Image Emotion Computing

Images can convey rich semantics and induce strong emotions in viewers. My research aims to predict image emotions from different aspects with respect to two main challenges: affective gap and subjective evaluation. To bridge the affective gap, we extract emotion features based on principles-of-art to recognize image-centric dominant emotions. As the emotions that are induced in viewers by an image are highly subjective and different, we propose to predict user-centric personalized emotion perceptions for each viewer and image-centric emotion probability distribution for each image. To tackle the subjective evaluation issue, we set up a large scale image emotion dataset from Flickr, named Image-Emotion-Social-Net, on both dimensional and categorical emotion representations with over 1 million images and about 8,000 users. Different types of factors may influence personalized image emotion perceptions, including visual content, social context, temporal evolution and location influence. We make an initial attempt to jointly combine them by the proposed rolling multi-task hypergraph learning. Both discrete and continuous emotion distributions are modelled via shared sparse learning. Further, several potential applications based on image emotions are designed and implemented.