HyperAI超神经

Video Quality Assessment On Youtube Ugc

评估指标

PLCC

评测结果

各个模型在此基准测试上的表现结果

模型名称
PLCC
Paper TitleRepository
SimpleVQA0.856A Deep Learning based No-reference Quality Assessment Model for UGC Videos
HVS-5M0.8451HVS Revisited: A Comprehensive Video Quality Assessment Framework-
FAST-VQA (trained on LSVQ only)0.748FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling
FasterVQA (fine-tuned)0.859Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessment
RAPIQUE0.7684RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content
FAST-VQA (finetuned on YouTube-UGC)0.852FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling
ReLaX-VQA (finetuned on YouTube-UGC)0.8652ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment
VIDEVAL0.7733UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content
CONTRIQUE0.813Image Quality Assessment using Contrastive Learning
2BiVQA0.7942BiVQA: Double Bi-LSTM based Video Quality Assessment of UGC Videos
DOVER (end-to-end)0.874Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives
ChipQA0.6911ChipQA: No-Reference Video Quality Prediction via Space-Time Chips
BVQA-20220.8178Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception
DOVER (head-only)0.862Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives
ReLaX-VQA (trained on LSVQ only)0.8354ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment
ReLaX-VQA0.8204ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment
CONVIQT0.822CONVIQT: Contrastive Video Quality Estimator
0 of 17 row(s) selected.