Affect recognition based on subjects' facial expressions has been a topic of major research in the attempt to generate machines that can understand the way subjects feel, act and react. In the past, due to the unavailability of large amounts of data captured in real-life situations, research has mainly focused on controlled environments. However, recently, social media and platforms have been widely used. Moreover, deep learning has emerged as a means to solve visual analysis and recognition problems. This paper exploits these advances and presents significant contributions for affect analysis and recognition in-the-wild. Affect analysis and recognition can be seen as a dual knowledge generation problem, involving: i) creation of new, large and rich in-the-wild databases and ii) design and training of novel deep neural architectures that are able to analyse affect over these databases and to successfully generalise their performance on other datasets. The paper focuses on large in-the-wild databases, i.e., Aff-Wild and Aff-Wild2 and presents the design of two classes of deep neural networks trained with these databases. The first class refers to uni-task affect recognition, focusing on prediction of the valence and arousal dimensional variables. The second class refers to estimation of all main behavior tasks, i.e. valence-arousal prediction; categorical emotion classification in seven basic facial expressions; facial Action Unit detection. A novel multi-task and holistic framework is presented which is able to jointly learn and effectively generalize and perform affect recognition over all existing in-the-wild databases. Large experimental studies illustrate the achieved performance improvement over the existing state-of-the-art in affect recognition. HIS paper presents recent developments and research directions in affective behavior analysis in-the-wild, which is a major targeted characteristic of human computer interaction systems in real life applications. Such systems, machines and robots, should be able to automatically sense and interpret facial and audio-visual signals relevant to emotions, appraisals and intentions; thus, being able to interact in a'human-centered' and engaging manner with people, as their digital assistants in the home, work, operational or industrial environment. Through human affect recognition, the reactions of the machine, or robot, will be consistent with people's expectations and emotions; their verbal and non-verbal interactions will be positively received by humans. Moreover, this interaction should not be dependent on the respective context, nor the human's age, sex, ethnicity, educational level, profession, or social position. As a consequence, the development of intelligent systems able to analyze human behavior in-the-wild can contribute to generation of trust, understanding and closeness between humans and machines in real life environments.

Automatic facial behavior analysis has a long history of studies in the intersection of computer vision, physiology and psychology. However it is only recently, with the collection of large-scale datasets and powerful machine learning methods such as deep neural networks, that automatic facial behavior analysis started to thrive. Three of its iconic tasks are automatic recognition of basic expressions (e.g. happy, sad, surprised), estimation of continuous emotions (e.g., valence and arousal), and detection of facial action units (activations of e.g. upper/inner eyebrows, nose wrinkles). Up until now these tasks have been mostly studied independently collecting a dataset for the task. We present the first and the largest study of all facial behaviour tasks learned jointly in a single multi-task, multi-domain and multi-label network, which we call FaceBehaviorNet. For this we utilize all publicly available datasets in the community (around 5M images) that study facial behaviour tasks in-the-wild. We demonstrate that training jointly an end-to-end network for all tasks has consistently better performance than training each of the single-task networks. Furthermore, we propose two simple strategies for coupling the tasks during training, co-annotation and distribution matching, and show the advantages of this approach. Finally we show that FaceBehaviorNet has learned features that encapsulate all aspects of facial behaviour, and can be successfully applied to perform tasks (compound emotion recognition) beyond the ones that it has been trained in a zero- and few-shot learning setting.