Video Moment Retrieval on TACoS (test)
44.31Recall@1 (0.5 Threshold)LD-DETR
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| LD-DETR2025.01 | 44.31 | — | 57.61 | — | 40.3 | 26.24 | — | — | — | |
| CVA2026.03 | 43.21 | — | 58.8 | — | 41.07 | 27.73 | — | — | — | |
| OursType=OS2026.05 | 42.72 | — | 55.44 | — | — | — | — | 73.48 | 64.48 | |
| FlashVTGVideo encoder=CLIP ViT-B/32 and SlowFast R-50, Text encoder=CLIP text enc.2026.04 | 41.76 | — | 53.71 | — | — | 24.74 | — | — | — | |
| FlashVTG + ClipTBPVideo encoder=CLIP ViT-B/32 and SlowFast R-50, Text encoder=CLIP text enc.2026.04 | 41.61 | — | 53.64 | — | — | 27.49 | — | — | — | |
| BAM-DETR2025.01 | 41.54 | — | 56.69 | — | 39.31 | 26.77 | — | — | — | |
| BAM-DETR2026.03 | 41.45 | — | 56.69 | — | 39.31 | 26.77 | — | — | — | |
| VIDEOLIGHTSVisual features=CLIP + SlowFast2024.12 | 40.61 | — | 54.29 | — | 37.18 | 22.67 | — | — | — | |
| CDTR2026.03 | 40.26 | — | 53.41 | — | 37.28 | 23.43 | — | — | — | |
| CG-DETR2025.01 | 39.61 | — | 52.23 | — | 36.48 | 22.23 | — | — | — | |
| CG-DETRVideo encoder=CLIP ViT-B/32 and SlowFast R-50, Text encoder=CLIP text enc.2026.04 | 39.61 | — | 52.23 | — | — | 22.23 | — | — | — | |
| MESM2025.01 | 39.52 | — | 52.69 | — | 36.94 | — | — | — | — | |
| R2-Tuning2025.01 | 38.72 | — | 49.71 | — | 35.92 | 25.12 | — | — | — | |
| R2-TuningVideo encoder=CLIP ViT-B/32 and SlowFast R-50, Text encoder=CLIP text enc.2026.04 | 38.72 | — | 49.71 | — | — | 25.12 | — | — | — | |
| [62]2025.01 | 37.99 | — | 49.77 | — | — | — | — | — | — | |
| MATN2025.01 | 37.57 | — | 48.79 | — | — | — | — | — | — | |
| MS-DETR2025.01 | 37.36 | — | 47.66 | — | 35.09 | 25.81 | — | — | — | |
| MCMN2025.01 | 36.78 | — | 50.24 | — | — | — | — | — | — | |
| UVCOM2025.01 | 36.39 | — | — | — | — | 23.32 | — | — | — | |
| UVCOM2026.03 | 36.39 | — | — | — | — | 23.32 | — | — | — | |
| SFEN2025.01 | 36.1 | — | 47.3 | — | — | — | — | — | — | |
| BM-DETR2025.01 | 35.42 | — | 50.31 | — | — | — | — | — | — | |
| CDNet2025.01 | 35.35 | — | 54.11 | — | 33.78 | 20.34 | — | — | — | |
| UniVTGFeat.=SF+C, S2@20=true2023.08 | 34.97 | — | 51.44 | — | — | — | — | — | — | |
| UniVTGVisual features=CLIP + SlowFast2024.12 | 34.97 | — | 51.44 | — | 33.6 | 17.35 | — | — | — | |
| UniVTG2025.01 | 34.97 | — | 51.44 | — | 33.6 | 17.35 | — | — | — | |
| UniVTG2026.03 | 34.97 | — | 51.44 | — | 33.6 | 17.35 | — | — | — | |
| UniVTGVideo encoder=CLIP ViT-B/32 and SlowFast R-50, Text encoder=CLIP text enc.2026.04 | 34.97 | — | 51.44 | — | — | 17.35 | — | — | — | |
| GVL2025.01 | 34.57 | — | 45.92 | — | 32.48 | — | — | — | — | |
| VLG-NetFeat.=C3D, S2@20=true2023.08 | 34.19 | 57.21 | 45.46 | — | — | — | — | — | — | |
| VLG-Net2025.01 | 34.19 | — | 45.46 | — | — | — | — | — | — | |
