List your company
ResearchFormerly WizWand

Violence Detection on XD-Violence

87.61APDSRL
24.835641.132857.4373.7272Jul 12, 2022Nov 23, 2022Apr 7, 2023Aug 20, 2023Jan 2, 2024May 16, 2024Sep 28, 2024
Updated 8mo ago

Evaluation results

MethodLinks
DSRLInput Setting=Multimodal, Feature Space=Euclidean and Hyperbolic2024.0987.61
HyperVDInput Setting=Multimodal, Feature Space=Hyperbolic2024.0985.67
MSBTModality=RGB+Audio+Flow2024.0584.32
Ours (full)Learning Manner=Weakly-supervised, Modality=A+V, Parameters=0.678M2022.0783.4
Yu et al. (Full)Modality=RGB+Audio2024.0583.4
MACIL-SDInput Setting=Multimodal, Feature Space=Euclidean2024.0983.4
Xiao et al.Modality=RGB+Audio+Flow2024.0583.09
MSBTModality=RGB+Audio2024.0582.54
Ours (light)Learning Manner=Weakly-supervised, Modality=A+V, Parameters=0.347M2022.0782.17
Yu et al. (Light)Modality=RGB+Audio2024.0582.17
DSRLInput Setting=Unimodal, Feature Space=Euclidean and Hyperbolic2024.0982.01
UMILInput Setting=Multimodal, Feature Space=Euclidean2024.0981.77
Pang et al.Learning Manner=Weakly-supervised, Modality=A+V, Parameters=1.876M2022.0781.69
UMILInput Setting=Unimodal, Feature Space=Euclidean2024.0981.66
Completeness-and-Uncertainty Aware Pseudo Label EnhancementSupervision=Weakly, Feature=I3D+VGGish2022.1281.43
Zhang et al.Modality=RGB+Audio2024.0581.43
Zhang et al.Input Setting=Multimodal, Feature Space=Euclidean2024.0981.43
MSBTModality=RGB+Flow2024.0580.68
ACFModality=RGB+Audio2024.0580.13
Yu et al. (Full)Modality=RGB+Flow, re-trained=true2024.0579.73
Wu et al.Modality=RGB+Audio+Flow2024.0579.53
Pang et al.Modality=RGB+Audio2024.0579.37
Pang et al.Input Setting=Multimodal, Feature Space=Euclidean2024.0979.37
MGFNInput Setting=Unimodal, Feature Space=Euclidean2024.0979.19
Completeness-and-Uncertainty Aware Pseudo Label EnhancementSupervision=Weakly, Feature=I3D2022.1278.74
CU-NetInput Setting=Unimodal, Feature Space=Euclidean2024.0978.74
Wu et al.† [62]Learning Manner=Weakly-supervised, Modality=A+V, Parameters=1.539M, Re-implementation=integrating logits of two identical networks with audio and visual inputs2022.0778.66
Wu et al. [62]Learning Manner=Weakly-supervised, Modality=A+V, Parameters=0.843M2022.0778.64
Wu et al.Supervision=Weakly, Feature=I3D+VGGish2022.1278.64
HL-NetModality=RGB+Audio2024.0578.64
HL-NetInput Setting=Multimodal, Feature Space=Euclidean2024.0978.64
Wu et al. [29]Input Setting=Multimodal, Feature Space=Euclidean2024.0978.64
RTFM†Learning Manner=Weakly-supervised, Modality=A+V, Parameters=13.190M, Re-implementation=integrating logits of two identical networks with audio and visual inputs2022.0778.54
Yu et al. (Light)Modality=RGB+Flow, re-trained=true2024.0578.49
Li et al.Learning Manner=Weakly-supervised, Modality=V2022.0778.28
MSLSupervision=Weakly, Feature=I3D2022.1278.28
MSLInput Setting=Unimodal, Feature Space=Euclidean2024.0978.28
RTFM*Learning Manner=Weakly-supervised, Modality=A+V, Parameters=13.510M, Re-implementation=fusing audio and visual features as inputs2022.0778.1
RTFMLearning Manner=Weakly-supervised, Modality=V, Parameters=12.067M2022.0777.81
RTFMSupervision=Weakly, Feature=I3D2022.1277.81
RTFMInput Setting=Unimodal, Feature Space=Euclidean2024.0977.81
MSBTModality=Audio+Flow2024.0577.47
Yu et al. (Full)Modality=Audio+Flow, re-trained=true2024.0577.06
Yu et al. (Light)Modality=Audio+Flow, re-trained=true2024.0576.58
Wu et al. [61]Learning Manner=Weakly-supervised, Modality=V2022.0775.9
Wu et al.Supervision=Weakly, Feature=I3D+VGGish2022.1275.9
Wu et al. [27]Input Setting=Unimodal, Feature Space=Euclidean2024.0975.9
Wu et al.Supervision=Weakly, Feature=I3D2022.1275.41
Sultani et al.Learning Manner=Weakly-supervised, Modality=V2022.0773.2
Sultani et al.Supervision=Weakly, Feature=I3D+VGGish2022.1273.2
Sultani et al.Input Setting=Unimodal, Feature Space=Euclidean2024.0973.2
Wu et al.Modality=Audio+Flow2024.0572.96
SVM baselineLearning Manner=Unsupervised, Modality=V2022.0750.78
SVM baselineSupervision=Semi, Feature=I3D+VGGish2022.1250.78
Hasan et al.Learning Manner=Unsupervised, Modality=V2022.0730.77
Hasan et al.Supervision=Semi, Feature=I3D+VGGish2022.1230.77
OCSVMLearning Manner=Unsupervised, Modality=V2022.0727.25
OCSVMSupervision=Semi, Feature=I3D+VGGish2022.1227.25