From: Semantic context driven language descriptions of videos using deep neural network
Lambda Values | Model_3 | |||||||
---|---|---|---|---|---|---|---|---|
BLUE score | Other metrics | |||||||
B@1 | B@2 | B@3 | B@4 | METEOR | ROUGE | CIDEr | SPICE | |
\(\uplambda =0.1\) | 78.4 | 64.8 | 54.2 | 43.7 | 32.3 | 68.8 | 70.7 | 5.1 |
\(\uplambda =0.3\) | 76.1 | 62.1 | 50.9 | 39.7 | 31.3 | 66.9 | 67.5 | 4.9 |
\(\uplambda =0.7\) | 74.9 | 60.7 | 49.7 | 38.9 | 30.9 | 66.6 | 63.3 | 4.8 |
\(\uplambda =0.8\) | 75.2 | 61.4 | 50.7 | 40.3 | 31.2 | 67.1 | 66.9 | 5.0 |
\(\uplambda =0.9\) | 75.2 | 61.3 | 50.4 | 39.9 | 30.8 | 66.6 | 64.1 | 4.9 |