Vision-language models encode diverse aesthetic attributes that propagate through decoder layers and enable effective personalized image aesthetics assessment using lightweight linear models without fine-tuning.
In Proceedings of the IEEE international conference on computer vision, pages 3514–3523
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
What Do Vision-Language Models Encode for Personalized Image Aesthetics Assessment?
Vision-language models encode diverse aesthetic attributes that propagate through decoder layers and enable effective personalized image aesthetics assessment using lightweight linear models without fine-tuning.