| MomentDiffFeatures=C3D2023.07 | 33.68 | 56.81 | 44.78 | — | — | — | — | — | — | |
| MomentDiff2025.01 | 33.68 | — | 44.78 | — | — | — | — | — | — | |
| MomentDiff2026.03 | 33.68 | — | 44.78 | — | — | — | — | — | — | |
| MomentDiffType=FS2026.05 | 33.68 | — | 44.78 | — | — | — | — | — | — | |
| RaNetFeatures=C3D2023.07 | 33.54 | — | 43.34 | — | — | — | — | — | — | |
| RaNet2025.01 | 33.54 | — | 43.34 | — | — | — | — | — | — | |
| RaNetType=FS2026.05 | 33.54 | — | 43.34 | — | — | — | — | 67.33 | 55.09 | |
| SMRNFeat.=C3D, S2@20=true2023.08 | 32.07 | 50.44 | 42.49 | — | — | — | — | — | — | |
| MMCDA(A→T)Mode=CD, Setting=A→T2022.09 | 31.69 | 55.38 | 43.07 | — | — | — | 77.54 | 63.81 | 51.82 | |
| G2LType=FS2026.05 | 30.95 | — | 42.74 | — | — | — | — | 65.83 | 49.86 | |
| LGNFeat.=C3D, S2@20=true2023.08 | 30.57 | 52.46 | 41.71 | — | — | — | — | — | — | |
| SimVTP2025.01 | 30.3 | — | 43.1 | — | — | — | — | — | — | |
| CLEARMode=FS2022.09 | 30.27 | — | 42.18 | — | — | — | — | 63.61 | 51.76 | |
| FVMRFeatures=C3D2023.07 | 29.12 | 53.12 | 41.48 | — | — | — | — | — | — | |
| FVMR2025.01 | 29.12 | — | 41.48 | — | — | — | — | — | — | |
| FVMRType=FS2026.05 | 29.12 | — | 41.48 | — | — | — | — | 64.53 | 50 | |
| DCLFeatures=C3D2023.07 | 29.07 | 49.36 | 38.84 | — | — | — | — | — | — | |
| DCL2025.01 | 29.07 | — | 38.84 | — | 28.26 | 19.05 | — | — | — | |
| FIANFeat.=C3D, S2@20=true2023.08 | 28.58 | 39.55 | 33.87 | — | — | — | — | — | — | |
| CPNet2025.01 | 28.29 | — | 42.61 | — | 28.69 | — | — | — | — | |
| 2D-TANFeat.=SF+C, S2@20=true2023.08 | 27.99 | — | 40.01 | — | — | — | — | — | — | |
| 2D TANVisual features=CLIP + SlowFast2024.12 | 27.99 | — | 40.01 | — | 27.22 | 12.92 | — | — | — | |
| 2D-TAN2026.03 | 27.99 | — | 40.01 | — | 27.22 | 12.92 | — | — | — | |
| CBLNFeatures=C3D2023.07 | 27.65 | 49.16 | 38.98 | — | — | — | — | — | — | |
| CBLN2025.01 | 27.65 | — | 38.98 | — | — | — | — | — | — | |
| CSMGANFeat.=C3D, S2@20=true2023.08 | 27.09 | 42.74 | 33.9 | — | — | — | — | — | — | |
| CSMGANMode=FS2022.09 | 27.09 | 42.74 | 33.9 | — | — | — | 68.97 | 53.98 | 41.22 | |
| MMCDA(C→T)Mode=CD, Setting=C→T2022.09 | 26.88 | 47.97 | 35.41 | — | — | — | 69.53 | 58.1 | 42.62 | |
| CrossGraphAlign2025.01 | 26.4 | — | 39.8 | — | — | — | — | — | — | |
| MMNFeatures=C3D, re-implemented=true2023.07 | 26.17 | 51.39 | 39.24 | — | — | — | — | — | — | |
| MMN2025.01 | 26.17 | — | 39.24 | — | — | — | — | — | — | |
| MMNType=FS2026.05 | 26.17 | — | 39.24 | — | — | — | — | 62.03 | 47.39 | |
| 2D-TANFeat.=C3D, S2@20=true2023.08 | 25.32 | 47.59 | 37.29 | — | — | — | — | — | — | |
| 2D-TAN2025.01 | 25.32 | — | 37.29 | — | — | — | — | — | — | |
| 2D-TANMode=FS2022.09 | 25.32 | 47.59 | 37.29 | — | — | — | 70.31 | 57.81 | 45.04 | |
