Our goal is to make the computer better perceive the real world like humans using computer vision and machine learning techniques. For computer vision, we are interested in developing accurate and efficient solutions for the basic recognition tasks, e.g., classification, object detection, pixel-level understanding (e.g., semantic segmentation, instance segmentation, class-agnostic segmentation, matting) for images/videos. For machine learning, we are interested in developing data-efficient algorithms for training models with imperfect or incomplete data, including unsupervised learning, weakly supervised learning, semi-supervised learning, few-shot learning, domain adaptive learning, active learning etc. Recently, we are growingly interested in applying multi-modality pre-training techniques for tackling vision & language problems, e.g., cross-media retrieval, referring recognition, open-world recognition, etc.
Thanks for your interest in joining my group! We always have openings for outstanding students. Interested candidates for Master/PhD opportunities are strongly encouraged to contact me by email. Please attach your CV, and clearly discuss your research interests, coding skills and English ability. Besides, we are alway open to working with outstanding BJTU undergraduates for some research projects, and you are welcome to my office to have a discussion. We provide extraordinarily strong support to students for internship, visiting, collaboration, and networking opportunities. We encourage you to talk with current members in our group for more details.
Before joining BJTU, he was a Senior Lecturer of ReLER Lab at the University of Technology Sydney from 2019 to 2021. He was a Postdoctoral Researcher of IFP group at UIUC from 2017 to 2019, working with Prof. Thomas S. Huang, and a Postdoctoral Researcher of National University of Singapore from 2016 to 2017, working with Prof. Jiashi Feng and Prof. Shuicheng Yan. He received his Ph.D. degree from Beijing Jiaotong University in 2016, advised by Prof. Yao Zhao. He was selected as MIT TR35 China by MIT Technology Review in 2021 and was named as one of the five top early-career researchers in Engineering and Computer Sciences in Australia by The Australian in 2020. He received the Discovery Early Career Researcher Award of the Australian Research Council in 2019, the 1st Prize in Science and Technology awarded by China Society of Image and Graphics (CSIG) in 2019. He has published more than 80 papers in top-tier conferences/journals, Google citations 8700+. He received many competition prizes from CVPR/ICCV/ECCV, such as the Winner prizes of ILSVRC 2014, LIP 2018/2019, Youtube VOS 2021, Runner-up Prizes of ILSVRC 2017, DAVIS 2020, etc. He organized many workshops on top-tier conferences, including Learning from Imperfect Data Workshop series (CVPR 2019, 2020, 2021) and Real-world Recognition from Low-quality Inputs Workshop series (ICCV 2019, ECCV 2020). He has broad research interests in computer vision and machine learning. His current research interest focuses on visual recognition with imperfect data, image/video segmentation and object detection, and multi-modal perception.