Video Moment Retrieval on Charades STA (test)
72.26Recall@1 (IoU=0.5)SMART
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| SMARTBackbone=CLIP+LLM2025.11 | 72.26 | 52.17 | 61.09 | 69.47 | 40.43 | — | — | — | — | |
| LLaVA-MRBackbone=BLIP-22024.11 | 70.65 | 49.58 | 59.78 | 69.96 | 39.66 | — | — | — | — | |
| LLaVA-MRBackbone=CLIP+LLM2025.11 | 70.65 | 49.58 | 59.78 | 69.96 | 39.66 | — | — | — | — | |
| FlashVTGBackbone=SF+CLIP2025.11 | 70.32 | 49.87 | — | — | — | — | — | — | — | |
| InternVideo2-6B2024.11 | 70.03 | 48.95 | — | — | — | — | — | — | — | |
| InternVideo2-6B2025.11 | 70.03 | 48.95 | — | — | — | — | — | — | — | |
| Mr. BLIPBackbone=BLIP-22024.11 | 69.31 | 49.29 | 58.63 | — | — | — | — | — | — | |
| Mr.BLIPBackbone=BLIP-22025.11 | 69.31 | 49.29 | 58.63 | — | — | — | — | — | — | |
| EaTRBackbone=I3D2024.11 | 68.47 | 44.92 | — | — | — | — | — | — | — | |
| EaTRBackbone=I3D2025.11 | 68.47 | 44.92 | — | — | — | — | — | — | — | |
| InternVideo2-1B2024.11 | 68.36 | 45.03 | — | — | — | — | — | — | — | |
| InternVideo2-1B2025.11 | 68.36 | 45.03 | — | — | — | — | — | — | — | |
| UniMD+Sync2024.11 | 63.98 | 44.46 | — | — | — | — | — | — | — | |
| UniMD+Sync2025.11 | 63.98 | 44.46 | — | — | — | — | — | — | — | |
| LD-DETR2025.01 | 62.58 | 41.56 | 53.44 | — | — | 73.92 | — | — | — | |
| VideoLights-B-ptBackbone=SF+CLIP+BLIP2025.11 | 61.96 | 41.05 | 52.94 | — | — | — | — | — | — | |
| UnLoc-LBackbone=CLIP*2024.11 | 60.8 | 38.4 | — | — | — | — | — | — | — | |
| UnLoc-LBackbone=CLIP*2025.11 | 60.8 | 38.4 | — | — | — | — | — | — | — | |
| BAM-DETR2025.01 | 59.95 | 39.38 | 52.33 | — | — | 72.93 | — | — | — | |
| R2-Tuning2025.01 | 59.78 | 37.02 | 50.86 | — | — | 70.91 | — | — | — | |
| R2-TuningBackbone=CLIP2025.11 | 59.78 | 37.02 | — | — | — | — | — | — | — | |
| BM-DETRVideo Feat=SF+C2023.06 | 59.48 | 38.33 | — | — | — | — | — | — | — | |
| UVCOMBackbone=SF+CLIP2025.11 | 59.25 | 36.64 | — | — | — | — | — | — | — | |
| CG-DETRBackbone=SF+CLIP2024.11 | 58.44 | 36.34 | 50.13 | — | — | — | — | — | — | |
| CG-DETR2025.01 | 58.44 | 36.34 | 50.13 | — | — | 70.43 | — | — | — | |
| CG-DETRBackbone=SF+CLIP2025.11 | 58.44 | 36.34 | 50.13 | — | — | — | — | — | — | |
| CDNet2025.01 | 58.09 | 36.53 | — | — | — | 71.25 | — | — | — | |
| UniVTGVideo Feat=SF+C2023.06 | 58.01 | 35.65 | — | — | — | — | — | — | — | |
| UniVTGBackbone=SF+CLIP2024.11 | 58.01 | 35.65 | 50.1 | — | — | — | — | — | — | |
| UniVTG2025.01 | 58.01 | 35.65 | 50.1 | — | — | 70.81 | — | — | — | |
