Event Localization on YouCook2 (val)
32.51RecallHiCM²
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| HiCM²PT=true, Backbone=CLIP2024.12 | 32.51 | 32.51 | 32.51 | |
| HiCM2Pre-trained=true2026.03 | 32.51 | 32.51 | 32.51 | |
| STaRCPre-trained=true2026.03 | 31.53 | 37.7 | 34.34 | |
| Sali4VidPre-trained=true2026.03 | 31.11 | 36.57 | 33.61 | |
| DIBSPretrain=56k, Backbone=UniVL2024.04 | 30.8 | 45.13 | — | |
| Vid2SeqPT=true, Backbone=CLIP, Note=reproduced from official implementation2024.12 | 30.38 | 31.81 | 31.08 | |
| Vid2SeqPre-trained=true2026.03 | 30.38 | 31.81 | 31.08 | |
| PDVCPretrain=Ø, Backbone=UniVL2024.04 | 29.66 | 42.04 | — | |
| Vid2SeqBackbone=CLIP2023.02 | 27.9 | 27.8 | — | |
| Vid2SeqPretrain=15M, Backbone=CLIP2024.04 | 27.9 | 27.8 | — | |
| DIBSPretrain=56k, Backbone=CLIP2024.04 | 26.24 | 39.18 | — | |
| DIBSPT=true, Backbone=CLIP2024.12 | 26.24 | 39.81 | 31.43 | |
| DIBSPre-trained=true2026.03 | 26.24 | 39.81 | 31.43 | |
| CACMIPre-trained=false2026.03 | 25.54 | 34.63 | 29.34 | |
| E2DVCPre-trained=false2026.03 | 25.01 | 34.13 | 28.87 | |
| CM2PT=false, Backbone=CLIP2024.12 | 24.76 | 33.38 | 28.43 | |
| CM2Pre-trained=false2026.03 | 24.76 | 33.38 | 28.43 | |
| PDVCPT=false, Backbone=CLIP2024.12 | 22.89 | 32.37 | 26.81 | |
| PDVCPre-trained=false2026.03 | 22.89 | 32.37 | 26.81 | |
| PDVCPretrain=Ø, Backbone=CLIP2024.04 | 21.76 | 31.92 | — | |
| SAILSetting=Weakly-Supervised, Features=CLIP2026.03 | 20.76 | 21.13 | 20.94 | |
| E2ESGBackbone=C3D, Source=Results provided by the authors2023.02 | 20.7 | 20.6 | — | |
| ILCACMSetting=Weakly-Supervised, Features=CLIP, Implementation=Re-implementation2026.03 | 17.76 | 18.01 | 17.88 | |
| E2ESGPretrain=Ø, Backbone=C3D2024.04 | 3.49 | 25 | — | |
| Streaming V2SPT=true, Backbone=CLIP2024.12 | — | — | 24.1 | |
| Streaming V2SPre-trained=true2026.03 | — | — | 24.1 |