Vu Minh Hieu Phan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Vu Minh Hieu Phan has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Bowen Zhang
The University of Adelaide
3 shared publications - Johan W. Verjans
University of Adelaide
3 shared publications - Zhibin Liao
Adelaide University
3 shared publications - Akide Liu
Monash University
2 shared publications - Jinchao Ge
The University of Adelaide
2 shared publications - Minh-Son To
Flinders University
2 shared publications
Latest Publications
- 11 September 2026
- Published by Springer Nature
- p. 1-17
Do Vision Language Models Recognize Visual Ambiguity?
- 11 September 2026
- Published by Springer Nature
- p. 1-17
Do Vision Language Models Recognize Visual Ambiguity?
- 19 September 2025
- Published by Springer Nature
- p. 670-680
Unleashing SAM for Few-Shot Medical Image Segmentation with Dual-Encoder and Automated Prompting
- 19 September 2025
- Published by Springer Nature
- p. 670-680
Unleashing SAM for Few-Shot Medical Image Segmentation with Dual-Encoder and Automated Prompting
- 26 July 2025
- Published by Springer Nature
- p. 141-152
ESA: Annotation-Efficient Active Learning for Semantic Segmentation
- 26 July 2025
- Published by Springer Nature
- p. 141-152
ESA: Annotation-Efficient Active Learning for Semantic Segmentation
- Open Access
- 26 April 2025
- Published by Elsevier in Pattern Recognition
- Vol. 167
CIT: Rethinking class-incremental semantic segmentation with a Class Independent Transformation
- 26 April 2025
- Published by Elsevier in Pattern Recognition
- Vol. 167
Open AccessCIT: Rethinking class-incremental semantic segmentation with a Class Independent Transformation
- 3 October 2024
- Published by Springer Nature
- p. 690-700
Structural Attention: Rethinking Transformer for Unpaired Medical Image Synthesis
- 3 October 2024
- Published by Springer Nature
- p. 690-700
Structural Attention: Rethinking Transformer for Unpaired Medical Image Synthesis
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 10392-10407
CARER - ClinicAl Reasoning-Enhanced Representation for Temporal Health Risk Prediction
Tuan Dung Nguyen, Thanh Trung Huynh, Minh Hieu Phan, Quoc Viet Hung Nguyen, Phi Le Nguyen. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 10392-10407
Open AccessCARER - ClinicAl Reasoning-Enhanced Representation for Temporal Health Risk Prediction
Tuan Dung Nguyen, Thanh Trung Huynh, Minh Hieu Phan, Quoc Viet Hung Nguyen, Phi Le Nguyen. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
- Open Access
- 27 October 2023
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (4) , 1126-1147
SegViT v2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers
This paper investigates the capability of plain Vision Transformers (ViTs) for semantic segmentation using the encoder–decoder framework and introduce SegViTv2. In this study, we introduce a novel Attention-to-Mask (ATM) module to design a lightweight decoder effective for plain ViT. The proposed ATM converts the global attention map into semantic masks for high-quality segmentation results. Our decoder outperforms popular decoder UPerNet using various ViT backbones while consuming only about $$5\%$$ of the computational cost. For the encoder, we address the concern of the relatively high computational cost in the ViT-based encoders and propose a Shrunk++ structure that incorporates edge-aware query-based down-sampling (EQD) and query-based up-sampling (QU) modules. The Shrunk++ structure reduces the computational cost of the encoder by up to $$50\%$$ while maintaining competitive performance. Furthermore, we propose to adapt SegViT for continual semantic segmentation, demonstrating nearly zero forgetting of previously learned knowledge. Experiments show that our proposed SegViTv2 surpasses recent segmentation methods on three popular benchmarks including ADE20k, COCO-Stuff-10k and PASCAL-Context datasets. The code is available through the following link: https://github.com/zbwxp/SegVit.- 27 October 2023
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (4) , 1126-1147
Open AccessSegViT v2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers
This paper investigates the capability of plain Vision Transformers (ViTs) for semantic segmentation using the encoder–decoder framework and introduce SegViTv2. In this study, we introduce a novel Attention-to-Mask (ATM) module to design a lightweight decoder effective for plain ViT. The proposed ATM converts the global attention map into semantic masks for high-quality segmentation results. Our decoder outperforms popular decoder UPerNet using various ViT backbones while consuming only about $$5\%$$ of the computational cost. For the encoder, we address the concern of the relatively high computational cost in the ViT-based encoders and propose a Shrunk++ structure that incorporates edge-aware query-based down-sampling (EQD) and query-based up-sampling (QU) modules. The Shrunk++ structure reduces the computational cost of the encoder by up to $$50\%$$ while maintaining competitive performance. Furthermore, we propose to adapt SegViT for continual semantic segmentation, demonstrating nearly zero forgetting of previously learned knowledge. Experiments show that our proposed SegViTv2 surpasses recent segmentation methods on three popular benchmarks including ADE20k, COCO-Stuff-10k and PASCAL-Context datasets. The code is available through the following link: https://github.com/zbwxp/SegVit. - 1 October 2023
- Published by Springer Nature
- p. 56-65
Structure-Preserving Synthesis: MaskGAN for Unpaired MR-CT Translation
- 1 October 2023
- Published by Springer Nature
- p. 56-65
Structure-Preserving Synthesis: MaskGAN for Unpaired MR-CT Translation
- 9 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (22) , 25181-25189
CompactNet: A Light-Weight Deep Learning Framework for Smart Intrusive Load Monitoring
Energy load monitoring via smart plugs or smart sockets has become more and more popular. Various studies have been undertaken to monitor energy consumption of household appliances and analyze the collected power data to obtain useful insights on consumers’ behaviors. The main challenge in load monitoring is to automatically recognize appliances in real time since the existing energy disaggregation process is time-consuming and labour-intensive. Although several deep learning models can achieve high accuracy on appliance classification, they usually consume large memory, hence not suitable for resources-constrained IoT devices. To resolve the issue, we demonstrate in this paper, for the first time, a novel framework named Smart Intrusive Load Monitoring based on a compact network (CompactNet), which is able to determine appliance types in real time. Specifically, our method distills the knowledge of an ensemble of large deep networks to a much more compact network. Our CompactNet accurately classifies various types of appliances, but its size is reduced by approximately eight times, making it possible to be deployed on edge IoT sensors for appliance recognition.
- 9 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (22) , 25181-25189
CompactNet: A Light-Weight Deep Learning Framework for Smart Intrusive Load Monitoring
Energy load monitoring via smart plugs or smart sockets has become more and more popular. Various studies have been undertaken to monitor energy consumption of household appliances and analyze the collected power data to obtain useful insights on consumers’ behaviors. The main challenge in load monitoring is to automatically recognize appliances in real time since the existing energy disaggregation process is time-consuming and labour-intensive. Although several deep learning models can achieve high accuracy on appliance classification, they usually consume large memory, hence not suitable for resources-constrained IoT devices. To resolve the issue, we demonstrate in this paper, for the first time, a novel framework named Smart Intrusive Load Monitoring based on a compact network (CompactNet), which is able to determine appliance types in real time. Specifically, our method distills the knowledge of an ensemble of large deep networks to a much more compact network. Our CompactNet accurately classifies various types of appliances, but its size is reduced by approximately eight times, making it possible to be deployed on edge IoT sensors for appliance recognition.