HyperAI超神经
首页资讯最新论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAI超神经

Video Quality Assessment On Live Vqc

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
RAPIQUE0.7863RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content
HVS-5M0.8422HVS Revisited: A Comprehensive Video Quality Assessment Framework-
ReLaX-VQA (finetuned on LIVE-VQC)0.8876ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment
2BiVQA0.8322BiVQA: Double Bi-LSTM based Video Quality Assessment of UGC Videos
DisCoVQA0.844DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessment
CONVIQT0.817CONVIQT: Contrastive Video Quality Estimator
FAST-VQA (trained on LSVQ only)0.844FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling
ChipQA0.7299ChipQA: No-Reference Video Quality Prediction via Space-Time Chips
DOVER (end-to-end)0.874Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives
PVQ0.791Patch-VQ: 'Patching Up' the Video Quality Problem
ReLaX-VQA (trained on LSVQ only)0.8242ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment
BVQA-20220.839Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception
FasterVQA (fine-tuned)0.858Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessment
VIDEVAL0.7514UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content
FAST-VQA (finetuned on LIVE-VQC)0.862FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling
VSFA0.7426Quality Assessment of In-the-Wild Videos
TLVQM0.8025Two-Level Approach for No-Reference Consumer Video Quality Assessment
DOVER (head-only)0.863Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives
ReLaX-VQA0.8079ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment
CONTRIQUE0.822Image Quality Assessment using Contrastive Learning
0 of 20 row(s) selected.