IST Research Talks: James Wang and Sharon Huang
Date & Time: September 11, 2025 from 12:05 PM - 01:15 PM
Location: Westgate Building | E202
Watch this talk below.
James Wang, Distinguished Professor of IST, and Sharon Huang, David Reese Professor of IST and Interim Head of Department, Informatics and Intelligent Systems, held a collaborative discussion as part of the IST Research Talks series.
Wang presented "Visions of Emotion: Decoding Human Bodily Expressions" and Huang presented "Synthetic Image and Video Generation for Data Augmentation and Sharing in Medical Applications." Together, they took questions from attendees at the conclusion of their talks.
View all upcoming talks on the IST Research Talks page.
About the Talks
"Visions of Emotion: Decoding Human Bodily Expressions " - presented by James Z. Wang
The emergence of artificial emotional intelligence technology is revolutionizing the fields of computers and robotics, allowing for a new level of communication and understanding of human behavior that was once thought impossible. Whereas recent advancements in deep learning have transformed the field of computer vision, automated understanding of evoked or expressed emotions in visual media remains in its infancy. This foundering stems from the absence of a universally accepted definition of "emotion," coupled with the inherently subjective nature of emotions and their intricate nuances. In this talk, Wang will provide a brief overview of the computer vision research of his lab and then focus on their recent work on bodily expressed emotion understanding in the wild. The multidisciplinary effort among computer and information sciences, psychology, and statistics, proposed a scalable and reliable crowdsourcing approach for collecting in-the-wild perceived emotion data for computers to learn to recognize body languages of humans. A large and growing annotated dataset with about 10,000 body movements video clips and over 13,000 human characters, named BoLD (Body Language Dataset), has been created. Comprehensive statistical analysis revealed many interesting insights from the dataset. A system to model emotional expressions based on bodily movements, named ARBEE (Automated Recognition of Bodily Expression of Emotion), has also been developed and evaluated. Besides, we have developed a high-quality human motor element dataset based on the Laban Movement Analysis movement coding system and utilized that to jointly learn about motor elements and emotions. Their long-term goal is to integrate knowledge from computing, psychology, and performing arts to enable automated understanding and analysis of emotion through body language.
"Synthetic Image and Video Generation for Data Augmentation and Sharing in Medical Applications " - presented by Sharon X. Huang
In this talk, Huang will discuss mainstream models for generating synthetic images and videos. She'll then present several conditional generative models for synthesizing realistic medical images and videos, and demonstrate how such synthetic data can be used for data augmentation towards enhancing image or video classification performance and for privacy-preserving data sharing towards enabling large-scale medical foundational model training. The talk will conclude with a discussion of future research directions in image and video synthesis.
About the Speakers
Sharon X. Huang is currently David Reese Professor and interim department head in the College of Information Sciences and Technology. Her research interests are in the areas of generative AI, computer vision, biomedical image analysis, and machine learning. She has published more than 200 articles and her works have been cited more than 23,000 times with h-index 50. She received her bachelor's degree in computer science from Tsinghua University, and her master of science and doctoral degrees in computer science from Rutgers University.
James Z. Wang received his bachelor's degree in mathematics summa cum laude from the University of Minnesota, Twin Cities, Minnesota, and mater of science in mathematics, master of science in computer science, and doctoral in medical information sciences degrees, all from Stanford University, Stanford, California. His publications have been cited about 30,000 times (h=65). He has supervised about 30 doctoral students. More information about his research group can be found at http://wang.ist.psu.edu.
Our events and programs are open to all students regardless of sex, gender, sexual orientation, race, or any other protected class. The College of Information Sciences and Technology is committed to building a community of belonging for all.