Video Summarization On Tvsum
Metrics
F1-score (Augmented)
F1-score (Canonical)
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | F1-score (Augmented) | F1-score (Canonical) |
|---|---|---|
| relational-reasoning-over-spatial-temporal | 63.6 | 63.0 |
| combining-global-and-local-attention-with | - | 61.0 |
| csta-cnn-based-spatiotemporal-attention-for | - | - |
| video-summarization-with-attention-based | 61.8 | 61.0 |
| summarizing-videos-with-attention | 62.37 | 61.42 |
| dsnet-a-flexible-detect-to-summarize-network | 63.9 | 62.1 |