List your company
ResearchFormerly WizWand

Video Anomaly Detection on ShanghaiTech standard (test)

97.98Frame-Level AUCProDisc-VAD
49.848862.344474.8487.3356Dec 11, 2018Jan 4, 2020Jan 27, 2021Feb 21, 2022Mar 17, 2023Apr 9, 2024May 4, 2025
Updated 8mo ago

Evaluation results

MethodLinks
ProDisc-VADReference=This work, Feature=ViT-B/162025.0597.98——
Cho et al.Reference=CVPR23, Feature=I3D2025.0597.6——
DARReference=TIFS22, Feature=I3D2025.0597.54——
VadCLIPReference=AAAI24, Feature=ViT-B/162025.0597.49——
S3RReference=ECCV22, Feature=I3D2025.0597.48——
RTFMReference=ICCV21, Feature=I3D2025.0597.21——
MSLReference=AAAI22, Feature=I3D2025.0596.08——
MISTReference=CVPR21, Feature=I3D2025.0594.83——
RTFMReference=ICCV21, Feature=C3D2025.0591.51——
CLAWSReference=ECCV20, Feature=C3D2025.0589.67——
STG-NF2022.1185.952.182.4
Sultani et al.Reference=CVPR18, Feature=I3D2025.0585.33——
AnomalyRulerZero-shot=false2025.0385.2——
object-centric convolutional auto-encoders2018.1284.9——
Wang et al.Input=Pre-trained object detection results2022.1184.222.460.8
Barbalau et al. (SSMTL++v2)Input=Pre-trained object detection results2022.1183.847.185.6
Georgescu et al. + SSPCABInput=Pre-trained object detection results2022.1183.640.683.5
MULDEZero-shot=false2025.0381.3——
AnyAnomalyZero-shot=true, Context-aware=true2025.0379.7——
AnyAnomalyCross-domain training=false, Few-shot adaptation=false, Auxiliary datasets=false2025.0379.7——
Zaheer et al.2022.1179.6——
MA-PDMZero-shot=false2025.0379.2——
AED-MAEZero-shot=false2025.0379.1——
SLMZero-shot=false2025.0378.8——
Shibao et al.Cross-domain training=true, Few-shot adaptation=false, Auxiliary datasets=true2025.0378.7——
FPDMZero-shot=false2025.0378.6——
rGANCross-domain training=true, Few-shot adaptation=true, Auxiliary datasets=false2025.0377.9——
AnyAnomalyZero-shot=true, Context-aware=false2025.0377.2——
Sultani et al.pre-trained model=true2018.1276.5——
Zhong et al.Reference=CVPR19, Feature=C3D2025.0576.44——
AccI-VADZero-shot=false2025.0376.2——
Markovitz et al.Input=Pose data2022.1176.1——
Rodrigues et al.Input=Pose data2022.1176——
DLAN-ACZero-shot=false2025.0374.7——
MPNZero-shot=false2025.0373.8——
USTN-DSCZero-shot=false2025.0373.8——
MPNCross-domain training=true, Few-shot adaptation=true, Auxiliary datasets=false2025.0373.8——
AMMC-NetZero-shot=false2025.0373.7——
STEAL-NetZero-shot=false2025.0373.7——
Morais et al.Input=Pose data2022.1173.4——
Liu et al. [21]2018.1272.8——
zxVADCross-domain training=true, Few-shot adaptation=false, Auxiliary datasets=true2025.0371.6——
Video-ChatGPTCross-domain training=false, Few-shot adaptation=false, Auxiliary datasets=false2025.0369.1——
Luo et al.2018.1268——
ZS ImageBindCross-domain training=false, Few-shot adaptation=false, Auxiliary datasets=false2025.0361.3——
ZS CLIPCross-domain training=false, Few-shot adaptation=false, Auxiliary datasets=false2025.0360.9——
Hasan et al.2018.1260.9——
LLaVA-1.5Cross-domain training=false, Few-shot adaptation=false, Auxiliary datasets=false2025.0359.6——
JigsawCross-domain training=true, Few-shot adaptation=false, Auxiliary datasets=false2025.0359.3——
STEAL-NetCross-domain training=true, Few-shot adaptation=false, Auxiliary datasets=false2025.0351.7——