Welcome to Yuqian Fu’s homepage

Biography

I am currectly a postdoc researcher at Computer Vision Lab (CVL), ETH Zürich, Switzerland, working with Prof. Luc Van Gool. I received my Ph.D. degree from School of Computer Science, Fudan University, China, advised by Prof. Yu-Gang Jiang, co-advised by Prof. Yanwei Fu, and Associate Professor Jingjing Chen, in June 2023. Before that, I received my bachelor’s degree in computer science from Zhejiang University of Technology, China, supervised by Associate Professor Cong Bai, in June 2018.

My research topics are computer vision and deep learning. I mainly focus on few-shot learning, especially cross-domain few-shot learning, and few-shot video action recognition. I am also open and willing to explore other 2D vision tasks, e.g., continual learning, prompt learning, domain adaptation/generalization. If you are interested in my topics, please do not hestitae to reach out.

News

[09/2023] I joined CVL lab at ETH Zürich.
[07/2023] One paper is accepted by ACM MM 2023.
[06/2023] I have earned a doctoral degree.
[04/2023] I have received 100 citations!
[02/2023] One paper is accepted by CVPR2023.
[10/2022] One paper is accepted by TIP.
[06/2022] Two papers are accepted by ACM MM 2022.
[12/2021] I am recognized as an outstanding student of Fudan University.
[06/2021] One paper is accepted by ACM MM 2021.
[04/2021] One paper is accepted by ICMR 2021.
[07/2020] One paper is accepted by ACM MM 2020.
[12/2019] I am awarded the Chinese National Scholarship.
[07/2019] One paper is accepted by ACM MM 2019.
[09/2018] I joined FVL lab at Fudan University.

Publications

	StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learning Yuqian Fu, Yu Xie, Yanwei Fu, Yu-Gang Jiang IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 [Paper][Code][Youtube Video][Bilibili Video][Project Page]

	Generalized Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data Yuqian Fu, Yanwei Fu, Jingjing Chen, Yu-Gang Jiang IEEE Transactions on Image Processinig (TIP), 2022. [Paper]

	ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning Yuqian Fu, Yu Xie, Yanwei Fu, Jingjing Chen, Yu-Gang Jiang ACM International Conference on Multimedia (ACM MM), 2022. [Paper][Code][Youtube Video][Bilibili Video]

	TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learning Linhai Zhuo, Yuqian Fu, Jingjing Chen, Yixin Cao, Yu-Gang Jiang ACM International Conference on Multimedia (ACM MM), 2022. [Paper]

	Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learning Yuqian Fu, Yu Xie, Yanwei Fu, Jingjing Chen, Yu-Gang Jiang arXiv preprint, 2022. [Paper][Code]

	Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data Yuqian Fu, Yanwei Fu, Yu-Gang Jiang ACM International Conference on Multimedia (ACM MM), 2021. [Paper][Code][Youtube Video][Bilibili Video][Project Page]

	Can Action be Imitated? Learn to Reconstruct and Transfer Human Dynamics from Videos Yuqian Fu, Yanwei Fu, Yu-Gang Jiang International Conference on Multimedia Retrieval (ICMR). 2021. (Oral) [Paper][Bilibili Video]

	Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition Yuqian Fu, Li Zhang, Junke Wang, Yanwei Fu, Yu-Gang Jiang ACM International Conference on Multimedia (ACM MM), 2020. (Oral) [Paper][Code][Youtube Video][Bilibili Video][Project Page]

	Embodied One-Shot Video Recognition: Learning from Actions of a Virtual Embodied Agent Yuqian Fu, Chengrong Wang, Yanwei Fu, Yu-Xiong Wang, Cong Bai, Xiangyang Xue, Yu-Gang Jiang ACM International Conference on Multimedia (ACM MM), 2019. (Oral) [Paper][Code][UnrealAction Dataset]