Research:
I'm generally interested in understanding how visual perception emerges.
In particular, on topics:
artificial intelligence for science (AI4Science).
learning visual representations from self-supervised training.
multi-modal co-training with visual apperance, motion, audio, textual description, etc.
open-world, object-centric representation learning.
learning visual representation for embodied agents.
|
To Prospective Student:
Make sure you read this document before sending emails.
For PhD applicants, please contact me at least half a year prior to your application.
|
News:
Feb 2024, 6 papers have been accepted by CVPR2024. Congrats to all co-authors !
Feb 2024, 1 papers have been accepted by Journal of the American Medical Informatics Association. Congrats to all co-authors !
Feb 2024, Talks on Multimodal Video Understanding, at Visual Geometry Group (VGG) at University of Oxford.
Dec 2023, invited talks at AI+ Health Conference at Stanford University .
Sep 2023, 2 papers have been accepted by NeurIPS2023. Congrats to all co-authors !
Aug 2023, 2 papers have been accepted by BMVC2023. Congrats to all co-authors !
Aug 2023, 1 papers have been accepted by WACV2023. Congrats to all co-authors !
July 2023, 6 papers have been accepted by ICCV2023. Congrats to all co-authors !
June 2023, 1 paper has been accepted by Nature Communications. Congrats to all co-authors !
June 2023, 1 paper have been accepted by MICCAI2023. Congrats to all co-authors !
June 2023, CVPR2023 Tutorial: Object Localisation for Free, Going Beyond Self-supervised Learning.
May 2023, invited talks at CFAR Rising Star Lecture Series .
Apr 2023, 1 paper has been accepted by ICML2023. Congrats to all co-authors !
Mar 2023, 4 papers have been accepted by CVPR2023. Congrats to all co-authors !
|
|
