Hui Lin (林惠)

2479 E Bayshore Rd

Palo Alto, CA 94303

#Senior Research Scientist at OPPO

Currently, I am working on representation learning and scalable AI infrastructure at the OPPO US Research Center . My work bridges the gap between complex algorithmic research and production-grade systems, focusing on architecting highly efficient deep learning pipelines to extract predictive metrics from highly constrained hardware (such as single-channel wrist PPG signals). I also contribute to the deployment of MLOps batch pipelines (Spark/Hive) to optimize multi-stage ranking algorithms for large-scale recommendation engines.

I recently completed my Ph.D. at the iVPL lab at Northwestern University, supervised by Prof. Aggelos Katsaggelos and Prof. Daniel Kim. My research concentrated on computer vision and sequential time-series analysis , specifically designing self-attention models, YOLO localization pipelines, and unsupervised domain adaptation (UDA) frameworks for high-resolution spatial imaging.

Throughout my career, my focus has been on resolving long-tail data imbalances and designing robust validation strategies. This work has led to 13 first-author papers, 1,150+ citations, and multiple Top-5 global algorithm rankings (MICCAI/ISBI) . I am highly proficient in deploying production infrastructure alongside complex architectures, including Transformers, GANs, GNNs, and ResNets.

Previously, I obtained a Master’s degree in Mechanical Engineering from Huazhong University of Science and Technology (HUST) in 2019, supervised by Prof. Bin Li and Prof. Xinggang Wang, and a Bachelor’s degree in Materials Processing and Control Engineering from Qiming College, HUST, in 2016.

Short resume

news

Apr 15, 2026	Our paper Gyroformer: Capturing 3D rotational BCG dynamics for cuffless hypertension risk screening has been accepted by EMBC 2026 !🎉 Stay tuned for more updates!
Sep 14, 2025	Our paper Drl-Stnet⁺⁺ Uncertainty-Aware Self-Training For Cross-Modality Segmentation With Generative Translation has been accepted by ICIP workshop 2026 !🎉 Stay tuned for more updates!
May 1, 2025	I am starting a full-time position at the OPPO US Research Center, focusing on wrist PPG analysis for reliable hypertension risk screening.
Feb 24, 2025	I am currently working as a Machine Learning Engineer intern at the OPPO US Research Center, contributing to the design of recommendation systems.
Dec 20, 2024	My work ( paper ) during the summer internship 2025 on analyzing wrist-collected PPG data for continuous hypertension risk screening has been accepted for presentation at ICASSP 2025 ! 🎉 Stay tuned for more updates!

selected publications

2025

ICASSP

Longitudinal Wrist PPG Analysis for Reliable Hypertension Risk Screening Using Deep Learning

Hui Lin, Jiyang Li, Ramy Hussein, and 6 more authors

ICASSP 2025, 2025

Bib

@article{lin2024longitudinal,
  title = {Longitudinal Wrist PPG Analysis for Reliable Hypertension Risk Screening Using Deep Learning},
  author = {Lin, Hui and Li, Jiyang and Hussein, Ramy and Sui, Xin and Li, Xiaoyu and Zhu, Guangpu and Katsaggelos, Aggelos K and Zeng, Zijing and Li, Yelei},
  journal = {ICASSP 2025},
  volume = {12},
  year = {2025},
}

2024

Usformer: A small network for left atrium segmentation of 3D LGE MRI

Hui Lin, Santiago López-Tapia, Florian Schiffers, and 8 more authors

Heliyon, 2024

Bib Slides

@article{lin2024usformer,
  title = {Usformer: A small network for left atrium segmentation of 3D LGE MRI},
  author = {Lin, Hui and L{\'o}pez-Tapia, Santiago and Schiffers, Florian and Wu, Yunan and Gunasekaran, Suvai and Hwang, Julia and Bishara, Dima and Kholmovski, Eugene and Elbaz, Mohammed and Passman, Rod S and others},
  journal = {Heliyon},
  volume = {10},
  number = {7},
  year = {2024},
  publisher = {Elsevier},
  video = {https://www.youtube.com/watch?v=4Mu5rgfUwoE},
  google_scholar_id = {QyVjEncAAAAJ}
}

2023

MICAAI Chall.

StenUNet: Automatic Stenosis Detection from X-ray Coronary Angiography

Hui Lin, Tom Liu, Aggelos Katsaggelos, and 1 more author

arXiv preprint arXiv:2310.14961, 2023

Bib

@article{lin2023stenunet,
  title = {StenUNet: Automatic Stenosis Detection from X-ray Coronary Angiography},
  author = {Lin, Hui and Liu, Tom and Katsaggelos, Aggelos and Kline, Adrienne},
  journal = {arXiv preprint arXiv:2310.14961},
  year = {2023},
}

2020

IEEE TASE

Defect image sample generation with GAN for improving defect recognition

Shuanlong Niu, Bin Li, Xinggang Wang, and 1 more author

IEEE Transactions on Automation Science and Engineering, 2020

Bib

@article{niu2020defect,
  title = {Defect image sample generation with GAN for improving defect recognition},
  author = {Niu, Shuanlong and Li, Bin and Wang, Xinggang and Lin, Hui},
  journal = {IEEE Transactions on Automation Science and Engineering},
  volume = {17},
  number = {3},
  pages = {1611--1622},
  year = {2020},
  publisher = {IEEE},
  dimensions = {true},
}

2019

J. Intell. Manuf.

Automated defect inspection of LED chip using deep convolutional neural network

Hui Lin, Bin Li, Xinggang Wang, and 2 more authors

Journal of Intelligent Manufacturing, 2019

Bib

@article{lin2019automated,
  title = {Automated defect inspection of LED chip using deep convolutional neural network},
  author = {Lin, Hui and Li, Bin and Wang, Xinggang and Shu, Yufeng and Niu, Shuanglong},
  journal = {Journal of Intelligent Manufacturing},
  volume = {30},
  pages = {2525--2534},
  year = {2019},
  publisher = {Springer},
  dimensions = {true},
}