Table 2 Performance evaluation of various approaches in trailer generation.
From: Automatic trailer generation for movies using convolutional neural network
Methods | Precision | Recall | F-measure | AUC of PRC | Avg. user scores |
|---|---|---|---|---|---|
Proposed | 0.5669 | 0.4500 | 0.5018 | 0.4482 | 6.4686 |
Prop. (visual features) | 0.3728 | 0.4207 | 0.3953 | 0.3123 | 4.8515 |
Prop. (subtitle features) | 0.4213 | 0.3103 | 0.3573 | 0.3316 | 4.3916 |
Prop. (no genre identification) | 0.4341 | 0.3892 | 0.4105 | 0.3494 | 4.2965 |
SmartTrailer22 | 0.4821 | 0.4242 | 0.4513 | 0.3931 | 6.0348 |
Movie2Trailer23 | 0.4110 | 0.3760 | 0.3927 | 0.3320 | 5.7832 |
