Wen-Huang Cheng is NTU Distinguished Chair Professor with the Department of Computer Science and Information Engineering, National Taiwan University (NTU). His current research interests include multimedia, computer vision, and machine learning. He has actively participated in international events and played important leading roles in prestigious journals and conferences and professional organizations, including Editor-in-Chief for IEEE CTSoc News on Consumer Technology, Senior Editor for IEEE Consumer Electronics Magazine, Associate Editor for IEEE Transactions on Multimedia (T-MM), General Chair for ACM MMAsia (2023), IEEE ICCE-TW (2023, 2022), IEEE ICME (2022) and ACM ICMR (2021), Chair for IEEE Multimedia Systems and Applications (MSA) technical committee, governing board member for IAPR. He has received numerous research and service awards, including the Best Paper Award of 2021 IEEE ICME and the Outstanding Associate Editor Award of IEEE T-MM (2021 and 2020, twice). He is IEEE Fellow, IET Fellow, and ACM Distinguished Member.

The focus of our research is on artificial intelligence (AI) and multimedia, closely integrated with computer vision, machine learning, and human-computer interaction. The basic objective of AI is the capability of computers to perform tasks commonly associated with intelligent beings. As humans, vision is central to the way we learn about the world, and it follows that one ultimate pursuit of building an intelligent AI machine is to enable it with powerful visual intelligence. To date, visual data (in particular, images, photos, videos, and other visual social media) have been increasingly becoming the biggest big data. The big visual data are not just big in volume, but also impose fundamental technical challenges as visual content is noisy, unsegmented, high entropy and multidimensional. Through tackling the technical challenges, enabling visual AI is the general goal of our research, i.e., we aim at investigating intelligent algorithms to enable efficient and robust predictive analytics on big visual data. More specifically, our main research activities are centered on developing novel machine learning approaches (e.g., deep learning) to perform important visual perception tasks (e.g., typical topics include object recognition, scene understanding, and human action analysis), while attaching importance to social, public, and industrial value.