About me 🌱
date
Mar 13, 2021
slug
about
status
Published
tags
summary
My name is Vo Thanh Hoang Son, who is an AI researcher right now. This is my information, let’s reach it out.
(AI Engineer, Data Science, Ho Chi Minh City, Machine Learning, LLM)
type
Page
About
Hello, my name is Hoang Son. I'm an artificial intelligence researcher and engineer at from in Viet Nam/ I finished my bachelor of science in IT degree @HUFLIT/ Now, I’m studying for a master's degree in AI Convergence @CNU/ I have recently been focusing on computer vision, particularly in the areas of medical image processing and emotion-driven vision generation/ You can find more of my information @sowwn.dev
Research Interests
- Medical Imaging, Image Enhancement.
- 3D Image Segmentation, Video Generation
Education
2024 - 2026: College of AI Convergence - Chonnam National University (Korea)
- Certificate:
- Global Scholarship
2019 - 2023: Faculty of Infomation Technology - HCMC University of Foreign Languages - Information Technology (Viet Nam)
- Certificate:
- Excellent students (Top 1) of academic year 2022-2023
- Talented student scholarship
- Degree: Bachelor of Information Technology
- Graduation thesis: Brain Tumor Detection using Deep Learning, advised by MSc. Tran Nguyen Quynh Tram, co-advised by PhD Nhu-Tai Do (Grade: 9,5/10)
Work Experience
2024:
- Research Assistant @ PRLab (https://prlabjnu.github.io/) - Present
- AI Consulter (Freelancer) @ V-Star Data (https://v-stardata.com/)
2023:
- AI Engineer at Octokit @ Marvy Co. (https://octokit.co/)
- AI Engineer at CVLab @ Wisdom Robotics (https://wisdomrobotics.org/)
- Project Developer (Internship) @ DKiV (http://dkiv.vn/)
Publication
†: Equal Distribution
2025 | Vo-Thanh Hoang-Son, Quang-Vinh Nguyen, Soonja Yeom, and Soo-Hyung Kim. “ATL-Diff: Audio-Driven Talking Head Generation with Early Landmarks-Guide Noise Diffusion” (Under review) |
2024: | • Vo-Thanh Hoang-Son, Quang-Vinh Nguyen, and Soo-Hyung Kim. "KAN-Based Fusion of Dual-Domain for Audio-Driven Facial Landmarks Generation." arXiv preprint arXiv:2409.05330 (2024)
• Quang Vinh Nguyen, Son Vo Thanh Hoang, Sae-Ryung Kang and Soo-Hyung Kim, "Polyp-SES: Automatic Polyp Segmentation with Self-Enriched Semantic Model," Proc. Asian Conf. Computer Vision (ACCV 2024), Hanoi, Vietnam, 2024.
• Hoang-Son Vo-Thanh, Nguyen, Q.-V., Yang, H.-J., Shin, J., Kim, S.-H., n.d. “Individual Audio-Driven Talking Head Generation based on Sequence of Landmark.” in ACK 2024: Annual Conference of KIPS, pp. 553-556, Gwangju, Korea. 2024.
• Quang Vinh Nguyen, Son Vo Thanh Hoang, Hoang Chau Truong Vinh, Duc Duy Nguyen, Nhat Huy Nguyen Minh and Soo-Hyung Kim, "Rethinking Top Probability from Multi-view for Distracted Driver Behavior Localization," Proc. 12th Int. Conf. Bigdata Applications and Services (BIGDAS 2024), pp. 103-112, Jeju, Korea, Aug. 2024. (Best Paper Award) |
2023: | • Nhu-Tai Do†, Hoang-Son Vo-Thanh†, Tram-Tran Nguyen-Quynh†, and Soo-Hyung Kim, "3D-DDA: 3D Dual-Domain Attention for Brain Tumor Segmentation," 2023 IEEE International Conference on Image Processing (ICIP), Kuala Lumpur, Malaysia, 2023, pp. 3215-3219, https://doi.org/10.1109/ICIP49359.2023.10222602
• Hoang-Son Vo-Thanh, Tram-Tran Nguyen-Quynh, Nhu-Tai Do, and Soo-Hyung Kim, “3D Dual-Fusion Attention Network: A fusion attention network for Brain Tumor Segmentation,” in ASK 2023 : Annual Spring Conference of KIPS, pp. 496–498, 2023.
• Tai Do Nhu†, Son Vo Thanh Hoang†, Tram Tran Nguyen Quynh, Huy Nguyen Thanh, Thanh Nguyen Thi Ngoc, Huy Nguyen Quoc and Soo-Hyung Kim, “Brain Tumor segmentation based on deep supervision and context feature fusion”, The 16th National Conference on Fundamental and Applied IT Research, FAIR'2023. https://doi.org/110.15625/vap.2023.0017
• Son Vo Thanh Hoang, Tram Tran Nguyen Quynh, Huy Nguyen Quoc and Tai Do Nhu, “DCDynUnet: Deep Supervision Attention Context for Brain Segmentation”, in Advances in Information and Communication Technology, ICTA 2023. Lecture Notes in Networks and Systems, vol 847. Springer, https://doi.org/10.1007/978-3-031-49529-817. |
"You'd think focus means saying yes, but it actually means to say no."
