Xiaojiang Peng (IEEE Senior Member) is a full professor at the College of Big Data and Internet, Shenzhen Technology University, and serves as the dean of artificial intelligence department. He received his Ph.D. degrees from Southwest Jiaotong University. He was an associate professor at Shenzhen Technology University from 2020 to 2023, and an associate professor at Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences from 2017 to 2020. Previously, he was a postdoctoral researcher at Idiap, Switzerland and Inria LEAR/THOTH, France from 2015 to 2017. He has published more than 100 top journal/conference papers (e.g., TIP, CVPR, ICCV, ECCV, NeurIPS, AAAI), garnering more than 7,300 citations on Google Scholar. He has been ranked as the World's Top 2% scientist since 2022. His research interests include computer vision, affective computing, and generative AI applications.

Title: Emotional AI: From Facial Expression Neural Networks to Multimodal Large  Language Models

Abstract: In an increasingly digital world, understanding human emotions is more important than ever. Affective computing bridges the gap between technology and human experience, enabling machines to recognize, interpret, and respond to our emotions. Nevertheless, it is challenging to analyse human emotions due to ambiguous annotations and data rarity. This talk will trace the evolution of affective computing, starting with the foundational work on facial expression recognition, which provided initial insights into how machines can decode visual cues of emotion. We will explore the limitations of early approaches and the subsequent shift towards more comprehensive multimodal emotion understanding, which integrates data from various sources, including image context, voice tone, and natural language. Moreover, we will examine recent Multimodal LLMs or LLMs in the field of affective computing, and highlight how these technologies enhance our ability to create emotionally intelligent systems.