I am interested in designing intelligent systems that can learn concepts from visual data. Visual data are images or videos coming from either existing available databases, or directly from the Web.

My PhD thesis was focused on the attribute-based object recognition task and centred around the framework of learning using privileged information. My current research interests include deep learning methods for understanding human behaviour (actions and emotions) from facial and bodily cues. Also I am interested in the topic of algorithmic fairness and in designing machine learning models that can overcome human and dataset collection biases.