Multimodal Violence Detection on DVD (test)
75.77AccuracyCoLoRSMamba
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| CoLoRSMambaArchitecture=SSM, Modality=audio-video2026.04 | 75.77 | 72.94 | 78.07 | 75.51 | |
| LAVISHArchitecture=Transformer, Modality=audio-video2026.04 | 74.4 | 69.15 | 78.12 | 73.64 | |
| CAV-MAE SyncArchitecture=Transformer, Modality=audio-video2026.04 | 73.88 | 70.88 | 76.32 | 73.6 | |
| MBTArchitecture=Transformer, Modality=audio-video2026.04 | 73.37 | 71.45 | 75.04 | 73.25 | |
| DBVideoMambaArchitecture=SSM, Modality=video-only2026.04 | 71.82 | 70.07 | 73.38 | 71.73 | |
| CUE-NetArchitecture=CNN+Transformer, Modality=video-only2026.04 | 70.1 | 67.68 | 72.21 | 69.95 | |
| VideoMamba-MArchitecture=SSM, Modality=video-only2026.04 | 69.42 | 64.24 | 73.28 | 68.76 | |
| VideoMambaPro-MArchitecture=SSM, Modality=video-only2026.04 | 68.9 | 63.87 | 72.7 | 68.29 | |
| TIMArchitecture=Transformer, Modality=audio-video2026.04 | 68.9 | 66.04 | 71.32 | 68.68 | |
| UniFormer-V2Architecture=CNN+Transformer, Modality=video-only2026.04 | 67.35 | 64.42 | 69.84 | 67.13 | |
| DepMambaArchitecture=SSM, Modality=audio-video2026.04 | 67.18 | 63.34 | 70.29 | 66.82 | |
| VideoSwin-BArchitecture=Transformer, Modality=video-only2026.04 | 65.81 | 62.66 | 68.46 | 65.56 | |
| SlowFast-AVArchitecture=CNN, Modality=audio-video2026.04 | 65.12 | 61.77 | 67.93 | 64.85 | |
| SlowFastArchitecture=CNN, Modality=video-only2026.04 | 63.57 | 59.54 | 66.88 | 63.21 | |
| AudioMambaArchitecture=SSM, Modality=audio-only2026.04 | 62.54 | 58.71 | 65.72 | 62.22 | |
| ASTArchitecture=Transformer, Modality=audio-only2026.04 | 60.82 | 56.82 | 64.15 | 60.49 | |
| Resnet-50Architecture=CNN, Modality=audio-only2026.04 | 58.76 | 54.72 | 62.15 | 58.44 |