csehong
Sungeun Hong
Assistant Professor & Photographer
AI & Media (AIM) Lab, Sungkyunkwan University
Web: www.csehong.com
Email: csehong@skku.edu
CV · Google Scholar · LinkedIn · GitHub · PhotoBlog
Seeking for new members from graduate students to post-doctoral researchers!
Work Experience
Sungkyunkwan University, Assistant Professor, 2023.09 - Present
Dept. of Immersive Media Engineering / College of Computing and InformaticsInha University, Assistant Professor, 2020.09 - 2023.08
Dept. of Information and Communication EngineeringSK telecom, Research Scientist, 2018.01 - 2020.08
T-Brain, AI Center
Education
KAIST, Ph.D., Computer Science, 2018
KAIST, M.S., Computer Science, 2012
Hanyang, B.S., Computer Engineering, 2010
Research Interests
· Multimodal Learning · Vision-Language Models · Domain Transfer · Robot Vision · Efficient Transfer Learning
Publications
Elastic Modulus Prediction from Indentation Using Machine Learning: Considering Tip Geometric Imperfection
Jong-hyoung Kim, Dong-Yeob Kim, Junsang Lee, Soon Woo Kwon, Jongheon Kim, Seung-Kyun Kang, Sungeun Hong, and Young-Cheon Kim, Metals and Materials International (Q1), March 2024.
[Paper]
Visual and tactile perception techniques for braille recognition
Byeong-Sun Park, Seong-Min Im, Hojun Lee, Young Tack Lee, Changjoo Nam, Sungeun Hong, and Min-gu Kim, Micro and Nano Systems Letters, vol. 11, no. 1, pp. 1-8, December 2023.
[Paper]
Re-Aging GAN++: Temporally consistent transformation of faces in videos
Farkhod Makhmudkhujaev, Sungeun Hong, and In Kyu Park, IEEE Access, vol. 11, pp. 137377-137386, December 2023.
[Paper]
SegTex: A large scale synthetic face dataset for face recognition
Laudwika Ambardi, Sungeun Hong, and In Kyu Park, IEEE Access, vol. 11, pp. 131939-131949, November 2023.
[Paper]
TL-ADA: transferable loss-based active domain adaptation
Kyeongtak Han, Youngeun Kim, Dongyoon Han, Hojun Lee, and Sungeun Hong, Neural Networks (Q1), February 2023.
[Paper]
Adaptive graph adversarial networks for partial domain adaptation
Youngeun Kim and Sungeun Hong, IEEE Trans. on Circuits and Systems for Video Technology (Q1), vol. 32, no. 1, pp. 172-182, January 2022.
[Paper]
Re-Aging GAN: Toward personalized face age transformation
Farkhod Makhmudkhujaev, Sungeun Hong, and In Kyu Park, Proc. IEEE/CVF International Conference on Computer Vision (ICCV 2021), October 2021.
[Paper]
Domain adaptation without source data
Youngeun Kim, Donghyeon Cho, Kyeongtak Han, Priyadarshini Panda, and Sungeun Hong, IEEE Trans. on Artificial Intelligence (TAI), vol. 2, no. 6, pp. 508-518, December 2021.
[Paper]
Self-supervised feature enhancement networks for small object detection in noisy images
Geonsoo Lee, Sungeun Hong (co-first author), and Donghyeon Cho, IEEE Signal Processing Letters, vol. 28, pp. 1026-1030, May 2021.
[Paper]
Towards privacy-preserving domain adaptation
Youngeun Kim, Donghyeon Cho, and Sungeun Hong, IEEE Signal Processing Letters, vol. 27, pp. 1675-1679, September 2020.
[Paper]
Attention-guided adaptation factors for unsupervised facial domain adaptation
Sungeun Hong and Jongbin Ryu, Electronics Letters, vol. 56, no. 16, pp. 816-818, August 2020.
[Paper]
Unsupervised face domain transfer for low-resolution face recognition
Sungeun Hong and Jongbin Ryu, IEEE Signal Processing Letters, vol. 27, pp. 156-160, December 2019.
[Paper]
VisDrone-DET2019: The vision meets drone object detection in image challenge results
Sungeun Hong and VisDrone Challenge Participants, VisDrone Workshops at International Conference on Computer Vision (ICCVW 2019), Ranked at 3rd, October 2019.
