Query-focused Video Summarization on QFVS
57.13Video Score 1CLIP-It
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| CLIP-ItBackbone=CLIP-Image, Query=true, Architecture=Transformer2021.07 | 57.13 | 53.6 | 66.08 | 41.41 | 54.55 | |
| CLIP-ItProperty=Supervised, Requires training data=true, Backbone=CLIP-Image2025.06 | 57.13 | 53.6 | 66.08 | 41.41 | 54.44 | |
| ResNet + Query + TransformerBackbone=ResNet, Query=true, Architecture=Transformer2021.07 | 55.19 | 51.03 | 64.26 | 39.47 | 52.49 | |
| CLIP-ItProperty=Supervised, Requires training data=true, Backbone=ResNet2025.06 | 55.19 | 51.03 | 64.26 | 39.47 | 52.49 | |
| CLIP-Image + Query + bi-LSTMBackbone=CLIP-Image, Query=true, Architecture=bi-LSTM2021.07 | 54.47 | 48.59 | 62.81 | 38.64 | 51.13 | |
| Prompts-to-SummariesProperty=Zero-Shot, Requires training data=false, Normalization=(MinMax + Exp) norm2025.06 | 53.57 | 55.66 | 63.25 | 41.2 | 53.42 | |
| Prompts-to-SummariesProperty=Zero-Shot, Requires training data=false, Normalization=MinMax norm2025.06 | 51.47 | 50.86 | 61.29 | 37.51 | 50.28 | |
| IntentVizorProperty=Supervised, Requires training data=true2025.06 | 51.27 | 53.48 | 61.58 | 37.25 | 50.9 | |
| QFVS2021.07 | 48.68 | 41.66 | 56.47 | 29.96 | 44.19 | |
| QFVSProperty=Supervised, Requires training data=true2025.06 | 48.68 | 41.66 | 56.47 | 29.96 | 44.19 | |
| Prompts-to-SummariesProperty=Zero-Shot, Requires training data=false, Normalization=Exp norm2025.06 | 48.66 | 50 | 55.26 | 42.63 | 49.14 | |
| QSANProperty=Supervised, Requires training data=true2025.06 | 48.52 | 46.64 | 56.93 | 34.25 | 46.59 | |
| SeqDPP2021.07 | 36.59 | 43.67 | 25.26 | 18.15 | 30.92 | |
| SeqDPPProperty=Supervised, Requires training data=true2025.06 | 36.59 | 43.67 | 25.26 | 18.15 | 30.92 | |
| SH-DPP2021.07 | 35.67 | 42.74 | 36.51 | 18.62 | 33.38 | |
| SH-DPPProperty=Supervised, Requires training data=true2025.06 | 35.67 | 42.74 | 36.51 | 18.62 | 33.38 |