Research
Deep learning, Vision, AI for Science and Society
My main research area is computer vision—understanding our world using visual data with the help of state-of-the-art deep learning models. I am particularly passionate about understanding objects in diverse and complex environments using images and videos.
I believe A.I. can and should be developed to improve people's quality of life. I am actively collaborating with researchers across disciplines to apply A.I. in scientific discovery, healthcare advancement, and societal challenges, aiming to create meaningful impact beyond traditional computer vision applications.
Publication highlights
A selection of recent and representative publications. For a full, up-to-date list, please see my Google Scholar profile.