FAST-VQA (finetuned on KonViD-1k)

Reported on 3 benchmarks across 3 tasks · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

Video UnderstandingonKoNViD-1k
PLCC· uses extra data· 2022-07-06
0.892
best: 0.905 (DOVER (end-to-end))
SOTA
FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling arXiv:2207.02595
VideoonKoNViD-1k
PLCC· uses extra data· 2022-07-06
0.892
best: 0.905 (DOVER (end-to-end))
SOTA
FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling arXiv:2207.02595

Time Series1 result

Video Quality AssessmentonKoNViD-1k
PLCC· uses extra data· 2022-07-06
0.892
best: 0.905 (DOVER (end-to-end))
SOTA
FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling arXiv:2207.02595