Temporal Grounding on Charades-STA (test)
60.8Recall@1 (IoU=0.5)UnLoc-L
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| UnLoc-LVision Enc.=CLIP2023.08 | 60.8 | 38.4 | 88.2 | 61.1 | — | — | — | |
| LGIVision Enc.=I3D2023.08 | 59.5 | 35.5 | — | — | — | — | — | |
| UnLoc-BVision Enc.=CLIP2023.08 | 58.1 | 35.4 | 87.4 | 59.1 | — | — | — | |
| M-DETRVision Enc.=CLIP2023.08 | 55.7 | 34.2 | — | — | — | — | — | |
| PFUSupervision setting=Glance, Features=VGG, reproducibility=Official code reproduction2023.08 | 54.66 | 28.34 | — | — | — | — | — | |
| ETCCategory=Gaussian Proposal (Closed), Utilizes additional annotations generated by a multi-modal large language model=true2026.02 | 53.39 | 25.84 | — | — | — | — | — | |
| OmniDCategory=Gaussian Proposal (Closed)2026.02 | 52.31 | 24.35 | — | — | — | — | — | |
| DSRNCategory=Gaussian Proposal (Closed)2026.02 | 52.18 | 24.6 | — | — | — | — | — | |
| PPSCategory=Gaussian Proposal (Open)2026.02 | 51.49 | 26.16 | 86.23 | 53.01 | — | — | — | |
| DISCategory=Gaussian Proposal (Closed)2026.02 | 51.39 | 25.9 | — | — | — | — | — | |
| DM2Category=Gaussian Proposal (Closed)2026.02 | 51.39 | 23.72 | — | — | — | — | — | |
| SCANetCategory=Gaussian Proposal (Closed)2026.02 | 50.85 | 24.07 | 86.32 | 53.28 | — | — | — | |
| CCRCategory=Gaussian Proposal (Closed)2026.02 | 50.79 | 23.75 | 84.48 | 52.44 | — | — | — | |
| VGCICategory=Gaussian Proposal (Closed)2026.02 | 50.71 | 25.84 | 87.43 | 52.41 | — | — | — | |
| CPICategory=Gaussian Proposal (Closed)2026.02 | 50.47 | 24.38 | 85.66 | 52.98 | — | — | — | |
| IVG-DCLVision Enc.=C3D2023.08 | 50.2 | 32.9 | — | — | — | — | — | |
| GBOPPSCategory=GBO (Ours)2026.02 | 50.01 | 26.25 | 87.49 | 53.45 | — | — | — | |
| UMTVision Enc.=VGG2023.08 | 49.4 | 26.2 | 89.4 | 55 | — | — | — | |
| UMTfeatures=video + optical flow2022.03 | 49.35 | 26.16 | 89.41 | 54.95 | — | — | — | |
| GBOCPLCategory=GBO (Ours)2026.02 | 49.27 | 22.64 | 85.78 | 52.06 | — | — | — | |
| CPLCategory=Gaussian Proposal (Open)2026.02 | 49.24 | 22.39 | 84.71 | 52.37 | — | — | — | |
| UMTfeatures=video + audio2022.03 | 48.31 | 29.25 | 88.79 | 56.08 | — | — | — | |
| MMNBackbone=VGG2021.09 | 47.31 | 27.28 | 83.74 | 58.41 | — | — | — | |
| MMNSupervision setting=Full, Features=VGG2023.08 | 47.31 | 27.28 | 83.74 | 58.41 | — | — | — | |
| VSLNetVision Enc.=I3D2023.08 | 47.3 | 30.2 | — | — | — | — | — | |
| CPNBackbone=VGG2021.09 | 46.08 | 25.06 | — | — | — | — | — | |
| SimVTP2022.12 | 44.7 | 26.3 | 83.7 | 55.1 | — | — | — | |
| CBLNBackbone=VGG2021.09 | 43.67 | 24.44 | 88.39 | 56.49 | — | — | — | |
| SSCSBackbone=VGG2021.09 | 43.15 | 25.54 | 84.26 | 54.17 | — | — | — | |
| SSCSSupervision setting=Full, Features=VGG2023.08 | 43.15 | 25.54 | 84.26 | 54.17 | — | — | — | |
| DRNBackbone=VGG2021.09 | 42.9 | 23.68 | 87.8 | 54.87 | — | — | — | |
| FVMRBackbone=VGG2021.09 | 42.36 | 24.14 | 83.97 | 50.15 | — | — | — | |
