SSMTL++v2

Reported on 5 benchmarks across 1 task · 1 paper

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

Methodology5 results

Anomaly DetectiononShanghaiTech
RBDC· uses extra data· 2022-07-16
47.1
best: 59.21 (EVAL)
SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection arXiv:2207.08003
Anomaly DetectiononShanghaiTech
TBDC· uses extra data· 2022-07-16
85.6
best: 89.44 (EVAL)
SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection arXiv:2207.08003
Anomaly DetectiononCUHK Avenue
FPS
19
best: 1670 (SD-MAE)
Anomaly DetectiononCUHK Avenue
RBDC
47.8
best: 68.2 (EVAL)
Anomaly DetectiononCUHK Avenue
TBDC
85.2
best: 89.28 (HF2VAD+SSPCAB)