Video Quality Assessment On Konvid 1K

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

		Paper Title	Repository
DOVER (end-to-end)	0.905	Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives
FasterVQA (fine-tuned)	0.898	Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessment
DOVER (head-only)	0.894	Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives
FAST-VQA (finetuned on KonViD-1k)	0.892	FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling
ReLaX-VQA (finetuned on KoNViD-1k)	0.8668	ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment
SimpleVQA	0.860	A Deep Learning based No-reference Quality Assessment Model for UGC Videos
DisCoVQA	0.860	DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessment
HVS-5M	0.8562	HVS Revisited: A Comprehensive Video Quality Assessment Framework	-
FAST-VQA (trained on LSVQ only)	0.855	FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling
CONVIQT	0.849	CONVIQT: Contrastive Video Quality Estimator
ReLaX-VQA	0.8473	ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment
ReLaX-VQA (trained on LSVQ only)	0.8427	ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment
CONTRIQUE	0.842	Image Quality Assessment using Contrastive Learning
2BiVQA	0.835	2BiVQA: Double Bi-LSTM based Video Quality Assessment of UGC Videos
BVQA-2022	0.834	Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception
RAPIQUE	0.8175	RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content
VIDEVAL	0.7803	UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content
VSFA	0.7754	Quality Assessment of In-the-Wild Videos
PVQ	0.770	Patch-VQ: 'Patching Up' the Video Quality Problem
TLVQM	0.7688	Two-Level Approach for No-Reference Consumer Video Quality Assessment	-

0 of 21 row(s) selected.