Video Grounding on Ego4D-NLQ v1 (test)
24.96Recall@1 (Avg)RGNet
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| RGNetNaQ=true2023.12 | 24.96 | 20.63 | 12.47 | 41.67 | 25.08 | — | 19.33 | |
| UniversalVTGTraining Dataset=Unified2026.04 | 24.81 | — | — | — | — | — | — | |
| RGNetNaQ=false2023.12 | 21.81 | 18.28 | 12.04 | 34.02 | 22.89 | — | 17.8 | |
| NLQ ExpertTraining Dataset=Ego4D-NLQ2026.04 | 19.55 | — | — | — | — | — | — | |
| CONENaQ=false2023.12 | 17.67 | 14.15 | 8.18 | 30.33 | 18.02 | — | 14.34 | |
| ReLeRNaQ=true2023.12 | 17.57 | 19.31 | 11.59 | 23.62 | 15.75 | — | — | |
| EgoVLPNaQ=true2023.12 | 17.38 | 15.9 | 9.46 | 26.38 | 17.8 | — | — | |
| H-HandsNaQ=false2023.12 | 15 | 13.2 | 7.9 | 23.3 | 15.6 | — | — | |
| SnAGVisual/Text Features=EgoVLP, Training Paradigm=query-centric2024.04 | 13.57 | 15.87 | 11.26 | 38.26 | 27.16 | 32.71 | — | |
| SnAGVisual/Text Features=EgoVLP, Training Paradigm=video-centric2024.04 | 13.25 | 15.72 | 10.78 | 38.39 | 27.44 | 32.92 | — | |
| M-DETRNaQ=false2023.12 | 12.46 | 8.23 | 5.01 | 23.23 | 13.37 | — | 9.27 | |
| VSLNetNaQ=true2023.12 | 11.93 | 10.26 | 5.81 | 19.01 | 12.67 | — | — | |
| SOONetNaQ=false2023.12 | 11.31 | 8 | 3.76 | 22.4 | 11.09 | — | 12.45 | |
| CONEVisual/Text Features=EgoVLP2024.04 | 11.17 | 14.15 | 8.18 | 30.33 | 18.02 | 24.18 | — | |
| Prior Unified SOTATraining Dataset=Unified2026.04 | 9.64 | — | — | — | — | — | — | |
| VSLNetVisual/Text Features=EgoVLP2024.04 | 8.83 | 10.84 | 6.81 | 18.84 | 13.45 | 16.15 | — | |
| SnAGVisual/Text Features=SF + BERT, Training Paradigm=query-centric2024.04 | 8.79 | 10.43 | 7.15 | 27.59 | 19.33 | 23.46 | — | |
| SnAGVisual/Text Features=SF + BERT, Training Paradigm=video-centric2024.04 | 8.33 | 9.83 | 6.83 | 27.93 | 19.27 | 23.6 | — | |
| CONEVisual/Text Features=SF + BERT2024.04 | 7.72 | 10.4 | 5.03 | 22.74 | 11.87 | 17.31 | — | |
| UniVTGNaQ=false2023.12 | 7.6 | 11.74 | 3.25 | 7.54 | 7.88 | — | — | |
| 2D-TANNaQ=false2023.12 | 6.46 | 5.04 | 2.02 | 12.89 | 5.88 | — | 6.07 | |
| SOONetVisual/Text Features=SF + BERT2024.04 | 5.88 | 8 | 3.76 | 22.4 | 11.09 | 16.75 | — | |
| Charades-STA ExpertTraining Dataset=Charades-STA2026.04 | 4.35 | — | — | — | — | — | — | |
| VSLNetVisual/Text Features=SF + BERT2024.04 | 4.29 | 5.45 | 3.12 | 10.74 | 6.63 | 8.69 | — | |
| ActivityNet-Captions ExpertTraining Dataset=ActivityNet-Captions2026.04 | 3.93 | — | — | — | — | — | — | |
| 2D-TANVisual/Text Features=SF + BERT2024.04 | 3.53 | 5.04 | 2.02 | 12.89 | 5.88 | 9.39 | — | |
| TACoS ExpertTraining Dataset=TACoS2026.04 | 3.39 | — | — | — | — | — | — |