I am currently a third-year PhD student under the supervision of Professor Chang D. Yoo in AIM lab, Korea Advanced Institute of Science and Technology (KAIST). My research involves in computer vision and deep learning.
Github Scholar thangvubk@kaist.ac.kr  

Education

2011 - 2016: Bachelor in Electronics and Telecommunications
Hanoi University of Science and Technology

2017 - 2019: Master in Electrical Engineering
2019 - present: PhD in Electrical Engineering
Korea Advanced Institute of Science and Technology

Selected publications

SoftGroup for 3D Instance Segmentation on Point Clouds

Thang Vu, Kookhoi Kim, Tung M. Luu, Thanh Nguyen, Chang D. Yoo
CVPR, 2022.

SCNet: Training Inference Sample Consistency for Instance Segmentation

Thang Vu, Haeyong Kang, Chang D. Yoo
AAAI, 2021.

SphereRPN: Learning Spheres For High-Quality Region Proposals On 3d Point Clouds Object Detection

Thang Vu, Kookhoi Kim, Tung M. Luu, Thanh Nguyen, Chang D. Yoo
ICIP, 2021.

Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model

Thanh Nguyen*, Tung M. Luu*, Thang Vu, Chang D. Yoo
IROS, 2021.

Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution

Thang Vu, Hyunjun Chang, Chang D. Yoo
NeurIPS, 2019. (Spotlight)

Fast and Efficient Image Quality Enhancement via Desubpixel Convolutional Neural Networks

Thang Vu, Cao V. Nguyen, Trung X. Pham, Tung M. Luu, Chang D. Yoo
ECCV Workshop, 2018. (Winning entry, Spotlight)

Perception-Enhanced Image Super-Resolution via Relativistic Generative Adversarial Networks

Thang Vu, Tung M. Luu, Chang D. Yoo
ECCV Workshop, 2018.

Academic Activities

  • Reviewer: ICCV 2021, IROS 2021, CVPR 2022.

Experience

2016 - 2017: Software engineer
Humax Vina