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/HF2-VAD

HF2-VAD

Reported on 6 benchmarks across 3 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 Vision4 results

  • 3D Anomaly DetectiononPed2
    AUC· 2021-08-16
    0.993
    SOTA
    A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame PredictionarXiv:2108.06852
  • 3D Anomaly DetectiononShanghaiTech Campus
    AUC· 2021-08-16
    76.2
    best: 85.75 (PoseWatch-H)
    SOTA
    A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame PredictionarXiv:2108.06852
  • Video Anomaly DetectiononPed2
    AUC· 2021-08-16
    0.993
    SOTA
    A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame PredictionarXiv:2108.06852
  • Video Anomaly DetectiononShanghaiTech Campus
    AUC· 2021-08-16
    76.2
    best: 85.75 (PoseWatch-H)
    SOTA
    A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame PredictionarXiv:2108.06852

Methodology2 results

  • Anomaly DetectiononPed2
    AUC· 2021-08-16
    0.993
    SOTA
    A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame PredictionarXiv:2108.06852
  • Anomaly DetectiononShanghaiTech Campus
    AUC· 2021-08-16
    76.2
    best: 85.75 (PoseWatch-H)
    SOTA
    A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame PredictionarXiv:2108.06852