Cognitive Distraction Detection on CogDrive (Aggregated)
74.38AccuracyEyeCue
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| EyeCueBackbone=TimeSformerK600, Training-free=false2026.05 | 74.38 | 74 | |
| EyeCueBackbone=VideoMAEK400, Training-free=false2026.05 | 70.83 | 68 | |
| GazeVQABackbone=CLIP ViT-B/32, Training-free=false2026.05 | 67.77 | 68 | |
| VideoMAEK400Backbone=ViT-B/16, Training-free=false2026.05 | 67.21 | 66 | |
| TimeSformerK600Backbone=ViT-B/16, Training-free=false2026.05 | 66.8 | 71 | |
| Heatmap-basedBackbone=SVM, Training-free=false2026.05 | 66.12 | 64 | |
| TimeSformerK400Backbone=ViT-B/16, Training-free=false2026.05 | 65.35 | 70 | |
| EgoVideoBackbone=ViT-B/14, Training-free=false2026.05 | 65.29 | 68 | |
| Voila-ABackbone=CLIP ViT-L/14, Training-free=false2026.05 | 62.81 | 58 | |
| InternVideo2s1-1BBackbone=ViT-B/14, Training-free=false2026.05 | 56.61 | 53 | |
| Video-LLaVABackbone=OpenCLIP-L/14, Training-free=false2026.05 | 55.06 | 55 | |
| VideoLLaMA3Backbone=ViT-B/16, Training-free=false2026.05 | 53.17 | 45 | |
| GazeGPTBackbone=GLM-4.5V-AWQ, Training-free=true2026.05 | 51.69 | 48 | |
| GazeLLMBackbone=Gemini-2.5-Pro, Training-free=true2026.05 | 48.35 | 12 |