Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
HUST Mathematics and Informatics Course Descriptions
Published:
Verified official HUST PDFs for selected courses in my K62 Talent Program transcript.
Converting HUST Credits to ECTS
Published:
A workload-based HUST credit conversion with course-level detail and country-specific ECTS estimates.
portfolio
projects
Poisson Hidden Markov Models for Over-Dispersed Counts
Published:
A thesis-backed implementation of Poisson Hidden Markov Models for discovering latent regimes in over-dispersed count time series.
Graph-Based Epidemic Model Simulation
Published:
A graph-based prototype for representing epidemic relationships, ranking influential cases, and exploring outbreak structure interactively.
Network Model for COVID-19 Risk Evaluation in Vietnam
Published:
A network and random-walk model for turning recent COVID-19 case locations into daily, region-level risk estimates for Vietnam.
Contrastive Viewpoint-Aware Shape Learning for Long-Term Person Re-Identification
Published:
A WACV 2024 project on making person re-identification less dependent on clothing and more sensitive to stable body-shape cues.
Random-Walk Refinement for Dynamic Community Detection
Published:
A RIVF 2025 project extending Dynamic Frontier Louvain with a local random-walk refinement for recovering community splits after graph updates.
Agent Skills: Reusable AI Workflows for Research and R&D
Published:
An open-source library of installable agent skills for research workflows, academic applications, industrial R&D, and structured project setup.
publications
Contrastive viewpoint-aware shape learning for long-term person re-identification
Published in WACV, 2024
CVSL combines 2D pose-based body-shape cues with appearance features and viewpoint-aware contrastive learning for more robust long-term person re-identification.
Recommended citation: V. D. Nguyen, K. Khaldi, D. Nguyen, P. Mantini, and S. Shah, “Contrastive viewpoint-aware shape learning for long-term person re-identification,” in Proc. IEEE/CVF Winter Conf. on Applications of Computer Vision (WACV), 2024, pp. 1041–1049, doi: 10.1109/WACV57701.2024.00108.
Download Paper | Download Bibtex | Code
Improving the DF-Louvain Algorithm through Random Walk-Based Refinement
Published in 2025 RIVF International Conference on Computing and Communication Technologies, 2025
RWGP-DF augments Dynamic Frontier Louvain with a local random-walk refinement that proposes community splits after structural changes and accepts them when modularity improves.
Recommended citation: D. H. Do, D. Nguyen, and T. H. D. Phan, “Improving the DF-Louvain algorithm through random walk-based refinement,” in Proc. 2025 RIVF International Conference on Computing and Communication Technologies (RIVF), Ho Chi Minh City, Vietnam, 2025, pp. 932–937, doi: 10.1109/RIVF68649.2025.11365046.
Download Paper | Code
talks
teaching
Python Data Science and Machine Learning
Teaching Assistant, PlusPlus Academy, 2021
I taught Python data-science and machine-learning libraries, including NumPy, Pandas, Scikit-learn, PyTorch, and TensorFlow, to a class of 15 students. I also guided algorithm implementation and evaluated final machine-learning and computer-vision projects.
