The School of EECS is hosting the following HDR Progress Review 1 Confirmation Seminar:
Effective Visual Data Compression
Speaker: Zhuojie Wu
Host/Chair: Prof Xue Li
Abstract
The success of modern computer vision relies heavily on the availability of high-quality, large-scale datasets. However, storing and transmitting such datasets poses significant challenges, and training deep models on them incurs substantial computational cost. Consequently, effective visual data compression is becoming an increasingly important research topic.
Existing visual data compression methods often rely on computationally intensive models or make idealized assumptions about data quality. These limitations hinder their practicality, particularly when dealing with large-scale datasets or deploying models in resource-constrained environments. Our goal is to develop a unified visual data compression framework that enables efficient storage and transmission of data, while also supporting robust and effective training and inference.
Bio
Zhuojie Wu is a second-year Ph.D. student at the School of EECS, University of Queensland, under the supervision of Dr Xin Yu and A/Prof Sen Wang. His research centres on data compression.
About Data Science Seminar
This seminar series is hosted by EECS Data Science.
Venue
Online: https://uqz.zoom.us/j/87014128210