no code implementations • 10 Oct 2022 • Shokhrukh Miraliev, Shakhboz Abdigapporov, Jumabek Alikhanov, Vijay Kakani, Hakil Kim
A safe and robust autonomous driving system relies on accurate perception of the environment for application-oriented scenarios.
1 code implementation • 2 Jun 2022 • Ziyan Chen, Jiazhen Liu, Changwen Cao, Changlong Jin, Hakil Kim
In the proposed framework, the domain mapper is an approximation to a specific extraction function thus the training is only a one-time effort with limited data.
1 code implementation • journal 2019 • Cheng-Bin Jin, Hakil Kim, Mingjie Liu, In Ho Han, Jae Il Lee, Jung Hwan Lee, Seongsu Joo, Eunsik Park, Young Saem Ahn, Xuenan Cui
In this paper, we propose a method for estimating lumbar spine MR images based on CT images using a novel objective function and a dual cycle-consistent adversarial network (DC2Anet) with semi-supervised learning.
no code implementations • 16 Jun 2019 • Trung Dung Do, Cheng-Bin Jin, Hakil Kim, Van Huan Nguyen
MSL consists of between-class and within-class loss.
no code implementations • 3 May 2019 • Trung Dung Do, Hakil Kim, Van Huan Nguyen
This paper proposes a novel method for classifying human gender in real time using gait information.
no code implementations • 3 May 2019 • Trung Dung Do, Xuenan Cui, Thi Hai Binh Nguyen, Hakil Kim, Van Huan Nguyen
In the previous blind deconvolution methods, de-blurred images can be obtained by using the edge or pixel information.
1 code implementation • 28 May 2018 • Cheng-Bin Jin, Hakil Kim, Wonmo Jung, Seongsu Joo, Ensik Park, Ahn Young Saem, In Ho Han, Jae Il Lee, Xuenan Cui
To improve the accuracy of CT-based radiotherapy planning, we propose a synthetic approach that translates a CT image into an MR image using paired and unpaired training data.
no code implementations • 21 Mar 2018 • Eunsoo Park, Xuenan Cui, Weonjin Kim, Hakil Kim
The proposed CNN structure uses the fire module as the base model and uses the gram module for texture extraction.
no code implementations • 21 Mar 2018 • Eunsoo Park, Xuenan Cui, Weonjin Kim, Jinsong Liu, Hakil Kim
This study proposes a patch-based fake fingerprint detection method using a fully convolutional neural network with a small number of parameters and an optimal threshold to solve the above-mentioned problem.
1 code implementation • 10 Oct 2017 • Cheng-Bin Jin, Shengzhe Li, Hakil Kim
The proposed approach achieved a mean average precision (mAP) of 76. 6% at the frame-based and 83. 5% at the video-based measurement on the new large-scale ICVL video surveillance dataset that the authors introduce and make available to the community with this paper.
no code implementations • 4 Feb 2017 • Youngwan Lee, Byeonghak Yim, Huien Kim, Eunsoo Park, Xuenan Cui, Taekang Woo, Hakil Kim
Since convolutional neural network(CNN)models emerged, several tasks in computer vision have actively deployed CNN models for feature extraction.