Seongmin Hong

Seongmin Hong

Auto-generated profile, based on publicly available information

Seongmin Hong

Seoul National University

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
18 February 2023
Verified
Book Chapter
Closed access
PDF file
AIAndrey Ignatov
Andrey Ignatov
Radu TimofteRadu Timofte
Radu Timofte
MDMaurizio Denna
Maurizio Denna
AYAbdel Younes
Abdel Younes
GGGanzorig Gankhuyag
Ganzorig Gankhuyag
GHGuanghui He
Guanghui He

29 September 2021 in IEEE Sensors Journal
Verified
Journal Article
Closed access
SHSeongmin Hong
Seongmin Hong
SLSeongwook Lee
Seongwook Lee
BLByeong-ho Lee
Byeong-ho Lee
JKJinwook Kim
Jinwook Kim
YKYong-Hwa Kim
Yong-Hwa Kim
Seong-Cheol KimSeong-Cheol Kim
Seong-Cheol Kim
In automotive frequency-modulated continuous wave radar systems, targets with similar ranges and velocities might be detected as a single target because their target information overlaps on the range-velocity (RV) plane. When the information of multiple targets overlaps on the RV plane, target classification cannot be performed accurately. Therefore, we propose a method to decompose the overlapped target information on the RV plane for effective target classification. To separate each target’s radar signal, we use an orthogonal projection, in which the steering vector formed from the angle information of the desired target is projected onto the kernel space composed of other steering vectors. To verify the performance of the proposed method, a convolutional neural network-based target classification is performed on the decomposed radar signals. Compared to the angle-fast Fourier transform (FFT)-based signal decomposition, the orthogonal projection-based signal decomposition shows higher classification accuracy, which implies that the target information overlapped on the RV plane is effectively separated. When information of two targets is overlapped, the classification accuracy of the proposed method is 5.9%p higher than that of the conventional method. Moreover, when the information of three targets is overlapped, the accuracy is improved by 25.5%p.

26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
SHSeongmin Hong
Seongmin Hong
SCSe Young Chun
Se Young Chun
Normalizing flows have been successfully modeling a complex probability distribution as an invertible transformation of a simple base distribution. However, there are often applications that require more than invertibility. For instance, the computation of energies and forces in physics requires the second derivatives of the transformation to be well-defined and continuous. Smooth normalizing flows employ infinitely differentiable transformation, but with the price of slow non-analytic inverse transforms. In this work, we propose diffeomorphic non-uniform B-spline flows that are at least twice continuously differentiable while bi-Lipschitz continuous, enabling efficient parametrization while retaining analytic inverse transforms based on a sufficient condition for diffeomorphism. Firstly, we investigate the sufficient condition for C(k-2)-diffeomorphic non-uniform kth-order B-spline transformations. Then, we derive an analytic inverse transformation of the non-uniform cubic B-spline transformation for neural diffeomorphic non-uniform B-spline flows. Lastly, we performed experiments on solving the force matching problem in Boltzmann generators, demonstrating that our C2-diffeomorphic non-uniform B-spline flows yielded solutions better than previous spline flows and faster than smooth normalizing flows. Our source code is publicly available at https://github.com/smhongok/Non-uniform-B-spline-Flow.

21 November 2024
Verified
Book Chapter
Closed access
PDF file
SHSeongmin Hong
Seongmin Hong
JBJaehyeok Bae
Jaehyeok Bae
JLJongho Lee
Jongho Lee
SCSe Young Chun
Se Young Chun

5 November 2025 in Image and Vision Computing
Verified
Journal Article
Closed access
HLHaechang Lee
Haechang Lee
DMDong Ju Mun
Dong Ju Mun
HLHyunwoo Lee
Hyunwoo Lee
KLKyung Chul Lee
Kyung Chul Lee
SHSeongmin Hong
Seongmin Hong
SCSe Young Chun
Se Young Chun

11 April 2023 in arXiv
Verified
Preprint
Open access
PDF file
SHSeongmin Hong
Seongmin Hong
SCSe Young Chun
Se Young Chun
Normalizing flows have been successfully modeling a complex probability distribution as an invertible transformation of a simple base distribution. However, there are often applications that require more than invertibility. For instance, the computation of energies and forces in physics requires the second derivatives of the transformation to be well-defined and continuous. Smooth normalizing flows employ infinitely differentiable transformation, but with the price of slow non-analytic inverse transforms. In this work, we propose diffeomorphic non-uniform B-spline flows that are at least twice continuously differentiable while bi-Lipschitz continuous, enabling efficient parametrization while retaining analytic inverse transforms based on a sufficient condition for diffeomorphism. Firstly, we investigate the sufficient condition for Ck-2-diffeomorphic non-uniform kth-order B-spline transformations. Then, we derive an analytic inverse transformation of the non-uniform cubic B-spline transformation for neural diffeomorphic non-uniform B-spline flows. Lastly, we performed experiments on solving the force matching problem in Boltzmann generators, demonstrating that our C2-diffeomorphic non-uniform B-spline flows yielded solutions better than previous spline flows and faster than smooth normalizing flows. Our source code is publicly available at https://github.com/smhongok/Non-uniform-B-spline-Flow.