MoPRL

Reported on 5 benchmarks across 3 tasks · 1 paper · 4 SOTA

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

Methodology3 results

Anomaly DetectiononCorridor
AUC· 2021-12-07
71.63
SOTA
Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection arXiv:2112.03649
Anomaly DetectiononHR-ShanghaiTech
AUC· 2021-12-07
84.3
best: 87.23 (PoseWatch-H)
SOTA
Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection arXiv:2112.03649
Anomaly DetectiononShanghaiTech
AUC· 2021-12-07
83.35
best: 88.8 (LMM_VAD)
Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection arXiv:2112.03649

Computer Vision2 results

3D Anomaly DetectiononHR-ShanghaiTech
AUC· 2021-12-07
84.3
best: 87.23 (PoseWatch-H)
SOTA
Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection arXiv:2112.03649
Video Anomaly DetectiononHR-ShanghaiTech
AUC· 2021-12-07
84.3
best: 87.23 (PoseWatch-H)
SOTA
Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection arXiv:2112.03649