演讲者 | Chong-Wah Ngo | 头衔职位 | 教授,The City University of Hong Kong | 时间 | 2019 年 11 月 26 日(周二)下午 2 点 | 地点 | 软件楼 105 IBM 会议室 | 联系人 | 李析燃,lixiran@fudan.edu.cn |
| |
演讲简介
Machine analysis and understanding of multimedia data has gradually become essential to make sense of everyday activities, social and emotional signals. The goal of multimedia computing is to inform how people perceive, remember and compose multi-modal content, while improving our ability to manage, reason and search information. This talk will share my recent research, particularly the building of multimedia systems for content understanding at the intersection of different media analysis for search and interaction in daily activities. These systems include interactive multimedia search, activity recognition, and food recognition and recipe retrieval. The underlying research addresses the challenges of integrating user behavior understanding and automated content analysis, cross-modal feature representation learning and zero-shot zero-example retrieval in different applications.
关于讲者
Chong-Wah Ngo is a professor in the Dept. of Computer Science at the City University of Hong Kong. He received his PhD in Computer Science from Hong Kong University of Science & Technology, and MSc and BSc, both in Computer Engineering, from Nanyang Technological University, Singapore. Before joining City University of Hong Kong, he was a postdoctoral scholar in Beckman Institute at the University of Illinois in Urbana‐Champaign. His main research interests include multimedia analysis and search, video analytics, and computational wellness. He was the associate editor of IEEE Trans. on Multimedia and is currently steering committee member of TRECVid, ICMR (Int. Conf. on Multimedia Retrieval) and ACM Multimedia Asia. He is program co-chair of ACM Multimedia 2019, Multimedia Modeling 2018, and general co-chair of ICIMCS 2018, PCM 2018 and ICMR 2015. He served as the chairman of ACM (Hong Kong Chapter) during 2008-2009, and was named ACM Distinguished Scientist in 2016 for contributions to video search and semantic understanding.