Video Summarization on TVSum (test)
0.675F-scoreMAVS
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MAVSDoesn't require training data=false, Text-queryable=false2025.06 | 0.675 | — | — | |
| CLIP-ItDoesn't require training data=false, Text-queryable=true2025.06 | 0.663 | — | — | |
| CLIP-ItFeature Backbone=GoogLeNet2023.03 | 0.642 | 0.108 | 0.147 | |
| re-SEQ2SEQDoesn't require training data=false, Text-queryable=false2025.06 | 0.639 | — | — | |
| iPTNetFeature Backbone=GoogLeNet2023.03 | 0.634 | 0.134 | 0.163 | |
| A2SummFeature Backbone=GoogLeNet2023.03 | 0.634 | 0.137 | 0.165 | |
| iPTNetDoesn't require training data=false, Text-queryable=false2025.06 | 0.634 | — | — | |
| A2SummDoesn't require training data=false, Text-queryable=false2025.06 | 0.634 | — | — | |
| Prompts-to-SummariesDoesn't require training data=true, Text-queryable=true2025.06 | 0.6222 | — | — | |
| DSNet-ABFeature Backbone=GoogLeNet2023.03 | 0.621 | 0.108 | 0.129 | |
| SegSumDoesn't require training data=false, Text-queryable=false2025.06 | 0.6202 | — | — | |
| DSNet-AFFeature Backbone=GoogLeNet2023.03 | 0.619 | 0.113 | 0.138 | |
| DMASumSetting=Canonical2020.08 | 0.614 | — | — | |
| VASNetFeature Backbone=GoogLeNet2023.03 | 0.614 | — | — | |
| RS-SUMDoesn't require training data=false, Text-queryable=false2025.06 | 0.614 | — | — | |
| SUM-GANSetting=Augmented2020.08 | 0.612 | — | — | |
| DMASumSetting=Augmented2020.08 | 0.612 | — | — | |
| STeMI (Few-shot)Doesn't require training data=false, Text-queryable=false2025.06 | 0.6089 | — | — | |
| A-AVSData Setting=Augmented2021.09 | 0.608 | — | — | |
| AC-SUM-GANDoesn't require training data=false, Text-queryable=false2025.06 | 0.606 | — | — | |
| DMASumSetting=Transfer2020.08 | 0.605 | — | — | |
| HMTData Setting=Augmented2021.09 | 0.603 | — | — | |
| HMTData Setting=Canonical2021.09 | 0.601 | — | — | |
| RSGNFeature Backbone=GoogLeNet2023.03 | 0.601 | 0.083 | 0.09 | |
| DR-DSNSetting=Augmented2020.08 | 0.598 | — | — | |
| DPP-LSTMSetting=Augmented2020.08 | 0.596 | — | — | |
| A-AVSData Setting=Canonical2021.09 | 0.594 | — | — | |
| CSNetSetting=Transfer2020.08 | 0.592 | — | — | |
| CSNetSetting=Augmented2020.08 | 0.59 | — | — | |
| DR-DSNSetting=Transfer2020.08 | 0.589 | — | — | |
| VASNetData Setting=Canonical2021.09 | 0.589 | — | — | |
| CSNetSetting=Canonical2020.08 | 0.588 | — | — | |
| DPP-LSTMSetting=Transfer2020.08 | 0.587 | — | — | |
| VASNetData Setting=Augmented2021.09 | 0.585 | — | — | |
| CSNetFeature Backbone=GoogLeNet2023.03 | 0.585 | 0.025 | 0.034 | |
| Contrastive (Zero-Shot)Doesn't require training data=true, Text-queryable=false2025.06 | 0.584 | — | — | |
| SASUMsupData Setting=Canonical2021.09 | 0.582 | — | — | |
| DR-DSNSetting=Canonical2020.08 | 0.581 | — | — | |
| DR-DSNFeature Backbone=GoogLeNet2023.03 | 0.581 | 0.02 | 0.026 | |
| RandomFeature Backbone=GoogLeNet2023.03 | 0.57 | 0 | 0 | |
| RandomDoesn't require training data=true, Text-queryable=false2025.06 | 0.5643 | — | — | |
| DPP-LSTMSetting=Canonical2020.08 | 0.547 | — | — | |
| SUM-GANSetting=Canonical2020.08 | 0.543 | — | — | |
| HumanFeature Backbone=GoogLeNet2023.03 | 0.54 | 0.177 | 0.204 | |
| dppLSTM-attData Setting=Canonical2021.09 | 0.539 | — | — | |
| SASUMData Setting=Canonical2021.09 | 0.539 | — | — | |
| HSA-RNNFeature Backbone=GoogLeNet2023.03 | 0.441 | 0.082 | 0.088 |