Toan Nguyen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Toan Nguyen has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Jean-Antoine Désidéri
Centre Inria Université Côte d'Azur 2 , Inria, 2004 Route des Lucioles, BP 93, 06902 Sophia Antipolis, France
1 shared publication Laurentiu Trifan
INRIA, 655, Av. de l'Europe, Montbonnot, FR-38334 Saint-Ismier (France)
1 shared publication- Lương Trần Ngọc Khiêt
Trường Đại học Sư phạm Thành phố Hồ Chí Minh
1 shared publication - Minh Nguyen
University of Education
1 shared publication - Nha Tran
Faculty of Information Technology, Ho Chi Minh City University of Education, Ho Chi Minh City, Vietnam
1 shared publication - Phat Tai Lam
University of Education
1 shared publication
Latest Publications
- Open Access
- 1 December 2023
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 12 (4) , 1883-1891
Global-local attention with triplet loss and label smoothed crossentropy for person re-identification
Person re-identification (Person Re-ID) is a research direction on tracking and identifying people in surveillance camera systems with non-overlapping camera perspectives. Despite much research on this topic, there are still some practical problems that Person Re-ID has not yet solved, in reality, human objects can easily be obscured by obstructions such as other people, trees, luggage, umbrellas, signs, cars, motorbikes. In this paper, we propose a multibranch deep learning network architecture. In which one branch is for the representation of global features and two branches are for the representation of local features. Dividing the input image into small parts and changing the number of parts between the two branches helps the model to represent the features better. In addition, we add an attention module to the ResNet50 backbone that enhances important human characteristics and eliminates irrelevant information. To improve robustness, the model is trained by combining triplet loss and label smoothing cross-entropy loss (LSCE). Experiments are carried out on datasets Market1501, and duke multi-target multi-camera (DukeMTMC) datasets, our method achieved 96.04% rank-1, 88,11% mean average precision (mAP) on the Market1501 dataset, and 88.78% rank-1, 78,6% mAP on the DukeMTMC dataset. This method achieves performance better than some state-of-the-art methods.
- 1 December 2023
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 12 (4) , 1883-1891
Open AccessGlobal-local attention with triplet loss and label smoothed crossentropy for person re-identification
Person re-identification (Person Re-ID) is a research direction on tracking and identifying people in surveillance camera systems with non-overlapping camera perspectives. Despite much research on this topic, there are still some practical problems that Person Re-ID has not yet solved, in reality, human objects can easily be obscured by obstructions such as other people, trees, luggage, umbrellas, signs, cars, motorbikes. In this paper, we propose a multibranch deep learning network architecture. In which one branch is for the representation of global features and two branches are for the representation of local features. Dividing the input image into small parts and changing the number of parts between the two branches helps the model to represent the features better. In addition, we add an attention module to the ResNet50 backbone that enhances important human characteristics and eliminates irrelevant information. To improve robustness, the model is trained by combining triplet loss and label smoothing cross-entropy loss (LSCE). Experiments are carried out on datasets Market1501, and duke multi-target multi-camera (DukeMTMC) datasets, our method achieved 96.04% rank-1, 88,11% mean average precision (mAP) on the Market1501 dataset, and 88.78% rank-1, 78,6% mAP on the DukeMTMC dataset. This method achieves performance better than some state-of-the-art methods.
- Open Access
- 1 June 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 71-77
Resilient workflows for high-performance simulation platforms
Workflows systems are considered here to support large-scale multiphysics simulations. Because the use of large distributed and parallel multi-core infrastructures is prone to software and hardware failures, the paper addresses the need for error recovery procedures. A new mechanism based on asymmetric checkpointing is presented. A rule-based implementation for a distributed workflow platform is detailed.
- 1 June 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 71-77
Open AccessResilient workflows for high-performance simulation platforms
Workflows systems are considered here to support large-scale multiphysics simulations. Because the use of large distributed and parallel multi-core infrastructures is prone to software and hardware failures, the paper addresses the need for error recovery procedures. A new mechanism based on asymmetric checkpointing is presented. A rule-based implementation for a distributed workflow platform is detailed.