TransformAR-KD+ uses knowledge distillation with category-aware teachers and cross-attention decoders to improve AR image quality prediction, achieving SRCC 0.8411 on ARIQA.
Research and application of the adaptive model of the human visual sys- tem for improving the effectiveness of objective video quality metrics,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Enhancing Content Representation for AR Image Quality Assessment Using Knowledge Distillation
TransformAR-KD+ uses knowledge distillation with category-aware teachers and cross-attention decoders to improve AR image quality prediction, achieving SRCC 0.8411 on ARIQA.