Zhiyuan You (尤志远)

I am a second-year first-year Ph.D. student of the joint program between MMLab, The Chinese University of Hong Kong (CUHK) and MMLab, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences (SIAT). I am supervised by Prof. Chao Dong and Prof. Tianfan Xue. I also work closely with Dr. Jinjin Gu.

Prior to that, I received my M.Eng. from Shanghai Jiao Tong University (SJTU) in 2023, supervised by Prof. Xinyi Le and Prof. Yu Zheng, and my B.Eng. from the same university in 2020. I spent a wonderful time in Horizon Robotics and SenseTime as a research intern, mentored by Dr. Yuelong Yu and Mr. Kai Yang, respectively.

My current research interest mainly lies in multi-modality vision for low-level vision, anomaly detection, few-shot learning, and industrial visual inspection.

CV  /  Google Scholar  /  Github
Email: zhiyuanyou [at] foxmail [dot] com

[2024.07]    One paper to appear in ECCV 2024. See you in Milan.

[2023.08]    I become a Ph.D. student at MMLab in The Chinese University of Hong Kong.

*: Equal Contribution, †: Corresponding Author

We introduce DepictQA-Wild, a multi-functional in-the-wild descriptive image quality assessment model.

We release MaskMA, a masked pretraining framework for multi-agent decision-making.

We introduce DepictQA, leveraging Multi-modal Large Language Models, allowing for detailed, language-based, and human-like evaluation of image quality.

We propose a novel SAFECount block, equipped with a similarity comparison module and a feature enhancement module for few-shot object counting.

We present UniAD that accomplishes anomaly detection for multiple classes with a unified framework.

We propose ADTR to apply a transformer to reconstruct pre-trained features for anomaly detection, and propose novel losses to extend ADTR to anomaly-available case (both image-level & pixel-level labeled).

We introduce UTRAD, a U-TRansformer based Anomaly Detection framework.

Template from JonBarron