RGB + Pose))
  • Temporal Action LocalizationonN-UCLA
    Accuracy· uses extra data
    93.7
    best: 99.1 (DSCNet (RGB + Pose))
  • Action LocalizationonN-UCLA
    Accuracy· uses extra data
    93.7
    best: 99.1 (DSCNet (RGB + Pose))

Methodology1 result

  • Zero-Shot LearningonN-UCLA
    Accuracy· uses extra data
    93.7
    best: 99.1 (DSCNet (RGB + Pose))

Natural Language Processing1 result

  • 3D Action RecognitiononN-UCLA
    Accuracy· uses extra data
    93.7
    best: 99.1 (DSCNet (RGB + Pose))