1 code implementation • CVPR 2021 • Xuan-Bac Nguyen, Duc Toan Bui, Chi Nhan Duong, Tien D. Bui, Khoa Luu
This work therefore presents the Clusformer, a simple but new perspective of Transformer based approach, to automatic visual clustering via its unsupervised attention mechanism.
no code implementations • 19 Aug 2020 • Naitik Bhise, Zhenfei Zhang, Tien D. Bui
Generative Adversarial Networks (GANs) have long been used to understand the semantic relationship between the text and image.
no code implementations • 9 Apr 2020 • Thanh-Dat Truong, Chi Nhan Duong, Kha Gia Quach, Ngan Le, Tien D. Bui, Khoa Luu
This work presents a novel Lightweight Attentive Angular Distillation (LIAAD) approach to Large-scale Lightweight AiFR that overcomes these limitations.
no code implementations • 24 Apr 2019 • MohammadReza Davari, Leila Kosseim, Tien D. Bui
These results underline the importance of domain specific embedding as well as specific linguistic features in toponym detection in medical journals.
no code implementations • CVPR 2019 • Chi Nhan Duong, Khoa Luu, Kha Gia Quach, Nghia Nguyen, Eric Patterson, Tien D. Bui, Ngan Le
This paper presents a novel approach to synthesize automatically age-progressed facial images in video sequences using Deep Reinforcement Learning.
no code implementations • 23 Feb 2018 • Chi Nhan Duong, Khoa Luu, Kha Gia Quach, Tien D. Bui
Face Aging has raised considerable attentions and interest from the computer vision community in recent years.
no code implementations • 28 Nov 2017 • Chi Nhan Duong, Kha Gia Quach, Khoa Luu, T. Hoang Ngan Le, Marios Savvides, Tien D. Bui
The proposed model is experimented in both tasks of face aging synthesis and cross-age face verification.
no code implementations • 23 Jul 2016 • Chi Nhan Duong, Khoa Luu, Kha Gia Quach, Tien D. Bui
This paper presents a novel Deep Appearance Models (DAMs) approach, an efficient replacement for AAMs, to accurately capture both shape and texture of face images under large variations.
no code implementations • 3 Jul 2016 • Kha Gia Quach, Chi Nhan Duong, Khoa Luu, Tien D. Bui
In this approach, two crucial components of face images, i. e. shape and texture, are represented by Deep Boltzmann Machines and Robust Deep Boltzmann Machines (RDBM), respectively.
no code implementations • CVPR 2016 • Chi Nhan Duong, Khoa Luu, Kha Gia Quach, Tien D. Bui
The Temporal Deep Restricted Boltzmann Machines based age progression model together with the prototype faces are then constructed to learn the aging transformation between faces in the sequence.
no code implementations • CVPR 2015 • Chi Nhan Duong, Khoa Luu, Kha Gia Quach, Tien D. Bui
The "interpretation through synthesis", i. e.