Sunjae Yoon

Mr. Sunjae Yoon

Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea
orcid

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

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

Representative Publications

View All Publications
29 October 2022
Verified
Book Chapter
Closed access
PDF file
SYSunjae Yoon
Sunjae Yoon
JHJi Woo Hong
Ji Woo Hong
EYEunseop Yoon
Eunseop Yoon
DKDahyun Kim
Dahyun Kim
JKJunyeong Kim
Junyeong Kim
CYChang D. Yoo
Chang D. Yoo

21 November 2024
Verified
Book Chapter
Closed access
PDF file
GKGwanhyeong Koo
Gwanhyeong Koo
SYSunjae Yoon
Sunjae Yoon
JHJi Woo Hong
Ji Woo Hong
CYChang D. Yoo
Chang D. Yoo

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
HRHyun Ryu
Hyun Ryu
SYSunjae Yoon
Sunjae Yoon
HYHee Suk Yoon
Hee Suk Yoon
EYEunseop Yoon
Eunseop Yoon
CYChang D. Yoo
Chang D. Yoo
Data augmentation is a crucial component in training neural networks to overcome the limitation imposed by data size, and several techniques have been studied for time series. Although these techniques are effective in certain tasks, they have yet to be generalized to time series benchmarks. We find that current data augmentation techniques ruin the core information contained within the frequency domain. To address this issue, we propose a simple strategy to preserve spectral information (SimPSI) in time series data augmentation. SimPSI preserves the spectral information by mixing the original and augmented input spectrum weighted by a preservation map, which indicates the importance score of each frequency. Specifically, our experimental contributions are to build three distinct preservation maps: magnitude spectrum, saliency map, and spectrum-preservative map. We apply SimPSI to various time series data augmentations and evaluate its effectiveness across a wide range of time series benchmarks. Our experimental results support that SimPSI considerably enhances the performance of time series data augmentations by preserving core spectral information. The source code used in the paper is available at https://github.com/Hyun-Ryu/simpsi.

1 March 2011
Verified
Conference Paper
Closed access
SYSunjae Yoon
Sunjae Yoon
JKJunbum Kwon
Junbum Kwon
Junsung ParkJunsung Park
Junsung Park
SCSewan Choi
Sewan Choi
This paper proposes an indirect current control algorithm for seamless transfer of three-phase utility-interactive inverters. With the proposed method the inverter is able to provide critical loads with a stable and seamless voltage during the whole transition period including both clearing time and control mode change. The LCL filter design which is suitable for the indirect current control is also proposed to meet the harmonic limits. The proposed control method is validated through simulation and experiment.

14 June 2022 in IEEE Access
Verified
Journal Article
Open access
SYSunjae Yoon
Sunjae Yoon
DKDahyun Kim
Dahyun Kim
JKJunyeong Kim
Junyeong Kim
CYChang D. Yoo
Chang D. Yoo
Video corpus moment retrieval aims to localize temporal moments corresponding to textual query in a large video corpus. Previous moment retrieval systems are largely grouped into two categories: (1) anchor-based method which presets a set of video segment proposals (via sliding window) and predicts proposal that best matches with the query, and (2) anchor-free method which directly predicts frame-level start-end time of the moment related to the query (via regression). Both methods have their own inherent weaknesses: (1) anchor-based method is vulnerable to heuristic rules of generating video proposals, which causes restrictive moment prediction in variant length; and (2) anchor-free method, as is based on frame-level interplay, suffers from insufficient understanding of contextual semantics from long and sequential video. To overcome the aforementioned challenges, our proposed Cascaded Moment Proposal Network incorporates the following two main properties: (1) Hierarchical Semantic Reasoning which provides video understanding from anchor-free level to anchor-based level via building hierarchical video graph, and (2) Cascaded Moment Proposal Generation which precisely performs moment retrieval via devising cascaded multi-modal feature interaction among anchor-free and anchor-based video semantics. Extensive experiments show state-of-the-art performance on three moment retrieval benchmarks (TVR, ActivityNet, DiDeMo), while qualitative analysis shows improved interpretability. The code will be made publicly available.

27 November 2024
Verified
Book Chapter
Closed access
PDF file
SYSunjae Yoon
Sunjae Yoon
GKGwanhyeong Koo
Gwanhyeong Koo
JHJi Woo Hong
Ji Woo Hong
CYChang D. Yoo
Chang D. Yoo