| UniVTGBackbone=SF+CLIP2025.11 | 58.01 | 35.65 | 50.1 | — | — | — | — | — | — | |
| MS-DETR2025.01 | 57.72 | 37.4 | 50.12 | — | — | 68.68 | — | — | — | |
| QD-DETRVideo Feat=SF+C2023.06 | 57.31 | 32.55 | — | — | — | — | — | — | — | |
| QD-DETRBackbone=SF+CLIP2024.11 | 57.31 | 32.55 | — | — | — | — | — | — | — | |
| QD-DETRBackbone=SF+CLIP2025.11 | 57.31 | 32.55 | — | — | — | — | — | — | — | |
| UniVTG+2025.01 | 57.18 | 36.05 | — | — | — | 68.06 | — | — | — | |
| MABANMode=FS2022.09 | 56.29 | 32.26 | — | — | — | — | — | — | — | |
| LMRBackbone=SF+CLIP2025.11 | 55.91 | 35.19 | — | — | — | — | — | — | — | |
| MomentDiffVideo Feat=SF+C2023.06 | 55.57 | 32.42 | — | — | — | — | — | — | — | |
| MMCDAMode=CD, Transfer=A→C2022.09 | 54.8 | 35.77 | — | — | — | 71.58 | 98.36 | 88.9 | 61.02 | |
| BM-DETRVideo Feat=C3D2023.06 | 54.42 | 33.84 | — | — | — | — | — | — | — | |
| BM-DETRVideo Feat=VGG2023.06 | 54.22 | 35.54 | — | — | — | — | — | — | — | |
| VSLNet2025.01 | 54.19 | 35.22 | 50.02 | — | — | 70.46 | — | — | — | |
| MomentDiffVideo Feat=C3D2023.06 | 53.79 | 30.18 | — | — | — | — | — | — | — | |
| MDETRVideo Feat=SF+C2023.06 | 53.63 | 31.37 | — | — | — | — | — | — | — | |
| Moment-DETR2024.11 | 53.63 | 31.37 | — | — | — | — | — | — | — | |
| Moment-DETR2025.11 | 53.63 | 31.37 | — | — | — | — | — | — | — | |
| QD-DETRVideo Feat=VGG2023.06 | 52.77 | 31.13 | — | — | — | — | — | — | — | |
| HUAL2025.01 | 52.69 | 28.9 | 48.11 | — | — | 70.4 | — | — | — | |
| MomentDiffVideo Feat=VGG2023.06 | 51.94 | 28.25 | — | — | — | — | — | — | — | |
| BPNet2025.01 | 50.75 | 31.64 | 46.34 | — | — | 65.48 | — | — | — | |
| IVG-DCLVideo Feat=C3D2023.06 | 50.24 | 32.88 | — | — | — | — | — | — | — | |
| DCL2025.01 | 50.24 | 32.88 | 48.02 | — | — | 67.63 | — | — | — | |
| CBLNVideo Feat=C3D2023.06 | 47.94 | 28.22 | — | — | — | — | — | — | — | |
| G2LVideo Feat=VGG2023.06 | 47.91 | 28.42 | — | — | — | — | — | — | — | |
| VSLNetVideo Feat=C3D2023.06 | 47.31 | 30.19 | — | — | — | — | — | — | — | |
| MMNVideo Feat=VGG2023.06 | 47.31 | 27.28 | — | — | — | — | — | — | — | |
| VSLNetMode=FS2022.09 | 47.31 | 30.19 | — | — | — | 64.3 | — | — | — | |
| DRNVideo Feat=C3D2023.06 | 45.4 | 26.4 | — | — | — | — | — | — | — | |
| CBLNVideo Feat=VGG2023.06 | 43.67 | 24.44 | — | — | — | — | — | — | — | |
| SSCSVideo Feat=VGG2023.06 | 43.15 | 25.54 | — | — | — | — | — | — | — | |
| DRNVideo Feat=VGG2023.06 | 42.9 | 23.68 | — | — | — | — | — | — | — | |
| FVMRVideo Feat=VGG2023.06 | 42.36 | 24.14 | — | — | — | — | — | — | — | |
| MCMN2025.01 | 41.38 | — | — | — | — | 62.69 | — | — | — | |
