CityU hosts AI lecture on challenges and opportunities in multimodal scene understanding

The Faculty of Data Science (FDS) at City University of Macau (CityU) recently held an academic lecture titled “Multimodal Scene Understanding” at the Ho Yin Convention Centre of the Taipa campus. The event featured Han Jungong, Xinghua distinguished university professor from the Department of Automation at Tsinghua University, as the distinguished speaker. The lecture attracted numerous faculty and students, who engaged in discussions on the application prospects of learning-enabled cyber-physical systems in autonomous vehicles and unmanned aerial vehicles.

During the lecture, Professor Han systematically presented cutting-edge advancements in multimodal scene understanding, explaining how machines integrate and reason with multi-source perceptual information—such as visual, auditory, and tactile data—to achieve accurate environmental perception, in-depth comprehension, and natural interaction in complex scenarios.

[foogallery id="98508"]

He systematically outlined the latest advancements in the field, covering model architecture design, multimodal fusion strategies, algorithm optimization, and practical applications. Professor Han demonstrated how these technologies are continuously pushing the boundaries of traditional perception and cognition, driving intelligent robots towards higher levels of autonomy and intelligence.

Furthermore, he provided an in-depth analysis of the key challenges and future opportunities in developing intelligent systems capable of cross-modal learning, robustness, context awareness, and human-like understanding.

During the Q&A session, faculty and students actively raised questions, and Professor Han provided detailed responses, further enhancing the understanding of the audience.

Participants found the lecture highly insightful, noting that it not only broadened their academic perspectives but also provided valuable references for practical research. They noted that the dialogue between theory and practice could further stimulated innovative thinking among all attendees.

Professor Han Jungong previously served as chair professor in the School of Computer Science at the University of Sheffield, UK, where he led the computer vision research team. Between 2004 and 2024, he held professorial and research positions at several renowned European universities, national-level research institutions, and international companies, achieving significant theoretical innovations and technological breakthroughs in dynamic neural networks, multimodal visual perception, brain-inspired machine learning, and large model optimization.

Source: Faculty of Data Science

HomePage_News

CityU hosts AI lecture on challenges and opportunities in multimodal scene understanding

Programs

About CityU

News and Event

Information

Quick Links