Test set
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Test Set (test)
98.5Sensitivity
15
n = 5,000 (test)
1.1Avg Brier Score (Type 1)
8
Test set n = 10,000 (test)
0.77Avg Brier Score (Type 1)
8
Test set (test)
99.47User Preference
4
Test set challenging N = 19
1.35AC Mean Error
3
Test set N = 30 (random)
1.1AC Mean Error
3
Test Set (n=140 videos)
84AUROC
1
Test Set (n=140 videos)
0.97AUROC
1
Test Set (test)
98AUROC
1