Thanh Phuong Nguyen

Dr. Thanh Phuong Nguyen

Auto-generated profile, based on publicly available information

Dr. Thanh Phuong Nguyen


Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 May 2024 in Neural Networks
Verified
Journal Article
Closed access
Van Tien PhamVan Tien Pham
Van Tien Pham
YZYassine Zniyed
Yassine Zniyed
TNThanh Phuong Nguyen
Thanh Phuong Nguyen

1 January 2016 in Neurocomputing
Verified
Journal Article
Closed access
TNThanh Phuong Nguyen
Thanh Phuong Nguyen
NVNgoc-Son Vu
Ngoc-Son Vu
AMAntoine Manzanera
Antoine Manzanera

1 January 2011 in Pattern Recognition
Verified
Journal Article
Closed access
TNThanh Phuong Nguyen
Thanh Phuong Nguyen
IDIsabelle Debled-Rennesson
Isabelle Debled-Rennesson

8 March 2024 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
Van Tien PhamVan Tien Pham
Van Tien Pham
YZYassine Zniyed
Yassine Zniyed
TNThanh Phuong Nguyen
Thanh Phuong Nguyen
Network compression techniques that combine tensor decompositions and pruning have shown promise in leveraging the advantages of both strategies. In this work, we propose enhanced Network cOmpRession through TensOr decompositions and pruNing (NORTON), a novel method for network compression. NORTON introduces the concept of filter decomposition, enabling a more detailed decomposition of the network while preserving the weight’s multidimensional properties. Our method incorporates a novel structured pruning approach, effectively integrating the decomposed model. Through extensive experiments on various architectures, benchmark datasets, and representative vision tasks, we demonstrate the usefulness of our method. NORTON achieves superior results compared to state-of-the-art (SOTA) techniques in terms of complexity and accuracy. Our code is also available for research purposes.

1 June 2014 in Image and Vision Computing
Verified
Journal Article
Closed access
NVNgoc-Son Vu
Ngoc-Son Vu
TNThanh Phuong Nguyen
Thanh Phuong Nguyen
CGChristophe Garcia
Christophe Garcia

12 December 2016 in EURASIP Journal on Image and Video Processing
Verified
Journal Article
Open access
PDF file
AMAntoine Manzanera
Antoine Manzanera
TNThanh Phuong Nguyen
Thanh Phuong Nguyen
XXXiaolei Xu
Xiaolei Xu
By estimating the first-order (direction) and second-order (curvature) derivatives in an image, the parameters of a line or circle passing through a point may be uniquely defined in most cases. This allows to compute a one-to-one Hough transform, every point in the image space voting for one unique point in the parameter space. Moreover, those parameters can be directly estimated on the greyscale image without the need to calculate the contour and without reducing the spatial support of the Hough transform, i.e. densely on the whole image. The general framework using multiscale derivatives is presented, and the one-to-one Hough dense transforms for detecting lines and circles are evaluated and compared with other variants of Hough transforms, from qualitative and computational points of view.