Quan Nguyen Minh

I am a master student in Biomedical Computing at Technical University of Munich (TUM), where I learn to combine computer science with healthcare.

I received my Bachelor Degree in Biomedical Engineering and in Computer Science at Hanoi University of Science and Technology in 2021 and 2022, respectively.

During my time as an undergraduate, I worked as an intern at Viettel High Tech where I develop Computer Vision Algorithms for smart camera systems, including People detection and Heatmap Visualization using Fisheye Camera for retail stores, face recognition algorithm for Edge devices and high speed traffic AI Camera. I also worked as a full-time Research Assistant at VinUni-Illinois Smart Health Center (VishC), a joint center between VinUni and the College of Engineering, University of Illinois at Urbana-Champaign . My research focus at VishC is federated learning for healthcare.

Currently, I am a working student at Luma Vision GmbH, working on cutting-edge ultrasound imaging technologies. I am also writing on my thesis on the impact of differential privacy on the fairness of AI algorithms at Lab for AI in Medicine at TU Munich and Siemens Healthineers .

Email  /  CV  /  Google Scholar  /  Github

I am passionate about trusworthy AI and AI in Medicine. Representative papers are highlighted.

We propose FedDCT (Federated Divide and Collaborative Training), a novel FL architecture that allows for DCML with considerably lower client memory requirements over traditional FL while introducing no additional training cost on the central server. FedDCT enables a cluster of several clients to cooperatively train a large deep learning model, in contrast to standard FL, which demands that each client train the full-size neural network independently during each training round.

Inspired by the human visual system, which only focuses on the non-occluded facial regions, we propose a novel Switching Re-placement Attention Network (SRAN) for robust face recognition based on attention mechanism.

In this work, we propose ARPD, a single-stage anchor-free fully convolutional network to detect arbitrarily rotated people in fish-eye images. Our network uses keypoint estimation to find the center point of each object and regress the object's other properties directly. To capture the various orientation of people in fish-eye cameras, in addition to the center and size, ARPD also predicts the angle of each bounding box.

The aim of this work is to incorporate the de-warping of fisheye image using polar to Cartesian transformation to generate a panoramic view to aid in fall detection.

●   [Nov 2023]   8.5 IELTS ( 9.0 R, 9.0 L, 7.5 W, 8.0 S)
●   [April. 2021]   985 TOEIC
●   [April. 2015]   Completed basic German Course (A2.2) at Goethe Institut.

●   [Jun. 2024]   I am working on my thesis at Lab for AI Medicine at TU Munich and Siemens Healthineers.

●   [Jun. 2024]   One paper (second author) is accepted to IEEE Ultrasonics, Ferroelectrics, and Frequency Control Joint Symposium.

●   [Sep. 2023]   I participated in SUMMER SCHOOL ON “MODERN MACHINE LEARNING: FOUNDATIONS AND APPLICATIONS” in Ninh Binh, Vietnam.

●   [Aug. 2023]   One paper (first author) FedDCT: A Novel Federated Learning Approach for Training Large Convolutional Neural Networks on Resource-constrained Devices is accepted to IEEE Transactions on Network and Service management.

●   [Aug. 2022]   I participated in 9th Vietnam Summer School of Science at Quy Nhon, Vietnam. The scholarship is to inspire and support young Vietnamese generations who are potential and keen as well as full of passions on pursuing research as a career.

●   [July. 2022]   I serve as the organizer for the First VinUni-Illinois Smart Health Center Workshop and VinUni-Illinois Smart Health Center | Pre-PhD Summer School 2022 .

●   [Feb. 2022]   I started working at Teaching Assistant for course COMP1020: OOP & Data Structures at Vin University, taught by Prof. Hieu Pham and Prof. Kok Seng.

●   [Jan. 2022]   I joined VinUni-Illinois Smart Health Center as Research Assistant under supervison of Prof. Hieu Pham and Prof. Kok Seng Wong. My research focus is on federated learning for healthcare. My work is a part of VAIPE project: AI-assisted IoT-enabled smart, optimal, and Protective Healthcare monitoring and supporting system for Vietnamese.

●   [December. 2021]   One paper "Occlusion Robust Face Recognition Based on Mask Learning With Attention Mechanism" got accepted to International Conference on Intelligent Systems & Networks (ICISN 2022).

●   [October. 2021]   One paper (first author) ARPD: Anchor-free Rotation-aware People Detection using Topview Fisheye Camera got accepted to 17th IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS 2021).

●   [September. 2021]   Our submission viettelhightech_000 for the FRVT 1:1 Vendor Test achieved the good results among all Vietnamese clients

●   [June. 2021]   Our group at Biosignal and Medical Image Analysis Lab achieved third prize in Hanoi University of Science and Technology Student's Academic Research Contest (University level)

●   [2020]   I achieved HUST Academic Incentive Scholarship for students with excellent academic results in semester 2020-2.

●   [Nov. 2019]   I became a member of cohort 20 of FPT Young Talents (FYT). FYT is a special educational organization founded in 1999 by the then-CEO of FPT Corporation : Truong Gia Binh aiming to nurture the young talents of Vietnam.

●   [Sep. 2018]   I was one of 25 HUST's students chosen to participate in a 3-weeks leadership exchange program TFI Scale at Temasek Polytechnic, Singapore. Fully sponsored by the Temasek Foundation.

This repository contains the code and experiments for the paper FedDCT:Federated Divide and Collaborative Training, accepted to IEEE Transactions on Network and Service Management
Github

I worked in a team with other engineers from VHT to design face recogntion algorithms to participate in NIST FRVT 1:1 Verification Test. NIST provides independent evaluations of commercially available and prototype face recognition technologies. Our submission achieved respectable results.

I reimplemented the famous SORT tracking algorithm from scratch in Java using only OpenCV. Was a fun project to code and i applied this for tracking Vehicle on edge devices.
Github

I redesigned the classic Mobilenet-SSD network to reduce FLOPS and Params while keeping good accuracy. I pruned the backbone manually, modify the feature map size and anchor configs. The detector achieves 30 FPS on Intel CPU while keeping respectable accuracy.
Github

This collection of Python code provides implementations for various analytical tomographic image reconstruction algorithms. These algorithms play a crucial role in transforming projection data into detailed images, making them valuable tools in medical imaging, materials science, and more. Included are Fourier Gridding, Backproject Filter, Filtered Backprojection and Convolve Backproject
Github

I’m a passionate rock and heavy metal fan with a wide range of musical interests, from the classic sounds of the '70s (think Pink Floyd, Led Zeppelin, KISS, ...) to the iconic '80s (Van Halen, Guns N' Roses, Mötley Crüe, ...) and '90s (Nirvana, Green Day). I even dig into some newer bands like My Chemical Romance and Paramore.

I also play bass guitar. If you’re interested in teaming up to bring some classic tunes to life, feel free to reach out!. Don't expect me to do much improvising though. I mean, i'm no Joe Walsh in the brain department (yes, that's a The Simpsons reference).

I have loved playing Yu-gi-Oh ever since i was a kid. Dropped it for a few years during college but started picking up again. Recently i have been picking up Warhammer 40k as well.

Well, who doesn't love traveling and enjoying new culture. Ever since i moved to Germany, i have started to enjoy going on hikes as well, especially in the mountains.