Exploiting emotional concepts for image emotion recognition

With the increasing number of users express their emotions via images on social media, image emotion recognition attracts much attention of researchers. Different from conventional computer vision tasks, image emotion recognition is inherently more challenging for the ambiguity and subjectivity of emotion. Existing methods are limited to learn a direct mapping from image feature to emotion. However, emotion cognition mechanism in psychology demonstrates that human beings perceive emotion in a stepwise way. Therefore, we propose a novel image emotion recognition method that leverages emotional concepts as intermediary to bridge image and emotion. Specifically, we organize the relationship between concept and emotion in the form of knowledge graph. The relation between image and emotion is explored in the semantic embedding space where the knowledge is encoded into. Then, based on the hierarchical relation of emotions, we propose a multi-task learning deep model to recognize image emotion from visual perspective. Finally, a fusion strategy is proposed to merge the results of both visual-semantic stream and visual stream. Extensive experimental results show that our method outperforms state-of-the-art methods on two public image emotion datasets.

Automated summary

The research proposes a novel method for image emotion recognition, leveraging emotional concepts as intermediaries to connect images and emotions by organizing the relationship between concepts and emotions in the form of a knowledge graph. By exploring the relation between images and emotions in the semantic embedding space and using a multi-task learning deep model, the method successfully recognizes image emotions from a visual perspective, with the fusion strategy showing promising experimental results.