Flickr Circles: Aesthetic Tendency Discovery by Multi-View Regularized Topic Modeling

Aesthetic tendency discovery is a useful and interesting application in social media. In this paper we propose to categorize large-scale Flickr users into multiple circles, each containing users with similar aesthetic interests (e.g., landscapes). We notice that: 1) an aesthetic model should be flexible as different visual features may be used to describe different image sets; 2) the numbers of photos from different Flickr users vary significantly and some users may have very few photos; and 3) visual features from each Flickr photo should be seamlessly integrated at both low-level and high-level. To meet these challenges, we propose to fuze color, textural, and semantic channel features using a multi-view learning framework, where the feature weights are adjusted automatically. Then, a regularized topic model is developed to quantify each user's aesthetic interest as a distribution in the latent space. Afterward, a graph is constructed to describe the discrepancy of aesthetic interests among users. Apparently, densely connected users are with similar aesthetic interests. Thus, an efficient dense subgraph mining algorithm is adopted to group Flickr users into multiple circles. Experiments have shown that our approach performs competitively on a million-scale image set crawled from Flickr. Besides, our method can enhance the transferal-based photo cropping [40] as reported by the user study.