Perceived emotion from images through deep neural networks
This is a yet unfinished project, whose aim is exploring the use of deep neural networks to predict the perceived emotion from natural images. Deep neural networks are extremely successful in a myriad of tasks, but the task of affective content analysis remains largely open, due to its subjective nature and the lack of large data sets that deep networks usually requires.
In this project we aim at exploring the ways in which deep neural networks can overcome these limitations. We propose to use new data augmentation techniques, semi-supervised learning as well as new network architectures, more suitable for this type of complex, subjective task.