Dinh Viet Sang

Deputy Head, BK.AI Center
Lecturer, Department Of Computer Science

Ph.D. (Dorodnitsyn Computing Centre, Russian Academy of Sciences, Russia, 2013)
M.S. (1st Class Honours, Tula State University, Russia, 2011)
B.S. (1st Class Honours, Tula State University, Russia, 2009)

Email: sangdv@soict.hust.edu.vn
Web:  http://users.soict.hust.edu.vn/sangdv

• Foundation models
• Computer Vision

• Self-supervised learning
• Semi-supervised learning
• Multimodal learning
• Object detection and semantic segmentation

• Evolutionary Multitasking for Solving Optimization Problems (Tài trợ bởi US Army Research Lab và US Army Asia Pacific, 2019-2022)
• Robust dynamic hand gestures recognition for human machine interaction using multimodal features and manifold learning (Tài trợ bởi AFOSR 2017-2019).
• Improving human action recognition using manifold representation and deep learning from multimodal data (Tài trợ bởi NAFOSTED 2017-2019).
• Algorithmic and combinatorial methods on discrete structures (Tài trợ bởi NAFOSTED 2017-2019).

Dinh Viet received his PhD at the Dorodnitsyn Computing Center of the Russian Academy of Sciences (CCRAS) in 2013. He is working at the Department of Computer Science, School of Information and Communications Technology, Hanoi University of Science and Technology. He is currently the Deputy Managing Director of the International Research Center for Artificial Intelligence (BKAI). His research interests are machine learning, deep learning, foundation models and computer vision.

• Nguyen Minh Chau, Nguyen Ngoc Toan, Le Dinh Tuyen, Dinh Viet Sang, Pooi-Mun Wong, Chin-Boon Chng and Chee-Kong Chui. Boosting Facial Landmark Detection via Self-supervised and Semi-supervised Learning. SOICT 2023
• Nguyen Viet Hoai, Pham Vu Hung, Dinh Viet Sang. Memory-Driven Region Contrast for Enhanced Polyp Semantic Segmentation. MAPR 2023
• Manh Nguyen Duy, Hang Dao Viet, Long Dao Van, Hung Le Quang, Khanh Pham Cong, Oanh Nguyen Thi, Thuy Nguyen Thi, Sang Dinh Viet. EndoUNet: A Unified Model for Anatomical Site Classification, Lesion Categorization and Segmentation for Upper Gastrointestinal Endoscopy. KSE 2022
• Nguyen Thanh Duc, Nguyen Thi Oanh, Nguyen Thi Thuy, Tran Minh Triet, Dinh Viet Sang. ColonFormer: An Efficient Transformer Based Method for Colon Polyp Segmentation. IEEE Access, vol. 10, pp. 80575-80586, 2022
• Lan, P.N., An, N.S., Hang, D.V., Long, D.V., Trung, T.Q., Thuy, N.T., Sang, D.V.. NeoUnet: Towards accurate colon polyp segmentation and neoplasm detection. In: Proceedings of the 16th International Symposium on Visual Computing (2021)
• In Seop Na, Chung Tran, Dung Nguyen, Sang Dinh. Facial UV Map Completion for Pose-invariant Face Recognition: A Novel Adversarial Approach based on Coupled Attention Residual UNets. Human-centric Computing and Information Sciences 2020

• Develop an AI-based Interactive E-learning Platform For Endoscopy Training in Vietnam, 2024 (funded by RMIT Vietnam Strategic Innovation Challenge)
• Transfer Learning for Combinatorial Optimization Problems VINIF.2022.DA183 (funded by VINIF)
• Research and Develop an Intelligent System to Support the Diagnosis of Upper Gastrointestinal Lesions by Endoscopic Images. KC4.0 program (funded by MOST)
• Mobility as a Service

• Computer Vision
• Scientific Computing
• Discrete Maths
• Applied Algorithms