Multimodal visual sensing: automated estimation of engagement

Many modern applications of artificial intelligence involve, to some extent, an understanding of human attention, activity, intention, and competence from multimodal visual data. Nonverbal behavioral cues detected using computer vision and machine learning methods include valuable information for understanding human behaviors, including attention and engagement. The use of such automated methods in educational settings has a tremendous potential for good. Beneficial uses include classroom analytics to measure teaching quality and the development of interventions to improve teaching based on these analytics, as well as presentation analysis to help students deliver their messages persuasively and effectively. This dissertation presents a general framework based on multimodal visual sensing to analyze engagement and related tasks from visual modalities. While the majority of engagement literature in affective and social computing focuses on computer-based learning and educational games, we investigate automated engagement estimation in the classroom using different nonverbal behavioral cues and developed methods to extract attentional and emotional features. Furthermore, we validate the efficiency of proposed approaches on real-world data collected from videotaped classes at university and secondary school. In addition to learning activities, we perform behavior analysis on students giving short scientific presentations using multimodal cues, including face, body, and voice features. Besides engagement and presentation competence, we approach human behavior understanding from a broader perspective by studying the analysis of joint attention in a group of people, teachers' perception using egocentric camera view and mobile eye trackers, and automated anonymization of audiovisual data in classroom studies. Educational analytics present valuable opportunities to improve learning and teaching. The work in this dissertation suggests a computational framework for estimating student engagement and presentation competence, together with supportive computer vision problems