When Visual Scene Understanding Meets Deep Learning and Big Data

Date: 2 March 2022 (Wednesday)
Time: 6-7pm
Venue: Zoom Meeting
Title: When Visual Scene Understanding Meets Deep Learning and Big Data
Speaker: Dr. Dan Xu, CSE

Abstract:

This talk will give an introduction to 2D and 3D visual scene understanding which is a fundamental and core research field in computer vision and also for various realistic application domains, such as self-driving, robotics, and AR/VR. The talk will present the current achievements and challenges on different important tasks for 2D and 3D visual scene understanding, with a particular focus on how deep learning and big data help to significantly boost the performance of these different tasks, and what promising research directions we could further explore to advance the performance level of this field.

Speaker Bio:

Dr. Dan Xu is an Assistant Professor in the Department of Computer Science and Engineering (CSE), Hong Kong University of Science and Technology (HKUST). Before joining HKUST, he was a postdoctoral researcher in the Visual Geometry Group (VGG) in the Department of Engineering Science at the University of Oxford. He received his Ph.D. in Computer Science from the University of Trento in 2018. He was also a visiting Ph.D. student in the MM lab at the Chinese University of Hong Kong (CUHK). His research mainly focuses on computer vision, multimedia, and deep learning. He served as Senior Programme Committee (SPC) / Area Chair (AC) at multiple international conferences including AAAI, ACM Multimedia, WACV, and ACCV. He received the Best Scientific Paper Award at ICPR 2016 and a Best Paper Nominee at ACM Multimedia 2018.