Search for: All records | NSF Public Access

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

LIAAD: Lightweight attentive angular distillation for large-scale age-invariant face recognition

https://doi.org/10.1016/j.neucom.2023.03.059

Truong, Thanh-Dat ; Duong, Chi Nhan ; Quach, Kha Gia ; Le, Ngan ; Bui, Tien D. ; Luu, Khoa ( July 2023 , Neurocomputing)

Full Text Available
Self-Supervised Domain Adaptation in Crowd Counting

https://doi.org/10.1109/icip46576.2022.9897440

Nguyen, Pha ; Truong, Thanh-Dat ; Huang, Miaoqing ; Liang, Yi ; Le, Ngan ; Luu, Khoa ( November 2022 , 2022 IEEE International Conference on Image Processing (ICIP))

Full Text Available
OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation

https://doi.org/10.1109/icpr56361.2022.9956335

Truong, Thanh-Dat ; Chappa, Ravi Teja ; Nguyen, Xuan-Bac ; Le, Ngan ; Dowling, Ashley P.G. ; Luu, Khoa ( August 2022 , 2022 26th International Conference on Pattern Recognition (ICPR))
EQAdap: Equipollent Domain Adaptation Approach to Image Deblurring

https://doi.org/10.1109/access.2022.3203736

Jalata, Ibsa ; Chappa, Naga Venkata ; Truong, Thanh-Dat ; Helton, Pierce ; Rainwater, Chase ; Luu, Khoa ( January 2022 , IEEE Access)

Full Text Available
Direcformer: A directed attention in transformer approach to robust action recognition

https://doi.org/10.1109/CVPR52688.2022.01940

Truong, Thanh-Dat ; Bui, Quoc-Huy ; Duong, Chi Nhan ; Seo, Han-Seok ; Phung, Son Lam ; Li, Xin ; Luu, Khoa ( January 2022 , Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR))

Full Text Available
Fast Flow Reconstruction via Robust Invertible n × n Convolution

https://doi.org/10.3390/fi13070179

Truong, Thanh-Dat ; Duong, Chi Nhan ; Tran, Minh-Triet ; Le, Ngan ; Luu, Khoa ( July 2021 , Future Internet)

Flow-based generative models have recently become one of the most efficient approaches to model data generation. Indeed, they are constructed with a sequence of invertible and tractable transformations. Glow first introduced a simple type of generative flow using an invertible 1×1 convolution. However, the 1×1 convolution suffers from limited flexibility compared to the standard convolutions. In this paper, we propose a novel invertible n×n convolution approach that overcomes the limitations of the invertible 1×1 convolution. In addition, our proposed network is not only tractable and invertible but also uses fewer parameters than standard convolutions. The experiments on CIFAR-10, ImageNet and Celeb-HQ datasets, have shown that our invertible n×n convolution helps to improve the performance of generative models significantly.
more » « less
Full Text Available