| 2D-TANType=FS2026.05 | 25.32 | — | 37.29 | — | — | — | — | 57.81 | 45.04 | |
| CBPMode=FS2022.09 | 24.79 | — | 27.31 | — | — | — | — | 43.64 | 37.4 | |
| M-DETRFeat.=SF+C, S2@20=true2023.08 | 24.67 | — | 37.97 | — | — | — | — | — | — | |
| Moment-DETRVisual features=CLIP + SlowFast2024.12 | 24.67 | — | 37.97 | — | 25.49 | 11.97 | — | — | — | |
| M-DETR2026.03 | 24.67 | — | 37.97 | — | 25.49 | 11.97 | — | — | — | |
| Moment-DETRVideo encoder=CLIP ViT-B/32 and SlowFast R-50, Text encoder=CLIP text enc.2026.04 | 24.67 | — | 37.97 | — | — | 11.97 | — | — | — | |
| VSLNet2025.01 | 24.27 | — | 29.61 | — | 24.11 | 20.03 | — | — | — | |
| VSLNetMode=FS2022.09 | 24.27 | — | 29.61 | — | — | — | — | — | — | |
| VSLNetFeat.=SF+C, S2@20=true2023.08 | 23.54 | — | 35.54 | — | — | — | — | — | — | |
| VSLNetVisual features=CLIP + SlowFast2024.12 | 23.54 | — | 35.54 | — | 24.99 | 13.15 | — | — | — | |
| VSLNet2026.03 | 23.54 | — | 35.54 | — | 24.99 | 13.15 | — | — | — | |
| SCDN2025.01 | 23.27 | — | 27.64 | — | — | — | — | — | — | |
| DRNFeatures=C3D2023.07 | 23.17 | — | — | — | — | — | — | — | — | |
| DRN2025.01 | 23.17 | — | — | — | — | — | — | — | — | |
| DRNType=FS2026.05 | 23.17 | — | — | — | — | — | — | — | 33.36 | |
| SCDMFeatures=C3D2023.07 | 21.17 | — | 26.11 | — | — | — | — | — | — | |
| SCDM2025.01 | 21.17 | — | 26.11 | — | — | — | — | — | — | |
| SCDMMode=FS2022.09 | 21.17 | — | 26.11 | — | — | — | — | 40.16 | 32.18 | |
| SCDMType=FS2026.05 | 21.17 | — | 26.11 | — | — | — | — | 40.16 | 32.18 | |
| BPNet2025.01 | 20.96 | — | 25.96 | — | 19.53 | 14.08 | — | — | — | |
| MomentDETRFeatures=C3D, re-implemented=true2023.07 | 20.55 | 41.16 | 32.21 | — | — | — | — | — | — | |
| SM-RL2025.01 | 20.25 | — | — | — | — | 15.95 | — | — | — | |
| ACL-KFeat.=C3D, S2@20=true2023.08 | 20.01 | 31.64 | 24.17 | — | — | — | — | — | — | |
| CMINFeat.=C3D, S2@20=true2023.08 | 19.57 | 36.68 | 27.33 | — | — | — | — | — | — | |
| TripNetFeat.=C3D, S2@20=true2023.08 | 19.17 | — | 23.95 | — | — | — | — | — | — | |
| TGNFeat.=C3D, S2@20=true2023.08 | 18.9 | 41.87 | 21.77 | — | — | — | — | — | — | |
| TGN2025.01 | 18.9 | — | 21.77 | — | — | — | — | — | — | |
| TGNMode=FS2022.09 | 18.9 | 41.87 | 21.77 | — | — | — | 53.4 | 39.06 | 31.02 | |
| SAPFeat.=C3D, S2@20=true2023.08 | 18.24 | 31.15 | — | — | — | — | — | — | — | |
| SAP2025.01 | 18.24 | — | — | — | — | — | — | — | — | |
| CMINMode=FS2022.09 | 18.05 | 32.48 | 24.64 | — | — | — | 62.13 | 38.46 | 27.02 | |
| CMINType=FS2026.05 | 18.05 | — | 24.64 | — | — | — | — | 38.46 | 27.02 | |
| SM-RLFeat.=C3D, S2@20=true2023.08 | 15.95 | 26.51 | 20.25 | — | — | — | — | — | — | |
| MMCDA(T→T)Mode=FS, Setting=T→T2022.09 | 14.95 | 36.58 | 22.63 | — | — | — | 54.01 | 45.77 | 34.78 |