Video Captioning On Msrvtt Ctn
Metrics
CIDEr
ROUGE-L
SPICE
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | CIDEr | ROUGE-L | SPICE |
|---|---|---|---|
| narrativebridge-enhancing-video-captioning | 49.87 | 27.90 | 15.76 |
| sem-pos-grammatically-and-semantically | 26.01 | 20.11 | 12.09 |
| action-knowledge-for-video-captioning-with | 25.90 | 21.42 | 11.99 |
| git-towards-generalist-vision-transformer | 32.43 | 24.51 | 13.70 |