Video Temporal Grounding on QVHighlights (val)
52.84mAP (Avg)FlashVTG
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| FlashVTGBackbone=InternVideo22024.12 | 52.84 | 73.1 | 57.29 | 72.75 | 54.33 | |
| MASRAFeatures=SF+C2026.05 | 50.97 | 68.97 | 54.19 | 68.93 | 52.47 | |
| FlashVTG2024.12 | 49.85 | 69.03 | 54.06 | 68.44 | 52.12 | |
| BAM-DETRFeatures=SF+C2026.05 | 47.61 | 65.1 | 51.61 | 65.41 | 48.56 | |
| R2-Tunning2024.12 | 47.59 | 68.71 | 52.06 | — | — | |
| KDAFeatures=SF+C2026.05 | 47.41 | 69.11 | 53.46 | 68.17 | 48.04 | |
| RGTRFeatures=SF+C2026.05 | 46.95 | 67.68 | 52.9 | 67.38 | 48 | |
| LLMEPET2024.12 | 46.24 | 66.58 | 51.1 | — | — | |
| UVCOM2024.12 | 45.79 | 65.1 | 51.81 | — | — | |
| UVCOMFeatures=SF+C2026.05 | 45.79 | 65.1 | 51.81 | — | — | |
| TaskWeave2024.12 | 45.38 | 64.26 | 50.06 | 65.39 | 46.47 | |
| TaskWeaveFeatures=SF+C2026.05 | 45.38 | 64.26 | 50.06 | 65.39 | 46.47 | |
| TR-DETR2024.12 | 45.09 | 67.1 | 51.48 | 66.27 | 46.42 | |
| TR-DETRFeatures=SF+C2026.05 | 45.09 | 67.1 | 51.48 | 66.27 | 46.42 | |
| CG-DETR2024.12 | 44.93 | 67.35 | 52.06 | 65.57 | 45.73 | |
| CG-DETRFeatures=SF+C2026.05 | 44.93 | 67.35 | 52.06 | 65.57 | 45.73 | |
| EaTRYear=2023, Setup=fully-supervised2024.03 | 41.74 | 61.36 | 45.79 | 61.86 | 41.91 | |
| EaTR2024.12 | 41.74 | 61.36 | 45.79 | 61.86 | 41.91 | |
| QD-DETR2024.12 | 41.22 | 62.68 | 46.66 | 62.23 | 41.82 | |
| QD-DETRFeatures=SF+C2026.05 | 41.22 | 62.68 | 46.66 | 62.23 | 41.82 | |
| QD-NetYear=2023, Setup=fully-supervised2024.03 | 40.34 | 61.71 | 44.76 | 61.88 | 39.84 | |
| MH-DETRYear=2022, Setup=fully-supervised2024.03 | 39.26 | 60.84 | 44.9 | 60.76 | 39.64 | |
| GranAlignSetup=ZS, TrC=0, InT (s)=6.2, GMU (G)=222026.01 | 39.12 | 61.94 | — | — | — | |
| UMT2024.12 | 38.59 | 60.26 | 44.26 | 56.7 | 39.9 | |
| UMTFeatures=SF+C2026.05 | 38.59 | 60.26 | 44.26 | 56.7 | 39.9 | |
| UMTYear=2023, Setup=fully-supervised2024.03 | 37.79 | — | — | — | — | |
| UniVTG2024.12 | 36.13 | 59.74 | — | — | — | |
| UniVTGFeatures=SF+C2026.05 | 36.13 | 59.74 | — | — | — | |
| Moment-GPTSetup=ZS, TrC=0, InT (s)=16.1, GMU (G)=322026.01 | 35.9 | 58.9 | — | — | — | |
| Moment-DETRYear=2021, Setup=fully-supervised2024.03 | 32.2 | 53.94 | 34.84 | — | — | |
| M-DETR2024.12 | 32.2 | 53.94 | 34.84 | — | — | |
| M-DETRFeatures=SF+C2026.05 | 32.2 | 53.94 | 34.84 | — | — | |
| VTG-GPTYear=2023, Setup=zero-shot2024.03 | 30.91 | 54.26 | 38.45 | 54.17 | 29.73 | |
| WattersserilSetup=ZS, TrC=0, InT (s)=12.7, GMU (G)=142026.01 | 30.2 | 53.1 | — | — | — | |
| Diwan et al.Year=2023, Setup=zero-shot2024.03 | 27.96 | 48.33 | 30.96 | 46.94 | 25.75 | |
| VTimeLLMSetup=FS, TrC=4090, InT (s)=40h, GMU (G)=182026.01 | 26.8 | 48.8 | — | — | — | |
| VideoChatGPTSetup=ZS, TrC=0, InT (s)=9.8, GMU (G)=112026.01 | 10.3 | 22.4 | — | — | — |