Video Quality Assessment On Msu Sr Qa Dataset

Metrics

KLCC

PLCC

SROCC

Type

Results

Performance results of various models on this benchmark

Comparison Table

Model Name	KLCC	PLCC	SROCC	Type
Model 1	0.16365	0.20138	0.21450	FR
exploring-clip-for-assessing-the-look-and	0.69774	0.71808	0.56875	NR
musiq-multi-scale-image-quality-transformer	0.51897	0.59151	0.64589	NR
fsim-a-feature-similarity-index-for-image	0.26942	0.35083	0.34996	FR
Model 5	0.12067	0.09428	0.16441	FR
pieapp-perceptual-image-error-assessment	0.61945	0.75743	0.75215	FR
norm-in-norm-loss-with-faster-convergence-and	0.52172	0.62204	0.64382	NR
multiscale-structural-similarity-for-image	0.07821	0.16035	0.11017	FR
topiq-a-top-down-approach-from-semantics-to	0.40663	0.51061	0.51687	NR
blind-image-quality-assessment-using-a-deep	0.55139	0.63971	0.68621	NR
q-align-teaching-lmms-for-visual-scoring-via	0.61677	0.74116	0.75088	NR
the-unreasonable-effectiveness-of-deep	0.43158	0.52385	0.54461	FR
Model 13	0.09998	0.13840	0.12914	FR
topiq-a-top-down-approach-from-semantics-to	0.42811	0.57564	0.55568	FR
the-unreasonable-effectiveness-of-deep	0.41471	0.52820	0.52868	FR
erqa-edge-restoration-quality-assessment-for	0.47785	0.60188	0.59345	FR
Model 17	0.47674	0.62311	0.60468	FR
Model 18	0.32283	0.40073	0.43219	FR
image-quality-assessment-unifying-structure	0.42320	0.55042	0.53346	FR
q-align-teaching-lmms-for-visual-scoring-via	0.42211	0.50055	0.51521	NR
Model 21	0.34004	0.41892	0.44064	NR
blindly-assess-image-quality-in-the-wild	0.48466	0.55211	0.59883	NR
Model 23	0.32331	0.39744	0.43296	FR
Model 24	0.13551	0.19672	0.17889	FR
unified-quality-assessment-of-in-the-wild	0.48406	0.61821	0.60193	NR
quality-assessment-of-in-the-wild-videos	0.43634	0.54407	0.53652	NR
musiq-multi-scale-image-quality-transformer	0.44669	0.52404	0.56152	NR
Model 28	0.24254	0.33169	0.33167	NR
musiq-multi-scale-image-quality-transformer	0.52673	0.60216	0.64927	NR
multiscale-structural-similarity-for-image	0.18174	0.21800	0.24422	FR
topiq-a-top-down-approach-from-semantics-to	0.53140	0.60905	0.64923	NR
exploring-clip-for-assessing-the-look-and	0.38794	0.50379	0.49881	NR
no-reference-image-quality-assessment-via-1	0.39398	0.50005	0.48882	NR
topiq-a-top-down-approach-from-semantics-to	0.28473	0.34000	0.36204	NR
topiq-a-top-down-approach-from-semantics-to	0.48428	0.58949	0.59564	NR
multiscale-structural-similarity-for-image	0.16578	0.30014	0.21604	FR
the-2018-pirm-challenge-on-perceptual-image	0.39101	0.53178	0.52319	NR
musiq-multi-scale-image-quality-transformer	0.55312	0.66531	0.67746	NR
from-patches-to-pictures-paq-2-piq-mapping	0.57753	0.70988	0.71167	NR
vila-learning-image-aesthetics-from-user	0.26180	0.28846	0.33728	NR
exploring-clip-for-assessing-the-look-and	0.49417	0.58944	0.60808	NR
no-reference-image-quality-assessment-via-1	0.49004	0.56226	0.62578	NR
no-reference-image-quality-assessment-in-the	0.24803	0.31143	0.32327	NR
image-quality-assessment-from-error	0.17175	0.20670	0.22468	FR
Model 45	0.08263	0.10931	0.10733	FR
topiq-a-top-down-approach-from-semantics-to	0.46217	0.57955	0.57341	FR
maniqa-multi-dimension-attention-network-for	0.54744	0.62733	0.66613	NR
exploring-clip-for-assessing-the-look-and	0.52628	0.65154	0.65713	NR
Model 49	0.11040	0.14638	0.14277	FR
Model 50	0.26485	0.36944	0.34862	FR
topiq-a-top-down-approach-from-semantics-to	0.50670	0.57674	0.62715	NR
multiscale-structural-similarity-for-image	0.17468	0.20935	0.23108	FR
shift-tolerant-perceptual-similarity-metric-1	0.42897	0.54740	0.53473	FR
learning-a-no-reference-quality-metric-for	0.52301	0.65357	0.67362	NR
q-align-teaching-lmms-for-visual-scoring-via	0.58634	0.71121	0.71812	NR
shift-tolerant-perceptual-similarity-metric-1	0.45898	0.56431	0.57336	FR
nima-neural-image-assessment	0.20377	0.26550	0.25887	NR
no-reference-image-quality-assessment-via-1	0.48901	0.56277	0.62496	NR
topiq-a-top-down-approach-from-semantics-to	0.26774	0.33940	0.34092	NR
locally-adaptive-structure-and-texture	0.41261	0.53289	0.51717	FR