Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Cognitive Distraction Detection on DADA 2000 (Leave-one-dataset-out)
Loading...
68.29
Accuracy
EyeCue
48.322
53.506
58.69
63.874
May 8, 2026
Accuracy
F1 Score
Updated 23d ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
EyeCue
Backbone=TimeSformerK6...
2026.05
68.29
68
Voila-A
Backbone=CLIP ViT-L/14...
2026.05
67.68
67
Heatmap-based
Backbone=SVM, Training...
2026.05
65.85
64
TimeSformerK400
Backbone=ViT-B/16, Tra...
2026.05
62.63
63
EyeCue
Backbone=VideoMAEK400,...
2026.05
62.5
62
TimeSformerK600
Backbone=ViT-B/16, Tra...
2026.05
61.89
53
VideoMAEK400
Backbone=ViT-B/16, Tra...
2026.05
61.28
60
GazeVQA
Backbone=CLIP ViT-B/32...
2026.05
59.45
47
EgoVideo
Backbone=ViT-B/14, Tra...
2026.05
59.15
63
VideoLLaMA3
Backbone=ViT-B/16, Tra...
2026.05
53.26
38
Video-LLaVA
Backbone=OpenCLIP-L/14...
2026.05
52.09
47
GazeGPT
Backbone=GLM-4.5V-AWQ,...
2026.05
51.81
53
InternVideo2s1-1B
Backbone=ViT-B/14, Tra...
2026.05
50.51
45
GazeLLM
Backbone=Gemini-2.5-Pr...
2026.05
49.09
28
Feedback
Search any
task
Search any
task