ReLaX-VQA (finetuned on KoNViD-1k)

Reported on 3 benchmarks across 3 tasks · 1 paper

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· 2024-07-16
0.8668
best: 0.905 (DOVER (end-to-end))
ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment arXiv:2407.11496
VideoonKoNViD-1k
PLCC· uses extra data· 2024-07-16
0.8668
best: 0.905 (DOVER (end-to-end))
ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment arXiv:2407.11496

Time Series1 result

Video Quality AssessmentonKoNViD-1k
PLCC· uses extra data· 2024-07-16
0.8668
best: 0.905 (DOVER (end-to-end))
ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment arXiv:2407.11496