Huy Anh Nguyen
Education
- Member of Be and Beyond Visual Intelligence Lab and Computer Vision Lab
- Advisor (M.Sc. and Ph.D.): Prof. Minh Hoai, Co-advisor Assoc. Prof. Feras Dayoub
- Thesis: Hand-held Object Segmentation and Tracking
- Thesis: New Classes of Operators and De Morgan Triples in Picture Fuzzy Set
- Advisor: Prof. Dr. Sc. Bui Cong Cuong
Research Interests
| Computer Vision | Egocentric Video Understanding, Temporal Action/Event Detection, Hand-Object Interaction, Video Object Segmentation (VOS) |
| Machine Learning | Representation Learning, Self-Supervised Learning |
Research Experience
- Temporally Precise Hand Touch Detection: Developing algorithms and datasets to spot and localize hand–object touch events in egocentric videos with tight temporal tolerances. Published at CVPR Findings 2026.
- Hand-held Object Identification, Segmentation, and Tracking: Processed and curated the Epic-Kitchens VISOR dataset for hand-held object segmentation and tracking. Developed a VOS method improving upon STCN with a novel contact region loss. The dataset pipeline, contact region loss, and comprehensive evaluation of competing methods contributed to HOIST-Former, published at CVPR 2024.
- Adaptive and Interactive AI-AR Task Assistance (Funded by DARPA): Developed Unity and ROS plugins for data streaming from HoloLens 2, with a rospy client achieving 12 fps for RGB and 5 fps for Depth streams with 200–400ms latency. The system feeds data into action, hand, and active object recognition modules. Also developed hand-object segmentation, tracking, and distance estimation models using synchronized RGB-D frames.
- Visual Attention: Toward an Attentional Toolkit (Funded by NSF): Developed a multi-device synchronized data collection system integrating a webcam, screen recording, and eye-gaze video from a GP3 tracker, achieving sub-120ms latency across all streams for accurate gaze-action alignment in cognitive science research.
- Fuzzy Logic Research: Proved De Morgan triples and constructed new classes of picture fuzzy negation operators. Presented findings at National Mathematical Conference (2018).
Publications & Presentations
[1] Huy Anh Nguyen, Feras Dayoub, Minh Hoai, "Detecting Precise Hand Touch Moments in Egocentric Video", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings, 2026. (To appear)
[2] Huy Vu, Huy Anh Nguyen, Adithya V Ganesan, Swanie Juhng, Oscar NE Kjell, Joao Sedoc, Margaret L Kern, Ryan L Boyd, Lyle Ungar, H Andrew Schwartz, Johannes C Eichstaedt, "PsychAdapter: Adapting LLMs to Reflect Traits, Personality, and Mental Health", npj Artificial Intelligence, 2026.
[3] Supreeth Narasimhaswamy, Huy Anh Nguyen, Lihan Huang, Minh Hoai, "HOIST-Former: Hand-held Objects Identification, Segmentation, and Tracking in the Wild", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
[4] Nguyen Thanh Binh, Huy Anh Nguyen, Pham Ngoc Linh, Nguyen Linh Giang, Tran Ngoc Thang, "Attentive RNN for HS Code Hierarchy Classification on Vietnamese Goods Declaration", International Conference on Intelligent System and Network (ICISN), 2021.
[5] Nguyen Huy Anh, Roan Thi Ngan, Bui Cong Cuong, "Some new classes of Picture Fuzzy negation and De Morgan triples", 9th Vietnam Mathematical Congress, Oral presentation in Discrete mathematics section, Nha Trang, Vietnam, 2018.
Work Experience
- Researched and developed Japanese image captioning models for stock images. Deployed BERTCap with ResNeST backbone into production at under 0.65s per image using ONNX.
- Developed a hierarchical classifier for HS Code prediction (68.9% full code, 95% chapter/heading accuracy) on 2TB+ customs data, published at ICISN 2021.
- Developed algorithmic models ('alphas') to predict stock market movements, utilizing 25 datasets. Gold medal in WorldQuant Challenge (global - 2018).
Teaching & Mentorship
- Mentored 2 undergraduate students in Summer Research at University of Adelaide (Summer 2024/25).
- Mentored student groups on final projects in CSE519 Data Science Fundamentals (Fall 2023).
- Teaching Assistant: CSE353 Machine Learning (Fall 2021), CSE519 Data Science Fundamentals (Fall 2023), CSE538 Natural Language Processing (Spring 2024).
Awards & Scholarships
Skills
| Languages | Python, SQL, C++, C#, Java |
| Tools/ Frameworks | PyTorch, Numpy, Pandas, TensorFlow/Keras, Scikit-learn, Git, ROS, FreeFEM, Linux, Hadoop/Spark, FastAPI, ONNX, Docker |