3rd Prize in Vision Meets Drone: A Challenge at ICCV '19
[Paper]
Key instance selection for unsupervised video object segmentation
Sungeun Hong, Donghyeon Cho, Sungil Kang, and Jiwon Kim, DAVIS Challenge Workshops at Computer Vision and Pattern Recognition (CVPRW 2019), Ranked 3rd, June 2019
3rd Prize in DAVIS Challenge on Video Object Segmentation at CVPR '19
Doubly Nested Network for Resource-Efficient Inference
Jaehong Kim, Sungeun Hong, Yongseok Choi, and Jiwon Kim
June 2018, arxiv
[Paper]
Cascaded pyramid network for 3D human pose estimation challenge
Sungeun Hong , Wonjin Jung, Ilsang Woo, and Seung Wook Kim, PoseTrack Workshops at European Conference on Computer Vision (ECCVW 2018), September 2018.
[Paper]
Sorted consecutive local binary pattern for texture classification
Jongbin Ryu, Sungeun Hong, and Hyun S. Yang, IEEE Trans. on Image Processing (Q1), vol. 24, no. 7, pp. 2254-2265, July 2015.
[Paper]
Recursive Bayesian fire recognition using greedy margin-maximizing clustering
Sujung Bae, Sungeun Hong, Yeongjae Choi, and Hyun S. Yang, Machine Vision and Applications, vol. 24, pp. 1605-1621, November 2013.
[Paper]
3D Keypoint Tracking Based on Hybrid Flow Computation for Human Motion Analysis
Sujung Bae, Sungeun Hong, and Hyun S. Yang, Machine Vision and Applications (MVA 2013), IAPR, May 2013.
[Paper]
Research Projects
Ongoing
RGB-X 데이터의 다중-모달 다수-작업 학습을 위한 경로 네트워크 기술 (2023.03 ~ 2026.02)
RGB 이미지와 선택적으로 주어지는 정보(깊이, 열화상, 촉각, 텍스트 등)를 효율적으로 융합하고, 서로 다른 작업 및 환경간의 지식 전이를 통합적으로 수행할 수 있는 RGB-X 데이터의 다중-모달 다수-작업 학습을 위한 경로 네트워크 기술을 연구
Funded by National Research Foundation (한국연구재단 이공분야기초연구사업 - 우수신진연구)
멀티모달리티 융합을 통한 RGB-D 객체 검출 및 분할 기술 (2023.03 ~ 2023.10)
로봇이 특정 물체를 자동으로 인식하고 조작하기 위해서 RGB 영상외에도 깊이 정보를 효율적으로 융합하는 객체 검출 및 분할 프레임워크 개발
Funded by Samsung Electronics (삼성전자 생산기술연구소)
인공지능 융합형 메타휴먼 플랫폼 연구실 (2022.06 ~ 2025.02)
다양한 메타버스 응용분야에 활용할 수 있는 가상 인간모델(메타휴먼) 생성의 기반기술을 연구하고 인간의 외형 뿐 아니라 물리적, 생리적, 심리적 특성들을 표현하고 외부 객체들과 인터랙션 할 수 있는 메타버스 플랫폼 기술을 연구
Funded by National Research Foundation (한국연구재단 기초연구실 지원사업)
인공지능 반도체 융합연구센터 (link) (2022.03 ~ 2025.12)
인공지능 알고리즘 및 시스템반도체 설계의 지식을 갖춘 전문 인력을 목표로 함
Funded by National Research Foundation (시스템 반도체 융합전문인력 양성센터)
동적 질량중심을 가지며 변형 가능한 물체를 인간 수준으로 조작하기 위한 시-촉각 인식 기술 (2021.09 ~ 2023.08)
본 과제는 로봇이 인간 수준으로 물체를 조작하기 위한, “시-촉각 융합” 및 “시-촉각 인식을 통한 연성 변형 물체의 안정적 파지 및 매니퓰레이션 원천 기술 개발을 목표로 함
Funded by Samsung Research Funding & Incubation Center for Future Technology (삼성미래기술 육성사업)
BK21 산업융합형 차세대 인공지능 혁신인재 교육연구단 (link) (2020.09 ~ 2027.08)
4단계 BK21 사업에 참여하며, 국내 최고 수준의 인공지능 분야 글로벌 리더를 양성하고 유기적인 인공지능 특화 산학협력 시스템을 구축하는 것을 목표로 함
Funded by National Research Foundation (교육부 4단계 BK21 사업)
인공지능융합연구센터/ 인공지능융합혁신대학원사업 (link) (2020.04 ~ 2025.12)
과기정통부 인공지능대학원 프로그램에 참여하는 인천지역 최초의 인공지능분야 특화 연구, 교육기관으로서, 인공지능 핵심 기술 연구개발 및 다양한 산업분야에 인공지능 기술을 확산하기 위한 인공지능 인재양성과 기술확산
Funded by Institute for Information & communications Technology Promotion (IITP) (정보통신기획평가원 인공지능융합연구센터/인공지능융합혁신대학원 지원사업)
Completed
Privacy-Preserving Domain Adaptation
Jun 2021 - Present, funded by NRF(한국연구재단) - 기본연구
Ethics of Artificial Intelligence
Jan 2020 – August 2020, funded by AI Research Center, SKT
Object Detection in Drone Images
May 2019 – Dec 2019, funded by AI Research Center, SKT
Unsupervised Video Object Segmentation
Mar 2019 – May 2019, funded by AI Research Center, SKT
