Visual Artificial Intelligence
Visual Artificial Intelligence
Visual Artificial Intelligence
Visual Artificial Intelligence

About Us

Generalized Category Discovery:
A new and realistic open-world problem.
JIFF reconstructs the 3D human model from a single image with detailed face geometry.
Open-Set Recognition: a Good Closed-set Classifier is All You Need?

Visual Artificial Intelligence Lab (VAiL) is a research group working on computer vision, deep learning, and machine learning, under Department of Statistics and Actuarial Science, The University of Hong Kong, directed by Dr. Kai Han. Our goal is to achieve principled and comprehensive visual understanding for real applications of artificial intelligent systems. Our recent research focuses on open-world learning, general representation learning, 3D vision and their relevant fileds, spanning topics like generalized/novel category discovery, open-set recognition, out-of-distribution detection, multimodal learning, foundation models, vision-language models, learning from limited data, semi-supervised learning, long-tailed learning, visual correspondence, 3D reconstruction (object/human/scene), image matting, photometric stereo, etc.

(1) We are always looking for strong PhD students to work on exciting computer vision research problems (☞ fellowships and scholarships) -- 2023 intake applications on-going.
(2) Postdoc positions in computer vision and deep learning are available, with a competitive salary.
(3) Summer Research Programme 2023 is now open for application (deadline: Jan 27, 2023 ☞ more more details), with the possiblity of conditional PhD offer of 2024 intake with HKU-PS scholarship.
Please drop Dr. Kai Han an email with your resume if you are interested in working with us.

News and Updates

Jul 2022:

One paper on novel category discovery without forgetting is accepted to ECCV 2022.
Jun 2022:

Best Paper Runner-Up Award at CVPR 2022 Workshop on Continual Learning in Computer Vision.
Mar 2022:

Three papers (about generalized category discovery/3D human reconstruction/instance segmentation) are accepted to CVPR 2022.
Jan 2022:

One paper about open-set recognition is accepted to ICLR 2022.
Oct 2021:

One paper about visual correspondence is accepted to BMVC 2021.
Sep 2021:

One paper about novel category discovery is accepted to NeurIPS 2021.