Video Quality Assessment on KoNViD-1k
0.922SROCCKSVQE
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| KSVQE2024.02 | 0.922 | — | — | 0.921 | — | — | |
| Soft Ranking (Stage 1)Training Stage=Stage 1, Evaluation Protocol=10-fold cross-validation2025.05 | 0.911 | — | — | 0.908 | — | — | |
| KVQPre-training Dataset=LSVQ [56]2025.03 | 0.909 | — | — | 0.915 | — | — | |
| DOVERprotocol=supervised2026.04 | 0.909 | — | — | 0.906 | — | — | |
| KVQprotocol=supervised2026.04 | 0.909 | — | — | 0.915 | — | — | |
| Doveraesthetic branch=false2024.02 | 0.908 | — | — | 0.91 | — | — | |
| DOVEREvaluation Protocol=10-fold cross-validation2025.05 | 0.908 | — | — | 0.91 | — | — | |
| qstRectifiers=Spatial and Temporal2024.02 | 0.901 | — | — | 0.905 | — | — | |
| Soft Ranking (Base)Training Stage=Base, Evaluation Protocol=10-fold cross-validation2025.05 | 0.896 | — | — | 0.877 | — | — | |
| Q-ALIGN (1fps) + FAST-VQATraining Set=LSVQtrain, IQA Pre-training=false, fps=12023.12 | 0.895 | — | — | 0.897 | — | — | |
| FasterVQAPre-training Dataset=LSVQ [56]2025.03 | 0.895 | — | — | 0.898 | — | — | |
| LMM-PVQA (Soft Ranking Stage 3)Training data=PLVD-P1/ P2/ P3 (700k), Human Label=No, Setting=Zero-shot2025.05 | 0.894 | — | — | 0.893 | — | — | |
| FastVQA2024.02 | 0.893 | — | — | 0.887 | — | — | |
| LMM-PVQA (Soft Ranking Stage 2)Training data=PLVD-P1/ P2 (600k), Human Label=No, Setting=Zero-shot2025.05 | 0.893 | — | — | 0.892 | — | — | |
| DOVER2024.02 | 0.892 | — | — | 0.9 | — | — | |
| qtRectifiers=Temporal2024.02 | 0.892 | — | — | 0.891 | — | — | |
| FastVQA2024.02 | 0.891 | — | — | 0.892 | — | — | |
| Fast-VQAPre-training Dataset=LSVQ [56]2025.03 | 0.891 | — | — | 0.892 | — | — | |
| VQ-Jarvis2026.03 | 0.891 | — | — | 0.899 | — | — | |
| FastVQAprotocol=supervised2026.04 | 0.891 | — | — | 0.892 | — | — | |
| FAST-VQAEvaluation Protocol=10-fold cross-validation2025.05 | 0.891 | — | — | 0.892 | — | — | |
| LMM-PVQA (Soft Ranking Stage 1)Training data=PLVD-P1 (500k), Human Label=No, Setting=Zero-shot2025.05 | 0.891 | — | — | 0.888 | — | — | |
| DOVER2026.03 | 0.89 | — | — | 0.883 | — | — | |
| MinimalisticVQAEvaluation Protocol=10-fold cross-validation2025.05 | 0.889 | — | — | 0.89 | — | — | |
| LMM-PVQA (Hard Ranking)Training data=PLVD-P1 (500k), Human Label=No, Setting=Zero-shot2025.05 | 0.886 | — | — | 0.869 | — | — | |
| DOVERInference Time (Sec)=0.047, Testing Protocol=Cross-dataset Testing2024.02 | 0.884 | — | — | 0.883 | — | — | |
| DOVERTraining Set=LSVQtrain, IQA Pre-training=false, Components=aesthetic branch + FAST-VQA2023.12 | 0.883 | — | — | 0.884 | — | — | |
| DPC-VQAprotocol=few-shot2026.04 | 0.883 | — | — | 0.891 | — | — | |
| qstInference Time (Sec)=0.159, Testing Protocol=Cross-dataset Testing2024.02 | 0.878 | — | — | 0.884 | — | — | |
| Modular-VQA2026.03 | 0.878 | — | — | 0.884 | — | — | |