| 2D-TANVideo Feat=VGG2023.06 | 41.34 | 23.91 | — | — | — | — | — | — | — | |
| 2D-TANMode=FS2022.09 | 39.81 | 23.25 | — | — | — | — | — | 79.33 | 52.15 | |
| 2D-TANVideo Feat=C3D2023.06 | 39.7 | 27.1 | — | — | — | — | — | — | — | |
| RaNet2025.01 | 39.65 | — | — | — | — | 60.4 | — | — | — | |
| CPNet2025.01 | 38.74 | — | — | — | — | 60.27 | — | — | — | |
| UnLoc2025.01 | 38.4 | — | — | — | — | 60.8 | — | — | — | |
| BM-DETR2025.01 | 38.33 | — | — | — | — | 59.48 | — | — | — | |
| CBLN2025.01 | 38.22 | — | — | — | — | 61.13 | — | — | — | |
| MESM2025.01 | 38.04 | — | — | — | — | 61.24 | — | — | — | |
| UVCOM2025.01 | 36.64 | — | — | — | — | 59.25 | — | — | — | |
| FVMR2025.01 | 35.48 | — | — | — | — | 59.46 | — | — | — | |
| LMR2025.01 | 35.19 | — | — | — | — | 55.91 | — | — | — | |
| MMCDAMode=CD, Transfer=T→C2022.09 | 35.17 | 17.28 | — | — | — | 48.69 | 85.4 | 69.93 | 39.74 | |
| LoGANMode=WS2022.09 | 34.68 | 14.54 | — | — | — | 51.67 | 92.74 | 74.3 | 39.11 | |
| SCDN2025.01 | 34.26 | — | — | — | — | 54.92 | — | — | — | |
| QD-DETRaudio modality=true2025.01 | 34.17 | — | — | — | — | 55.51 | — | — | — | |
| TaskWeave2025.01 | 33.66 | — | — | — | — | 56.51 | — | — | — | |
| TR-DETR2025.01 | 33.52 | — | — | — | — | 57.61 | — | — | — | |
| LLaViLo2025.01 | 33.43 | — | — | — | — | 55.72 | — | — | — | |
| MomentDiff2025.01 | 32.42 | — | — | — | — | 55.57 | — | — | — | |
| RTBPNMode=WS2022.09 | 32.36 | 13.24 | — | — | — | 60.04 | 97.48 | 71.85 | 41.18 | |
| VLANetMode=WS2022.09 | 31.83 | 14.17 | — | — | — | 45.24 | 95.7 | 82.85 | 33.09 | |
| Moment-DETR2025.01 | 31.37 | — | — | — | — | 53.63 | — | — | — | |
| SCDM2025.01 | 31.37 | — | — | — | — | 54.44 | — | — | — | |
| SFABD2025.01 | 30.51 | — | — | — | — | — | — | — | — | |
| ACL-KMode=FS2022.09 | 30.48 | 12.2 | — | — | — | — | — | 64.84 | 35.13 | |
| VCSJT+2025.01 | 30.22 | — | — | — | — | 51.21 | — | — | — | |
| UMTaudio modality=true2025.01 | 29.25 | — | — | — | — | 48.31 | — | — | — | |
| SAPMode=FS2022.09 | 27.42 | 13.36 | — | — | — | — | — | 66.37 | 38.15 | |
| MMN2025.01 | 27.28 | — | — | — | — | 47.31 | — | — | — | |
| DRN2025.01 | 26.4 | — | — | — | — | 45.4 | — | — | — | |
| SimVTP2025.01 | 26.3 | — | — | — | — | 44.7 | — | — | — | |
| MIM+2025.01 | 25.89 | — | — | — | — | 43.92 | — | — | — | |
| LSJT+2025.01 | 25.13 | — | — | — | — | 44.62 | — | — | — | |
| FMAN2025.01 | 25.05 | — | 38.23 | — | — | 51.4 | — | — | — | |
| MMCDAMode=FS, Transfer=C→C2022.09 | 24.53 | 10.04 | — | — | — | 39.42 | 75.21 | 53.52 | 30.87 |