Predicting Subjective Attributes in Visual Data

Recent progress in deep neural networks has revolutionized many computer vision tasks such as image classification, detection, and segmentation. However, in addition to excelling in tasks that predict well defined objective information, human centered artificial intelligence systems should also be able to model subjective attributes, as defined by human perceptual behavior, that goes beyond the pure physical content of visual data. Example subjective tasks are the prediction of spatial or temporal regions that are interesting to humans (eg, attract attention or are visually pleasing) and the recognition of subjective attributes (eg, visually elicited sentiments). Better models for these tasks will improve the human-computer interaction experience in various applications. This thesis investigates several approaches to address the challenges in predicting those subjective attributes in visual data over a diverse set of tasks. I …