Duc-Dung Nguyen
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
Duc-Dung Nguyen has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Do Van Thanh
Nguyen Tat Thanh University
2 shared publications - Hai-Son Le
Vietnam Academy of Science and Technology
2 shared publications - Ngoc-Quan Pham
Vietnam Academy of Science and Technology
2 shared publications - Truong Duc Phuong
Hanoi Metropolitan University , Vietnam
2 shared publications Kazunori Matsumoto
KDDI Research and Development Laboratories Inc., Saitama, Japan
1 shared publicationKazuo Hashimoto
Graduate School of Information Sciences, Tohoku University, Sendai, Japan
1 shared publication
Latest Publications
- Open Access
- 1 October 2025
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Information and Systems
- Vol. E108.D (10) , 1279-1282
Multi-Label Semantic Segmentation for Mathematical Expressions Detection in Document Images
Compared to general object detection problems, the detection of mathematical expressions (MED) in document images has its own challenges, like the small size of inline formulas, the rich set of mathematical symbols, and the similarity between variables and normal text characters. To deal with those challenges, we transform the multi-class MED task into a multi-label semantic segmentation problem. With a basic encoder-decoder structure of 3.9 million parameters and trained from scratch, our proposed MEDNet model can achieve top detection performance on three public datasets: TFD2019, Marmot, and IBEM2021. MEDNet is especially effective in detecting small formulas when achieving the F1 score of 95.40% for the inline and 95.82% for all expressions on the test set of the IBEM2021 competition data.
- 1 October 2025
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Information and Systems
- Vol. E108.D (10) , 1279-1282
Open AccessMulti-Label Semantic Segmentation for Mathematical Expressions Detection in Document Images
Compared to general object detection problems, the detection of mathematical expressions (MED) in document images has its own challenges, like the small size of inline formulas, the rich set of mathematical symbols, and the similarity between variables and normal text characters. To deal with those challenges, we transform the multi-class MED task into a multi-label semantic segmentation problem. With a basic encoder-decoder structure of 3.9 million parameters and trained from scratch, our proposed MEDNet model can achieve top detection performance on three public datasets: TFD2019, Marmot, and IBEM2021. MEDNet is especially effective in detecting small formulas when achieving the F1 score of 95.40% for the inline and 95.82% for all expressions on the test set of the IBEM2021 competition data.
- 22 November 2021
- Published by Springer Nature in International Journal on Document Analysis and Recognition (IJDAR)
- Vol. 25 (1) , 1-14
TableSegNet: a fully convolutional network for table detection and segmentation in document images
- 22 November 2021
- Published by Springer Nature in International Journal on Document Analysis and Recognition (IJDAR)
- Vol. 25 (1) , 1-14
TableSegNet: a fully convolutional network for table detection and segmentation in document images
- Open Access
- 1 June 2018
- Published by Walter de Gruyter GmbH in Cybernetics and Information Technologies
- Vol. 18 (2) , 3-19
Mining Fuzzy Sequential Patterns with Fuzzy Time-Intervals in Quantitative Sequence Databases
The main objective of this paper is to introduce fuzzy sequential patterns with fuzzy time-intervals in quantitative sequence databases. In the fuzzy sequential pattern with fuzzy time-intervals, both quantitative attributes and time distances are represented by linguistic terms. A new algorithm based on the Apriori algorithm is proposed to find the patterns. The mined patterns can be applied to market basket analysis, stock market analysis, and so on.
- 1 June 2018
- Published by Walter de Gruyter GmbH in Cybernetics and Information Technologies
- Vol. 18 (2) , 3-19
Open AccessMining Fuzzy Sequential Patterns with Fuzzy Time-Intervals in Quantitative Sequence Databases
The main objective of this paper is to introduce fuzzy sequential patterns with fuzzy time-intervals in quantitative sequence databases. In the fuzzy sequential pattern with fuzzy time-intervals, both quantitative attributes and time distances are represented by linguistic terms. A new algorithm based on the Apriori algorithm is proposed to find the patterns. The mined patterns can be applied to market basket analysis, stock market analysis, and so on.