| FVMR2022.03 | 42.36 | 24.14 | 83.97 | 50.15 | — | — | — | |
| D3GSupervision setting=Glance, Features=VGG2023.08 | 41.64 | 19.6 | 79.25 | 49.3 | — | — | — | |
| MAN2022.03 | 41.24 | 20.54 | 83.21 | 51.85 | — | — | — | |
| MANBackbone=VGG2021.09 | 41.21 | 20.54 | 83.21 | 51.85 | — | — | — | |
| MANSupervision setting=Full, Features=VGG2023.08 | 41.21 | 20.54 | 83.21 | 51.85 | — | — | — | |
| LocVTP2022.12 | 41.2 | 24.8 | 81.3 | 53.5 | — | — | — | |
| 2D-TAN2022.03 | 40.94 | 22.85 | 83.84 | 50.35 | — | — | — | |
| 2D-TANBackbone=VGG2021.09 | 39.7 | 23.31 | 80.32 | 51.26 | — | — | — | |
| 2D-TANSupervision setting=Full, Features=VGG2023.08 | 39.7 | 23.31 | 80.32 | 51.26 | — | — | — | |
| 2D TANVision Enc.=VGG2023.08 | 39.7 | 23.3 | 80.3 | 51.3 | — | — | — | |
| PS-VTGSupervision setting=Glance, Features=VGG, reproducibility=Official code reproduction2023.08 | 39.22 | 20.17 | — | — | — | — | — | |
| OA-Trans2022.12 | 39.2 | 22.6 | 78.5 | 50.8 | — | — | — | |
| LCNetSupervision setting=Weak, Features=VGG2023.08 | 39.19 | 18.87 | 80.56 | 45.24 | — | — | — | |
| Frozen2022.12 | 38.8 | 22.9 | 77.6 | 50.3 | — | — | — | |
| UniVL2022.12 | 38.2 | 22.7 | 77.2 | 51.4 | — | — | — | |
| VCACategory=Non-Gaussian Proposal2026.02 | 38.13 | 19.57 | 78.75 | 37.75 | — | — | — | |
| December2022.12 | 37.2 | 21.6 | 78.3 | 50.6 | — | — | — | |
| MIL-NCE2022.12 | 37 | 21.2 | 74.3 | 50.4 | — | — | — | |
| VIGASupervision setting=Glance, Features=VGG, reproducibility=Official code reproduction for R@52023.08 | 36.56 | 16.1 | 48.9 | 25.86 | — | — | — | |
| GBOCNMCategory=GBO (Ours)2026.02 | 36.38 | 16.69 | — | — | — | — | — | |
| CNMSupervision setting=Weak, Features=VGG2023.08 | 35.43 | 15.45 | — | — | — | — | — | |
| CNMCategory=Gaussian Proposal (Open)2026.02 | 35.18 | 14.95 | — | — | — | — | — | |
| CRMSupervision setting=Weak, Features=VGG2023.08 | 34.76 | 16.37 | — | — | — | — | — | |
| CCLCategory=Non-Gaussian Proposal2026.02 | 33.21 | 15.68 | 73.5 | 41.87 | — | — | — | |
| VideoBERT2022.12 | 32.7 | 19.5 | 68.1 | 46.2 | — | — | — | |
| CPLSupervision setting=Weak, Features=I3D2023.08 | 32.27 | 14.22 | 78.34 | 43.45 | — | — | — | |
| MARNCategory=Non-Gaussian Proposal2026.02 | 31.94 | 14.81 | 70 | 37.4 | — | — | — | |
| CWSTGCategory=Non-Gaussian Proposal2026.02 | 31.02 | 16.53 | 77.53 | 41.91 | — | — | — | |
| SAPBackbone=VGG2021.09 | 27.42 | 13.36 | 66.37 | 38.15 | — | — | — | |
| SAP2022.03 | 27.42 | 13.36 | 66.37 | 38.15 | — | — | — | |
| CTFCategory=Non-Gaussian Proposal2026.02 | 27.3 | 12.9 | — | — | — | — | — | |
| SM-RL2022.03 | 24.36 | 11.17 | 61.25 | 32.08 | — | — | — | |
| CTRLVision Enc.=C3D2023.08 | 23.6 | 8.9 | 58.9 | 29.5 | — | — | — | |
| SCNCategory=Non-Gaussian Proposal2026.02 | 23.58 | 9.97 | 71.8 | 38.87 | — | — | — | |
| MCNBackbone=VGG2021.09 | 17.46 | 8.01 | 48.22 | 26.73 | — | — | — | |
| RandomCategory=Non-Gaussian Proposal2026.02 | 8.61 | 3.39 | 37.57 | 14.98 | — | — | — | |
