Behaviour Analysis Using Visual Cues
Abstract: Humans are capable of forming accurate impressions of others’ personality traits upon observing relatively short behavioural sequences. Recently, a number of automated personality prediction approaches have been proposed. I will first present a brief overview of my Human‐centric computing research focused on understanding perception and behaviour. Then, I will describe our work on personality estimation employing multimodal behavioural cues, followed by a discussion on the challenges in estimating social attention (where one looks) from visual data.
Biosketch: Ramanathan Subramanian (Subramanian.R@adsc.com.sg) is a Research Scientist at the Advanced Digital Sciences Center (ADSC). Previously, he has served as a post‐doctoral researcher at the Dept. of Information Engineering and Computer Science, University of Trento, Italy and the School of Computing, NUS. His research interests span Human‐centered computing, Human‐behavior understanding, Computer Vision and Multimedia processing. He is especially interested in studying and modelling various aspects of human visual and emotional perception. His research has contributed to the prominent NUSEF (eye‐fixation) and DPOSE (dynamic head pose) datasets. ADSC is a research center of Illinois at Singpore Pte, Ltd, and affiliate of the University of Illinois. Located in Singapore, it is led by Illinois faculty, dedicated to transform the way people and organizations use and interact with information technologies and contribute to the advance of the knowledge‐based economy in Singapore and beyond.