- Open Access
- 17 August 2017
- Published by Publishing House for Science and Technology, Vietnam Academy of Science and Technology (Publications)
MỘT PHƯƠNG PHÁP PHÂN ĐOẠN KÝ TỰ CHO BÀI TOÁN NHẬN DẠNG CHỮ VIẾT TAY ONLINE
MỘT PHƯƠNG PHÁP PHÂN ĐOẠN KÝ TỰ CHO BÀI TOÁN NHẬN DẠNG CHỮ VIẾT TAY ONLINE
- 17 August 2017
- Published by Publishing House for Science and Technology, Vietnam Academy of Science and Technology (Publications)
Open AccessMỘT PHƯƠNG PHÁP PHÂN ĐOẠN KÝ TỰ CHO BÀI TOÁN NHẬN DẠNG CHỮ VIẾT TAY ONLINE
MỘT PHƯƠNG PHÁP PHÂN ĐOẠN KÝ TỰ CHO BÀI TOÁN NHẬN DẠNG CHỮ VIẾT TAY ONLINE
- Open Access
- 25 May 2016
- Published by Indian Society for Education and Environment in Indian Journal of Science and Technology
- Vol. 9 (17)
An Effective Algorithm for Association Rules Mining from Temporal Quantitative Databases
An Effective Algorithm for Association Rules Mining from Temporal Quantitative Databases
- 25 May 2016
- Published by Indian Society for Education and Environment in Indian Journal of Science and Technology
- Vol. 9 (17)
Open AccessAn Effective Algorithm for Association Rules Mining from Temporal Quantitative Databases
An Effective Algorithm for Association Rules Mining from Temporal Quantitative Databases
- 1 January 2015
- Published by Springer Nature
- p. 459-471
A Study of Feature Combination in Gesture Recognition with Kinect
- 1 January 2015
- Published by Springer Nature
- p. 459-471
A Study of Feature Combination in Gesture Recognition with Kinect
- 1 January 2015
- Published by Springer Nature
- p. 299-311
Neural Networks with Hidden Markov Models in Skeleton-Based Gesture Recognition
- 1 January 2015
- Published by Springer Nature
- p. 299-311
Neural Networks with Hidden Markov Models in Skeleton-Based Gesture Recognition
- 18 October 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 21 (12) , 1903-1914
Condensed Vector Machines: Learning Fast Machine for Large Data
Scalability is one of the main challenges for kernel-based methods and support vector machines (SVMs). The quadratic demand in memory for storing kernel matrices makes it impossible for training on million-size data. Sophisticated decomposition algorithms have been proposed to efficiently train SVMs using only important examples, which ideally are the final support vectors (SVs). However, the ability of the decomposition method is limited to large-scale applications where the number of SVs is still too large for a computer's capacity. From another perspective, the large number of SVs slows down SVMs in the testing phase, making it impractical for many applications. In this paper, we introduce the integration of a vector combination scheme to simplify the SVM solution into an incremental working set selection for SVM training. The main objective of the integration is to maintain a minimal number of final SVs, bringing a minimum resource demand and faster training time. Consequently, the learning machines are more compact and run faster thanks to the small number of vectors included in their solution. Experimental results on large benchmark datasets shows that the proposed condensed SVMs achieve both training and testing efficiency while maintaining a generalization ability equivalent to that of normal SVMs.
- 18 October 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 21 (12) , 1903-1914
Condensed Vector Machines: Learning Fast Machine for Large Data
Scalability is one of the main challenges for kernel-based methods and support vector machines (SVMs). The quadratic demand in memory for storing kernel matrices makes it impossible for training on million-size data. Sophisticated decomposition algorithms have been proposed to efficiently train SVMs using only important examples, which ideally are the final support vectors (SVs). However, the ability of the decomposition method is limited to large-scale applications where the number of SVs is still too large for a computer's capacity. From another perspective, the large number of SVs slows down SVMs in the testing phase, making it impractical for many applications. In this paper, we introduce the integration of a vector combination scheme to simplify the SVM solution into an incremental working set selection for SVM training. The main objective of the integration is to maintain a minimal number of final SVs, bringing a minimum resource demand and faster training time. Consequently, the learning machines are more compact and run faster thanks to the small number of vectors included in their solution. Experimental results on large benchmark datasets shows that the proposed condensed SVMs achieve both training and testing efficiency while maintaining a generalization ability equivalent to that of normal SVMs.