Aesthetic Visual Question Answering of Photographs

Abstract

Aesthetic assessment of images can be categorized into two main forms: numerical assessment and language assessment. In this paper, we propose a new task of aesthetic language assessment: aesthetic visual question and answering (AVQA) of images. We use images from www.flickr.com. The objective QA pairs are generated by the proposed aesthetic attributes analysis algorithms. Moreover, we introduce subjective QA pairs that are converted from aesthetic numerical labels and sentiment analysis from large-scale pre-train models. We build the first aesthetic visual question answering dataset, AesVQA, that contains 72,168 high-quality images and 324,756 pairs of aesthetic questions. This is the first work that both addresses the task of aesthetic VQA and introduces subjectiveness into VQA tasks. The experimental results reveal that our methods outperform other VQA models on this new task.