| StarVQA+Pre-training Dataset=ImageNet [7], LSVQ [56], ...2025.03 | 0.876 | — | — | 0.881 | — | — | |
| Q-AlignTraining data=fused [11, 17, 28, 40, 70], Human Label=Yes, Setting=Zero-shot2025.05 | 0.876 | — | — | 0.878 | — | — | |
| VQ-Insight2026.03 | 0.875 | — | — | 0.884 | — | — | |
| DOVERTraining data=LSVQ [70], Human Label=Yes, Setting=Zero-shot2025.05 | 0.874 | — | — | 0.869 | — | — | |
| qsRectifiers=Spatial2024.02 | 0.868 | — | — | 0.878 | — | — | |
| QPT V2Evaluation Protocol=Cross-dataset2024.07 | 0.866 | — | — | 0.865 | — | — | |
| Q-ALIGN (1fps)Training Set=LSVQtrain, IQA Pre-training=false, fps=12023.12 | 0.865 | — | — | 0.877 | — | — | |
| Q-AlignModel Type=Specialized VQA Model2026.02 | 0.865 | — | — | 0.877 | — | — | |
| Q-Align2026.03 | 0.865 | — | — | 0.876 | — | — | |
| Q-AlignEvaluation Protocol=Cross-dataset2024.07 | 0.865 | — | — | 0.877 | — | — | |
| Q-Alignprotocol=supervised2026.04 | 0.865 | — | — | 0.877 | — | — | |
| qbRectifiers=None2024.02 | 0.864 | — | — | 0.875 | — | — | |
| FasterVQA2022.10 | 0.863 | — | — | 0.863 | — | — | |
| MinimalisticVQA(IX)Training data=LSVQ [70], Human Label=Yes, Setting=Zero-shot2025.05 | 0.862 | — | — | 0.859 | — | — | |
| SimpleVQAEvaluation Protocol=Cross-dataset2024.07 | 0.86 | — | — | — | — | — | |
| FAST-VQA2022.10 | 0.859 | — | — | 0.855 | — | — | |
| FAST-VQATraining Set=LSVQtrain, IQA Pre-training=false2023.12 | 0.859 | — | — | 0.855 | — | — | |
| FastVQAInference Time (Sec)=0.045, Testing Protocol=Cross-dataset Testing2024.02 | 0.859 | — | — | 0.855 | — | — | |
| Fast-VQA2026.03 | 0.859 | — | — | 0.857 | — | — | |
| Minimalist-VQA2026.03 | 0.859 | — | — | 0.861 | — | — | |
| FastVQAEvaluation Protocol=Cross-dataset2024.07 | 0.859 | — | — | 0.855 | — | — | |
| FAST-VQATraining data=LSVQ [70], Human Label=Yes, Setting=Zero-shot2025.05 | 0.859 | — | — | 0.854 | — | — | |
| VQTPre-training Dataset=ImageNet [7], Kinetics-400 [18]2025.03 | 0.858 | — | — | 0.868 | — | — | |
| SimpleVQAType=VQA2022.04 | 0.856 | — | — | 0.86 | — | — | |
| SimpleVQA2024.02 | 0.856 | — | — | 0.86 | — | — | |
| SimpleVQAprotocol=supervised2026.04 | 0.856 | — | — | 0.86 | — | — | |
| SimpleVQAEvaluation Protocol=10-fold cross-validation2025.05 | 0.856 | — | — | 0.86 | — | — | |
| FasterVQA-MSAMI=true2022.10 | 0.852 | — | — | 0.854 | — | — | |
| DisCoVQATraining Set=LSVQtrain, IQA Pre-training=false2023.12 | 0.851 | — | — | 0.853 | — | — | |
| qtInference Time (Sec)=0.159, Testing Protocol=Cross-dataset Testing2024.02 | 0.851 | — | — | 0.853 | — | — | |
| CONVIQTprotocol=few-shot2026.04 | 0.851 | — | — | 0.849 | — | — | |
| DisCoVQAPre-training Dataset=None2025.03 | 0.847 | — | — | 0.847 | — | — | |
| FasterVQA-MTAMI=true2022.10 | 0.846 | — | — | 0.849 | — | — | |
| qsInference Time (Sec)=0.159, Testing Protocol=Cross-dataset Testing2024.02 | 0.845 | — | — | 0.856 | — | — | |
