Zhaoying Pan


I am a second-year PhD student in Electrical and Computer Engineering at Purdue University, advised by Prof. Xiaoqian Wang.

Prior to that, I worked with Prof. Andrew Owens and Daniel Geng during my master's program. Earlier, I collaborated with Jinge Ma and Yutong Xie on an explorative project, advised by Prof. Qiaozhu Mei. Before my master's program, I received my Bachelor of Engineering in Electronic and Information Engineering, from University of Chinese Academy of Sciences. During my bachelor's study, I worked with Zhiqiang Yuan under the supervision of Prof. Kun Fu and Prof. Xian Sun. I'm thankful for the invaluable experiences and collaborative insights gained while working with exceptional researchers.

I'm currently working on distribution shift. I'm also interested in computer vision and machine learning, and their applications to other areas. I'm open to new areas as well, and feel free to reach out for potential collaborations.

Email: zhaoyingpan AT purdue DOT edu

Google Scholar Github LinkedIn Twitter

Profile picture

Education

UCAS
Purdue University 2023-present
Doctor of Philosophy in Electrical and Computer Engineering
Advisor: Prof. Xiaoqian Wang
UM
University of Michigan2021-2023
Master of Science in Electrical and Computer Engineering
Specialization: Computer Vision
Advisor: Prof. Andrew Owens
UCAS
University of Chinese Academy of Sciences 2017-2021
Bachelor of Engineering in Electronic and Information Engineering
Thesis: Image Caption Generating of High-Resolution Remote Sensing Images. (Bachelor’s Thesis with Honors)
Advisor: Prof. Kun Fu and Prof. Xian Sun

Publications

Project image
Self-Supervised Motion Magnification by Backpropagating Through Optical Flow
Zhaoying Pan*, Daniel Geng*, Andrew Owens. (equal contribution)
The Conference on Neural Information Processing Systems (NeurIPS), 2023
Paper / Code / Website /
@inproceedings{pan2023selfsupervised,
        title={Self-Supervised Motion Magnification by Backpropagating Through Optical Flow},
        author={Zhaoying Pan and Daniel Geng and Andrew Owens},
        booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
        year={2023},
        url={https://arxiv.org/abs/2311.17056}
}

We present a method to magnify subtle motion that can be trained without groundtruth magnified videos. Furthermore, our method is flexible to allow users only magnify specific area, or overfit on a single video for better performance.
Project image
A Prompt Log Analysis of Text-to-Image Generation Systems
Yutong Xie*, Zhaoying Pan*, Jinge Ma*, Luo Jie, Qiaozhu Mei. (equal contribution)
The ACM Web Conference (WWW), The Creative Web Track, 2023
Paper / Code /
@article{xie2023prompt,
        title={A Prompt Log Analysis of Text-to-Image Generation Systems},
        author={Xie, Yutong and Pan, Zhaoying and Ma, Jinge and Luo, Jie and Mei, Qiaozhu},
        journal={arXiv preprint arXiv:2303.04587},
        year={2023}
}

We explored the large-scale prompt logs collected from multiple text-to-image generation systems to investigate the information needs, and provided concrete implications on how to improve text-to-image generation systems for creation purposes.
Project image
Learning to Evaluate Performance of Multi-modal Semantic Localization
Zhiqiang Yuan, Wenkai Zhang, Chongyang Li, Zhaoying Pan, Jialiang Chen, Yongqiang Mao, Shuoke Li, Hongqi Li, Xian Sun.
IEEE Transactions on Geoscience and Remote Sensing, 2022
Paper / Code /
@article{yuan2022learning,
        title={Learning to Evaluate Performance of Multi-modal Semantic Localization},
        author={Yuan, Zhiqiang and Zhang, Wenkai and Li, Chongyang and Pan, Zhaoying and Mao, Yongqiang and Chen, Jialiang and Li, Shouke and Wang, Hongqi and Sun, Xian},
        journal={arXiv preprint arXiv:2209.06515},
        year={2022}
}

We contributed test sets, evaluation metrics and baselines for evaluation of Semantic Localization (SeLo) tasks, and provided a detailed demo to use this evaluation framework.
Project image
Diffusion Model with Detail Complement for Super-resolution of Remote Sensing
Jinzhe Liu, Zhiqiang Yuan, Zhaoying Pan, Yiqun Fu, Li Liu, Bin Lu.
Remote Sensing, 2022
Paper /
@article{liu2022diffusion,
    title={Diffusion Model with Detail Complement for Super-Resolution of Remote Sensing},
    author={Liu, Jinzhe and Yuan, Zhiqiang and Pan, Zhaoying and Fu, Yiqun and Liu, Li and Lu, Bin},
    journal={Remote Sensing},
    volume={14},
    number={19},
    pages={4834},
    year={2022},
    publisher={MDPI}
}

We proposed the Diffusion Model with Detail Complement (DMDC) for the super-resolution task on remote sensing images.

Projects

  • The Evolution of AI and Data Mining: We analyzed computer science papers over half a century and revealed the evolution of domains by examining how the distribution changes over time. Check the video.

Teaching Experience

  • 24 Fall: ECE 570 Artificial Intelligence, Graduate Teaching Assistant Purdue University
  • 24 Spring: ECE 264 Advanced C Programming, Graduate Teaching Assistant Purdue University
  • 23 Fall: ECE 264 Advanced C Programming, Graduate Teaching Assistant Purdue University