Nguyen Minh Khiem
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nguyen Minh Khiem has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
Hiroki Yasuma
Faculty of Fisheries Sciences, Hokkaido University, Hakodate, Japan
5 shared publications- Nguyen Thai-Nghe
Can Tho University
5 shared publications Nobuo Kimura
Faculty of Fisheries Sciences, Hokkaido University, Hakodate, Japan
5 shared publicationsTran Ngoc Hai
College of Aquaculture & Fisheries, Can Tho University
5 shared publicationsYuki Takahashi
Faculty of Fisheries Sciences, Hokkaido University, Hakodate, Japan
5 shared publications- Le Huynh Quoc Bao
Can Tho University
4 shared publications
Latest Publications
- 20 November 2026
- Published by Springer Nature
- p. 540-553
FAR-VL: A Cascading Vision-Language Framework with Explainable Verification for False Alarm Reduction in Early Fire Warning Systems
- 20 November 2026
- Published by Springer Nature
- p. 540-553
FAR-VL: A Cascading Vision-Language Framework with Explainable Verification for False Alarm Reduction in Early Fire Warning Systems
- Open Access
- 9 November 2026
- Published by Can Tho University in CTU Journal of Innovation and Sustainable Development
- Vol. 18 (Special : ) , 88-99
FLAIR-XGT: Local visual patch feature aggregation with multi-graph fusion for image-based recommendation
Existing multimodal recommender systems discard fine-grained spatial information before recommendation training even starts by representing each product image as a single global vector, either a pooled CNN output or a Vision Transformer’s CLS token. We propose FLAIR-XGT, an image-based recommendation framework that uses three parallel graph networks (LightGCN, VisualGCN, and TextGCN) to jointly train representative local DINOv2 ViT-B/14 patch tokens (each covering a pixel region) end-to-end under a combined BPR + InfoNCE objective. Our primary scoring component, GlobalVis, combines the local patch tokens using a projector that is optimized in tandem with the recommender. In comparison to all fixed pre-extracted global-feature baselines, this joint training of local patch aggregation with multi-graph collaborative fusion produces NDCG@20 on Amazon Fashion ( over MMGCN) and NDCG@20 on Sports & Outdoors ( over MMGCN). We also study XGT, a user-conditioned cross-attention module that focuses spatial attention on user-relevant patches. A Graph Transformer block with a CF residual connection fuses the attended output. One important empirical finding is that XGT cross-attention performs worse than GlobalVis on both datasets, which reflects a cold-start limitation: user embeddings are too sparse to form discriminative attention queries, making learned mean-pooling of local patches the stronger configuration in practice. Sensitivity analysis verifies resilience across the critical hyperparameters, and ablation studies link each performance gain to particular design decisions.
- 9 November 2026
- Published by Can Tho University in CTU Journal of Innovation and Sustainable Development
- Vol. 18 (Special : ) , 88-99
Open AccessFLAIR-XGT: Local visual patch feature aggregation with multi-graph fusion for image-based recommendation
Existing multimodal recommender systems discard fine-grained spatial information before recommendation training even starts by representing each product image as a single global vector, either a pooled CNN output or a Vision Transformer’s CLS token. We propose FLAIR-XGT, an image-based recommendation framework that uses three parallel graph networks (LightGCN, VisualGCN, and TextGCN) to jointly train representative local DINOv2 ViT-B/14 patch tokens (each covering a pixel region) end-to-end under a combined BPR + InfoNCE objective. Our primary scoring component, GlobalVis, combines the local patch tokens using a projector that is optimized in tandem with the recommender. In comparison to all fixed pre-extracted global-feature baselines, this joint training of local patch aggregation with multi-graph collaborative fusion produces NDCG@20 on Amazon Fashion ( over MMGCN) and NDCG@20 on Sports & Outdoors ( over MMGCN). We also study XGT, a user-conditioned cross-attention module that focuses spatial attention on user-relevant patches. A Graph Transformer block with a CF residual connection fuses the attended output. One important empirical finding is that XGT cross-attention performs worse than GlobalVis on both datasets, which reflects a cold-start limitation: user embeddings are too sparse to form discriminative attention queries, making learned mean-pooling of local patches the stronger configuration in practice. Sensitivity analysis verifies resilience across the critical hyperparameters, and ablation studies link each performance gain to particular design decisions.
- 15 July 2026
- Published by Springer Nature
- p. 82-87
An Explainable Ensemble CNN Approach for Automated Shrimp Disease Diagnosis Using Enhanced Aquaculture Image Data
- 15 July 2026
- Published by Springer Nature
- p. 82-87
An Explainable Ensemble CNN Approach for Automated Shrimp Disease Diagnosis Using Enhanced Aquaculture Image Data
- 5 April 2026
- Published by Springer Nature
- p. 535-549
REBANet: A Hybrid Deep Learning Model for Rice Leaf Disease Prediction with Grad-CAM Explainability
- 5 April 2026
- Published by Springer Nature
- p. 535-549
REBANet: A Hybrid Deep Learning Model for Rice Leaf Disease Prediction with Grad-CAM Explainability
- 23 February 2026
- Published by Springer Nature
- p. 239-251
Leveraging Deep Learning for Lung Disease Diagnosis and Classification Through X-ray Imaging
- 23 February 2026
- Published by Springer Nature
- p. 239-251
Leveraging Deep Learning for Lung Disease Diagnosis and Classification Through X-ray Imaging
- 23 February 2026
- Published by Springer Nature
- p. 509-526
A Fusion Model of Image and Text for Product Recommendation
- 23 February 2026
- Published by Springer Nature
- p. 509-526
A Fusion Model of Image and Text for Product Recommendation
- 22 November 2025
- Published by Springer Nature
- p. 411-418
A Fusion of Graph Neural Networks and Attention Mechanism for Image-Based Recommendation Systems
- 22 November 2025
- Published by Springer Nature
- p. 411-418
A Fusion of Graph Neural Networks and Attention Mechanism for Image-Based Recommendation Systems
- 12 July 2025
- Published by Springer Nature
- p. 86-99
An Approach for Enhancing Ripe Tomato Classification and Counting by Using Deep Learning and SAHI Image Processing
- 12 July 2025
- Published by Springer Nature
- p. 86-99
An Approach for Enhancing Ripe Tomato Classification and Counting by Using Deep Learning and SAHI Image Processing