Table 2: 

Results of the full model on narration test data. We show the mean and standard deviation of bootstrapped scores, pooled over four training runs (chance recall@10 = 10%; chance triplet accuracy = 50%).

R@10 (fixed)R@10 (jitter)Triplet Acc
0.73 ± 0.05 0.73 ± 0.04 0.91 ± 0.01 
R@10 (fixed)R@10 (jitter)Triplet Acc
0.73 ± 0.05 0.73 ± 0.04 0.91 ± 0.01 
Close Modal

or Create an Account

Close Modal
Close Modal