Highlight Detection on QVHighlights
0.453mAPMeCo
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MeCoEvaluation Protocol=Dataset-wise fine-tuning, Backbone=QWen2VL, Model Scale=7B2025.03 | 0.453 | 75.1 | |
| MeCoEvaluation Protocol=Dataset-wise fine-tuning, Backbone=ETChat, Model Scale=7B2025.03 | 0.447 | 74.3 | |
| MeCoEvaluation Protocol=Dataset-wise fine-tuning, Backbone=ETChat, Model Scale=3.8B2025.03 | 0.446 | 71.8 | |
| CG-DETREvaluation Protocol=Dataset-wise fine-tuning2025.03 | 0.408 | 66.7 | |
| UMTEvaluation Protocol=Dataset-wise fine-tuning2025.03 | 0.399 | 64.2 | |
| MeCoEvaluation Protocol=Zero-shot (Fine-tuned on E.T.Instruct), Backbone=ETChat, Model Scale=7B2025.03 | 0.395 | 64.3 | |
| MeCoEvaluation Protocol=Zero-shot (Fine-tuned on E.T.Instruct), Backbone=ETChat, Model Scale=3.8B2025.03 | 0.392 | 61.8 | |
| QD-DETREvaluation Protocol=Dataset-wise fine-tuning2025.03 | 0.391 | 63 | |
| UniVTGEvaluation Protocol=Dataset-wise fine-tuning2025.03 | 0.388 | 61.8 | |
| MeCoEvaluation Protocol=Zero-shot (Fine-tuned on E.T.Instruct), Backbone=QWen2VL, Model Scale=7B2025.03 | 0.372 | 57.9 | |
| M-DETREvaluation Protocol=Dataset-wise fine-tuning2025.03 | 0.357 | 55.6 | |
| TRACEModel Scale=7B2026.01 | 0.318 | 0.515 | |
| VideoLoomModel Scale=8B2026.01 | 0.275 | 0.633 | |
| TimeSuiteModel Scale=7B2026.01 | 0.27 | 0.553 | |
| VideoChat-TEvaluation Protocol=Dataset-wise fine-tuning, Model Scale=7B2025.03 | 0.27 | 55.3 | |
| TRACEEvaluation Protocol=Zero-shot (official checkpoints), Model Scale=7B2025.03 | 0.268 | 42.7 | |
| VideoChat-TEvaluation Protocol=Zero-shot (official checkpoints), Model Scale=7B2025.03 | 0.265 | 54.1 | |
| TemporalVLMEvaluation Protocol=Task-specific fine-tuning2024.12 | 0.251 | 0.43 | |
| NumPro-FTEvaluation Protocol=Zero-shot (official checkpoints), Model Scale=7B2025.03 | 0.25 | 37.2 | |
| VTG-LLMModel Scale=7B2026.01 | 0.241 | 0.413 | |
| E.T.ChatEvaluation Protocol=Zero-shot (official checkpoints), Model Scale=3.8B2025.03 | 0.232 | 58.9 | |
| E.T.ChatEvaluation Protocol=Zero-shot (Fine-tuned on E.T.Instruct), Model Scale=3.8B2025.03 | 0.232 | 58.9 | |
| TimeChatModel Scale=7B2026.01 | 0.217 | 0.379 | |
| TimeChatEvaluation Protocol=Dataset-wise fine-tuning, Model Scale=7B2025.03 | 0.217 | 37.9 | |
| TimeChatEvaluation Protocol=Task-specific fine-tuning2024.12 | 0.217 | 0.379 | |
| VTG-LLMEvaluation Protocol=Zero-shot (official checkpoints), Model Scale=7B2025.03 | 0.165 | 33.5 | |
| TimeChatEvaluation Protocol=Zero-shot (Fine-tuned on E.T.Instruct), Model Scale=7B2025.03 | 0.164 | 30.6 | |
| TRACEEvaluation Protocol=Zero-shot (Fine-tuned on E.T.Instruct), Model Scale=7B2025.03 | 0.164 | 30.6 | |
| LongVLMEvaluation Protocol=Task-specific fine-tuning2024.12 | 0.16 | 0.225 | |
| VTGLLMEvaluation Protocol=Zero-shot (Fine-tuned on E.T.Instruct), Model Scale=7B2025.03 | 0.159 | 27.1 | |
| TimeChatEvaluation Protocol=Zero-shot (official checkpoints), Model Scale=7B2025.03 | 0.145 | 23.9 | |
| MomentorEvaluation Protocol=Zero-shot (official checkpoints), Model Scale=7B2025.03 | 0.076 | — |