Department of Computer Science HKBU
Invited Talk

Open-world Visual Learning and Its Applications

Prof. Mang Ye

School of Computer Science
Wuhan University

Title: Open-world Visual Learning and Its Applications
Date & Time: 09:00, 18 June 2021
Zoom link:

With the advancement of deep learning, significant achievements have been obtained in various visual learning applications. However, they usually rely on the assumption: extensive well-annotated training data, the data annotations are clean and the data are collected from the same modality, while these assumptions are hard to satisfied in many practical open-world scenarios. In this talk, I will introduce my research works on open-world visual learning and its applications from the following three aspects: (1) unsupervised learning from large-scale unlabeled data; (2) robust deep learning from noisy data; (3) cross-modality matching from multi-modality data. Finally, I will discuss several future directions in this challenging but promising area.


Mang Ye is currently a Full Professor at the School of Computer Science, Wuhan University. He received the PhD degree from Hong Kong Baptist University in 2019, supported by Hong Kong PhD Fellowship. He received the B.Sc and M.Sc degrees from Wuhan University in 2013 and 2016. He worked as a Research Scientist at Inception Institute of Artificial Intelligence from 2019-2020 and worked as a Visiting Scholar at Columbia University in 2018. He has published more than 50 papers, including 18 CCF-A/IEEE Trans. papers as the first/corresponding author. He received 1800+ citations, including those from 2 Turing awardees (Geoffrey Hinton and Yann Lecun). Five papers are ESI Highly Cited. His research interests include open-world visual learning and its applications in multimedia analysis, person re-identification and etc.