| Benchmark | Model | Rank | Results |
|---|---|---|---|
| temporal-action-localization-on-ego4d-mq-validation | ActionFormer + VideoMAE-L (InternVideo-Ego4D) | #1 | mAP Avg IoU=0.1:0.5: 23.29R@1 IoU=0.5: 40.36 |
| short-term-object-interaction-anticipation-on-ego4d | InternVideo | #4 | Overall (Top5 mAP): 3.4Noun (Top5 mAP): 24.6Noun+Verb(Top5 mAP): 9.18… |
| natural-language-queries-on-ego4d | InternVideo | #6 | R@1 Mean(0.3 and 0.5): 13.26R@1 IoU=0.3: 16.45R@1 IoU=0.5: 10.06… |