Multi-modal Learnable Queries for Image Aesthetics Assessment

arXiv:2405.01326v1 Announce Type: new
Abstract: Image aesthetics assessment (IAA) is attracting wide interest with the prevalence of social media. The problem is challenging due to its subjective and ambiguous nature. Instead of directly extracting aesthetic features solely from the image, user comments associated with an image could potentially provide complementary knowledge that is useful for IAA. With existing large-scale pre-trained models demonstrating strong capabilities in extracting high-quality transferable visual and textual features, learnable queries are shown to be effective in …

abstract arxiv assessment cs.cv features image knowledge media modal multi-modal nature queries social social media type