Abstract

Talk Abstract:

Discover how we’re rethinking change detection in remote sensing! Traditional methods often categorize changes—like “forest to urban”—but what about subtle or complex transformations that don’t fit neatly into predefined labels? In this talk, we’ll explore groundbreaking research that moves beyond these boundaries by leveraging self-supervised learning. Learn how contrastive learning aligns features from various sensors and time periods to detect nuanced changes, overcoming challenges like seasonal variations or sensor differences. This innovative approach enhances our ability to monitor Earth’s surface and respond to changes with greater accuracy. Join us to see how this research transforms our understanding of the world!

Speaker Bio:

Yuxing Chen received his M.S. degree in Geodesy and Surveying Engineering from the University of Chinese Academy of Sciences, Beijing, China, in 2019, and a Ph.D. cum laude in Information and Communication Technology from the University of Trento, Italy, in 2023. He is currently a postdoctoral researcher at the University Paris Cité. Yuxing’s research interests include remote sensing image feature representation, in-context learning, and automating remote sensing data analysis using large language models. His work bridges the gap between traditional remote sensing methods and cutting-edge machine learning, offering new tools to understand and analyze Earth’s surface.

Join Zoom Meeting

https://cam-ac-uk.zoom.us/j/88230088472?pwd=dXhkeWJVL3lHVGRERUtwL3BOK1dPUT09

Meeting ID: 882 3008 8472

Passcode: 685305