Weakly Supervised Learning For Unconstrained Face Processing PDF Download

In this Thesis we focus on Automatic Facial Behavior Analysis, which attempts to develop autonomous systems able to recognize and understand human facial expressions. Given the amount of information expressed by facial gestures, this type of systems has potential applications in multiple domains such as Human Computer Interaction, Marketing or Healthcare. For this reason, the topic has attracted a lot of attention in Computer Vision and Machine Learning communities during the past two decades. Despite the advances in the field, most of facial expression analysis problems can be considered far from being solved. In this context, this dissertation is motivated by the observation that the vast majority of methods in the literature has followed the Supervised Learning paradigm, where models are trained by using data explicitly labelled according to the target problem. However, this approach presents some limitations given the difficult annotation process typically involved in facial expression analysis tasks. In order to address this challenge, we propose to pose Automatic Facial Behavior Analysis from a weakly-supervised perspective. Different from the fully-supervised strategy, weakly-supervised models are trained by using labels which are easy to collect but only provide partial information about the task that aims to be solved (i.e, weak-labels). Following this idea, we present different weakly-supervised methods to address standard problems in the field such as Action Unit Recognition, Expression Intensity Estimation or Affect Analysis. Our results obtained by evaluating the proposed approaches on these tasks, demonstrate that weakly-supervised learning may provide a potential solution to alleviate the need of annotated data in Automatic Facial Behavior Analysis. Moreover we also show how these approaches are able to facilitate the labelling process of databases designed for this purpose.