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/ST-GR

ST-GR

Reported on 8 benchmarks across 8 tasks

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

Computer Vision3 results

  • VideoonKinetics-Skeleton dataset
    Accuracy
    33.6
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
  • Temporal Action LocalizationonKinetics-Skeleton dataset
    Accuracy
    33.6
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
  • Action LocalizationonKinetics-Skeleton dataset
    Accuracy
    33.6
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))

Time Series2 results

  • Action DetectiononKinetics-Skeleton dataset
    Accuracy
    33.6
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))
  • Action RecognitiononKinetics-Skeleton dataset
    Accuracy
    33.6
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))

Methodology1 result

  • Zero-Shot LearningonKinetics-Skeleton dataset
    Accuracy
    33.6
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))

Robots1 result

  • Activity RecognitiononKinetics-Skeleton dataset
    Accuracy
    33.6
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))

Natural Language Processing1 result

  • 3D Action RecognitiononKinetics-Skeleton dataset
    Accuracy
    33.6
    best: 52.3 (Structured Keypoint Pooling (PPNv2 skeletons+objects))