Moment Query on Ego4D (test)
0.325mAP (IoU Avg)InternVideo + EgoVideo-V + EgoVideo-MQ
Evaluation results
| Method | Links | ||
|---|---|---|---|
| InternVideo + EgoVideo-V + EgoVideo-MQFeature=InternVideo + EgoVideo-V + EgoVideo-MQ2024.06 | 0.325 | 0.5007 | |
| InternVideo + EgoVideo-VFeature=InternVideo + EgoVideo-V2024.06 | 0.3152 | 0.4922 | |
| Slowfast + Omnivore + EgoVLP + InternVideoFeature=Slowfast + Omnivore + EgoVLP + InternVideo2024.06 | 0.2934 | 0.485 | |
| ASLFeatures=EgoVLP2025.02 | 0.223 | — | |
| ActionFormerFeatures=SlowFast+Omnivore+EgoVLP, Fusion=Proj+Cat2022.11 | 0.2176 | 0.4254 | |
| Hier-EgoPackFeatures=EgoVLP2025.02 | 0.18 | — | |
| ActionFormerFeatures=SlowFast+Omnivore, Fusion=Cat2022.11 | 0.1792 | 0.3551 | |
| ActionFormerFeatures=EgoVLP2025.02 | 0.175 | — | |
| VSGNVis-text Enc=Frozen+EgoNCE, Vis-text PT=EgoClip2022.06 | 0.1033 | 0.2803 | |
| VSGNFeatures=EgoVLP2025.02 | 0.103 | — | |
| VSGNVis-text Enc=Frozen, Vis-text PT=EgoClip2022.06 | 0.0978 | 0.2798 | |
| VSGNVis-text Enc=Frozen, Vis-text PT=CC3M+WebVid-2M2022.06 | 0.0595 | 0.1974 | |
| VSGNVis-text Enc=SlowFast, Vis-text PT=-2022.06 | 0.0568 | 0.2425 | |
| VSGNFeatures=SlowFast, Fusion=n/a2022.11 | 0.0568 | 0.2425 | |
| Ego4D BaselineFeatures=SlowFast2025.02 | 0.0568 | — | |
| VSGNVis-text Enc=Frozen, Vis-text PT=HowTo100M2022.06 | 0.0528 | 0.1806 |