Minh Hoai Nguyen – Research Interests

My research broadly encompasses computer vision and machine learning, specifically focusing on human behavior analysis. By human behavior, I mean the actions or activities of a person or a group of people as captured by cameras or recorded by wearable devices. Human behavior also refers to the interaction between hands and other objects, and sometimes the behavior of a person can be determined based only on the observation of their hands. Human behavior could also include facial or head movements, as there might be a need to quantify how happy or depressed a person is. Human behavior also includes attentional behavior, and I am interested in discovering the parts of an image or a video that attract visual attention, as well as predicting and manipulating visual attention. As for the analysis tasks, I am working on both recognition and prediction tasks. Recognition is concerned with the past, while prediction refers to the future. There is a third category of analysis tasks called early recognition which I am particularly interested in. Early recognition refers to the present, and the task is to detect and categorize an ongoing activity.

Advancing algorithms for human behavior analysis necessitates tackling a range of computer vision challenges, such as hand detection and tracking, identification and segmentation of hand-held objects, and counting of repetitive actions. My research extends to machine learning because human behavior is so complex that algorithms for human behavior analysis need to be trained rather than hand-designed. In general, the performance of a learning-based method depends on the quantity and quality of human-annotated data to train it, but providing detailed annotations for human behavior is a laborious and subjective process. Thus underlying many of my research projects is the development of algorithms that can learn from weakly-labeled, noisily-labeled, or unlabeled data. A particular interest of mine is in life-long learning algorithms that self-improve and adapt autonomously to new scenes and situations.

Human behavior analysis is essential for many applications in a wide range of fields, from entertainment and education to surveillance and healthcare. My research often begins with interdisciplinary collaborations with domain experts in fields such as psychology, nephrology, physics, and education. Although initiated by practical applications, my research is predominantly driven by identifying and resolving technical challenges, which leads to the development of innovative algorithms. While these algorithms are designed for specific use cases, their impacts extend well beyond their original applications.

Browse my publications by topics on my publication page to gain a deeper understanding of my research.