| Conan-7BSetting=tool-augmented setting (<think>→<tool_call>→<answer>)2026.05 | — | — | — | — | — | — | 25.4 | |
| E.T. ChatCategory=Open-source ~ 7B Models2025.05 | — | — | — | — | — | — | 45.6 | |
| GPT-4oCategory=API-based Models2025.05 | — | — | — | — | — | — | 25.1 | |
| HawkEye2026.01 | — | — | — | — | 31.4 | 14.5 | — | |
| LongVT-RFT-7BSetting=tool-augmented setting (<think>→<tool_call>→<answer>)2026.05 | — | — | — | — | — | — | 23.4 | |
| MMDuet2026.01 | — | — | — | — | 42.4 | 18 | — | |
| MUSEG-3BCategory=Open-source ~ 3B Models2025.05 | — | — | — | — | — | — | 53.7 | |
| MUSEG-7BCategory=Open-source ~ 7B Models2025.05 | — | — | — | — | — | — | 59.7 | |
| ParaVT-8BSetting=tool-augmented setting (<think>→<tool_call>→<answer>)2026.05 | — | — | — | — | — | — | 50.1 | |
| Qwen2.5-VL-3BCategory=Open-source ~ 3B Models2025.05 | — | — | — | — | — | — | 41.4 | |
| Qwen2.5-VL-7BCategory=Open-source ~ 7B Models2025.05 | — | — | — | — | — | — | 50.2 | |
| Qwen2.5-VL-7BSetting=direct-answer setting (native single-pass prompt)2026.05 | — | — | — | — | — | — | 31.6 | |
| Qwen2.5-VL-7B + vanilla GRPOCategory=Open-source ~ 7B Models, Training=vanilla GRPO2025.05 | — | — | — | — | — | — | 53.9 | |
| Qwen2.5-VL-7B + vanilla SFTCategory=Open-source ~ 7B Models, Training=vanilla SFT2025.05 | — | — | — | — | — | — | 28.1 | |
| Qwen3-VL-8BSetting=tool-augmented setting (<think>→<tool_call>→<answer>)2026.05 | — | — | — | — | — | — | 49.3 | |
| ReWatch-R1-7BSetting=reasoning-enhanced setting (<think>→<answer>)2026.05 | — | — | — | — | — | — | 20.2 | |
| ROMA2026.01 | — | — | — | — | 44.3 | 19.9 | — | |
| ROMATraining=Mixed Training2026.01 | — | — | — | — | 28.2 | 10.1 | — | |
| ROMAK=12026.01 | — | — | — | — | 32.4 | 13.1 | — | |
| ROMAwpos=22026.01 | — | — | — | — | 42.2 | 18.4 | — | |
| ROMAwpos=42026.01 | — | — | — | — | 38 | 16.4 | — | |
| SAGE-7BSetting=tool-augmented setting (<think>→<tool_call>→<answer>)2026.05 | — | — | — | — | — | — | 28.9 | |
| TEMPURACategory=Open-source ~ 3B Models2025.05 | — | — | — | — | — | — | 44.5 | |
| Time-R1-7BSetting=reasoning-enhanced setting (<think>→<answer>)2026.05 | — | — | — | — | — | — | 34.7 | |
| TimeChat2026.01 | — | — | — | — | 32.2 | 13.4 | — | |
| TimeZeroCategory=Open-source ~ 7B Models2025.05 | — | — | — | — | — | — | 59.2 | |
| TRACE-7BCategory=Open-source ~ 7B Models2025.05 | — | — | — | — | — | — | 29.9 | |
| Video-R1Category=Open-source ~ 7B Models2025.05 | — | — | — | — | — | — | 11.3 | |
| Video-R1-7BSetting=reasoning-enhanced setting (<think>→<answer>)2026.05 | — | — | — | — | — | — | 25.4 | |
| Video-Thinker-7BSetting=reasoning-enhanced setting (<think>→<answer>)2026.05 | — | — | — | — | — | — | 29 | |
| VideoChat-R1Category=Open-source ~ 7B Models2025.05 | — | — | — | — | — | — | 59.4 | |
| VideoChat-R1-7BSetting=reasoning-enhanced setting (<think>→<answer>)2026.05 | — | — | — | — | — | — | 31.5 |