| CONTRIQUEprotocol=few-shot2026.04 | 0.844 | — | — | 0.842 | — | — | |
| Li22Inference Time (Sec)=27.632, Testing Protocol=Cross-dataset Testing2024.02 | 0.843 | — | — | 0.835 | — | — | |
| MinimalisticVQA(VII)Training data=LSVQ [70], Human Label=Yes, Setting=Zero-shot2025.05 | 0.843 | — | — | 0.841 | — | — | |
| BVQA-2022Attack Status=Before Attack2023.09 | 0.8427 | — | — | 0.8469 | — | — | |
| StarVQAPre-training Dataset=LSVQ [56]2025.03 | 0.842 | — | — | 0.849 | — | — | |
| FAST-VQA-M2022.10 | 0.841 | — | — | 0.832 | — | — | |
| SimpleVQATraining Set=LSVQtrain, IQA Pre-training=true2023.12 | 0.84 | — | — | 0.834 | — | — | |
| BVQATraining Set=LSVQtrain, IQA Pre-training=true2023.12 | 0.839 | — | — | 0.83 | — | — | |
| Li222024.02 | 0.839 | — | — | 0.83 | — | — | |
| BVQAEvaluation Protocol=Cross-dataset2024.07 | 0.839 | — | — | 0.83 | — | — | |
| Li et al.Type=VQA2022.04 | 0.836 | — | — | 0.834 | — | — | |
| BVQA-TCSVT-20222022.10 | 0.834 | — | — | 0.837 | — | — | |
| Li et al.Pre-training Dataset=BID [6], LIVE [9], KonIQ-10k [15], SPAQ [8]2025.03 | 0.834 | — | — | 0.836 | — | — | |
| BVQAprotocol=supervised2026.04 | 0.834 | — | — | 0.836 | — | — | |
| VQA^22026.03 | 0.833 | — | — | 0.844 | — | — | |
| SimpleVQAInference Time (Sec)=0.714, Testing Protocol=Cross-dataset Testing2024.02 | 0.826 | — | — | 0.82 | — | — | |
| SSL-VQAprotocol=few-shot2026.04 | 0.826 | — | — | 0.828 | — | — | |
| Full-res Swin-T feat., 32 x 4 frames2022.10 | 0.825 | — | — | 0.828 | — | — | |
| qbInference Time (Sec)=0.159, Testing Protocol=Cross-dataset Testing2024.02 | 0.822 | — | — | 0.836 | — | — | |
| 2BiVQAPre-training Dataset=ImageNet [7], KonIQ-10k [15]2025.03 | 0.815 | — | — | 0.835 | — | — | |
| GSTVQA2024.02 | 0.814 | — | — | 0.825 | — | — | |
| RAPIQUEprotocol=supervised2026.04 | 0.811 | — | — | 0.819 | — | — | |
| VSFAInference Time (Sec)=11.109, Testing Protocol=Cross-dataset Testing2024.02 | 0.81 | — | — | 0.811 | — | — | |
| TiVQAAttack Status=Before Attack2023.09 | 0.8046 | — | — | 0.8377 | — | — | |
| RAPIQUEbackbone=ResNet-50, sampling_rate=2 fps2021.01 | 0.8031 | — | — | 0.8175 | 0.3623 | — | |
| RAPIQUEType=VQA2022.04 | 0.803 | — | — | 0.818 | — | — | |
| RAPIQUE2024.02 | 0.803 | — | — | 0.817 | — | — | |
| ResNet50Type=IQA2022.04 | 0.802 | — | — | 0.81 | — | — | |
| ASOTraining Strategy=Analytic Score Optimization2026.02 | 0.801 | — | — | 0.835 | — | — | |
| CSPTprotocol=few-shot2026.04 | 0.801 | — | — | 0.806 | — | — | |
| MDTVSFAAttack Status=Before Attack2023.09 | 0.8003 | — | — | 0.8074 | — | — | |
| VSFA2024.02 | 0.794 | — | — | 0.799 | — | — | |
| VSFAprotocol=supervised2026.04 | 0.794 | — | — | 0.799 | — | — | |
| VSFAEvaluation Protocol=10-fold cross-validation2025.05 | 0.794 | — | — | 0.799 | — | — | |
| SimpleVQA2024.02 | 0.792 | — | — | 0.798 | — | — | |
| PVQ w/patch2022.10 | 0.791 | — | — | 0.795 | — | — |