Enhancing Zero-shot Personalized Image Aesthetics Assessment with Profile-aware Multimodal LLM
For researchers and practitioners in personalized image aesthetics assessment, this work addresses the cold-start problem where no historical user ratings are available.
The paper tackles zero-shot personalized image aesthetics assessment (PIAA) by using user profiles instead of historical ratings. The proposed P-MLLM achieves competitive zero-shot performance, remaining effective even with coarse profile information.
Personalized image aesthetics assessment (PIAA) aims to predict an individual user's subjective rating of an image, which requires modeling user-specific aesthetic preferences. Existing methods rely on historical user ratings for this modeling and therefore struggle when such data are unavailable. We address this zero-shot setting by using user profiles as contextual signals for personalization and adopting a profile-based personalization paradigm. We introduce P-MLLM, a profile-aware multimodal LLM that augments a frozen LLM with selective fusion modules for controlled visual integration. These modules selectively integrate visual information into the model's evolving hidden states during profile-conditioned reasoning, allowing visual information to be incorporated in a profile-aware manner. Experiments on recent PIAA benchmarks show that P-MLLM achieves competitive zero-shot performance and remains effective even with coarse profile information, highlighting the potential of profile-based personalization for zero-shot PIAA.