Video Summarization On Tvsum
評価指標
F1-score (Augmented)
F1-score (Canonical)
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | F1-score (Augmented) | F1-score (Canonical) | Paper Title | Repository |
|---|---|---|---|---|
| RR-STG | 63.6 | 63.0 | Relational Reasoning Over Spatial-Temporal Graphs for Video Summarization | - |
| PGL-SUM | - | 61.0 | Combining Global and Local Attention with Positional Encoding for Video Summarization | |
| CSTA | - | - | CSTA: CNN-based Spatiotemporal Attention for Video Summarization | |
| M-AVS | 61.8 | 61.0 | Video Summarization with Attention-Based Encoder-Decoder Networks | - |
| VASNet | 62.37 | 61.42 | Summarizing Videos with Attention | |
| DSNet | 63.9 | 62.1 | DSNet: A Flexible Detect-to-Summarize Network for Video Summarization |
0 of 6 row(s) selected.