Visual Question Answering for Visually Impaired People
Aug 2018 – February 2019, funded by AI Research Center, SKT
Neural Architecture Search for Large Scale Image Classification
Jan 2018 – May 2018, funded by AI Research Center, SKT
Multi-view Face Recognition based on Deep Learning
Aug 2012 – May 2017, funded by Electronics and Telecommunications Research Institute (ETRI)
Person Identification using Facial Attributes (Race, Gender, and Age)
Nov 2013 – October 2015, funded by National Research Foundation (NRF)
Spontaneous Facial Expression Recognition
Aug 2012 – Apr 2015, funded by National Research Foundation (NRF)
Vehicle License Plate Detection and Recognition in Real Environment
Aug 2010 – Feb 2012, funded by AddPac Technology
Academic Activities
Reviewer
International Conference on Computer Vision (ICCV)
Neural Information Processing Systems (NeurIPS)
International Conference on Machine Learning (ICML)
Advancement of Artificial Intelligence (AAAI)
International Journal of Computer Vision (IJCV)
IEEE Transactions on Image Processing (TIP)
IEEE Transactions on Multimedia (TMM)
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)
IEEE Signal Processing Letters (SPL)
Elsevier Neurocomputing
Lecturer
Teck Talk: ‘Latest Artificial Intelligence Trend ’, KISTEP & ETRI, Nov 2022
Course: ‘AI for Business Project’ KAIST Executive MBA, Aug 2022
Course: ‘AI Academy Team Leader Course’ Korean Air, Jul 2022
Lecture: ‘Emerging AI Trends We Need to Know' @KAIST Techno MBA, Mar 2022
Course: ‘Machine Learning & Deep Learning’ @Hanjin AI Academy, Feb 2022
Course: ‘ML Understanding and Applications’ @LG Electronics (H&A 본부), Nov-Dec 2021
Teck Talk: ‘Domain Adaptation Trends’ @ETRI, Mar 2021
Teck Talk: ‘Emerging Computer Vision Trends You Need to Know’ @Yonsei Univ., Jan 2021
Lecture: ‘AI Research Trends You Need to Know’ @KAIST AIC Course, Dec 2020
Lecture: ‘AIR: Artificial Intelligence Research’ at @KAIST MBA Course, Jul 2020
Lecture: ‘Artificial Intelligence Research Trends You Need to Know’ @ KAIST, Apr 2019
Tech Talk: ‘CES 2019: Tech trends’ @SK telecom Tech Expert Board (TEB), Mar 2019
Course: ‘Domain Adaptation & Multimodal Learning’ @Seoul National University, Dec 2018 [Slides] [Video1] [Video2] [Video3]
Conference: ‘Introduction to Bilinear Attention Networks’ @SK ICT Tech Summit 2018, Oct 2018
Course: ‘Overview of Domain Adaptation’ @SK AI Course, May 2018 – Jun 2018
Tech Talk: ‘Deep Domain Adaptation Network for SSPP Face Recognition’ @Naver Tech Talk, Apr 2018 [Slides][Video]
Course: ‘Introduction to Programming using Python’ @KAIST, Sep 2014 – Aug 2017 [Web]
Honors & Awards
Best Paper Award at The 25th Korean MEMS Conference, March 2023
Outstanding Young Researcher Award from the Korea Broadcasting and Media Engineering Society (한국방송·미디어공학회 신진연구자상), Dec 2021
3rd Prize in Vision Meets Drones 2019: A Challenge (ICCV '19), Oct 2019
Title: Patch-level Augmentation for Object Detection in Aerial Images
3rd Prize in Unsupervised DAVIS Challenge on Video Object Segmentation (CVPR '19), Jun 2019
Title: Key Instance Selection for Unsupervised Video Object Segmentation
1st prize in SK telecom Tech Expert Board (TEB) excellent work awards, Oct 2018
Main tasks: 1) SK AI course lecturer 2) Naver tech talk 3) ranked 2nd in VizWiz Challenge
2nd Prize in VizWiz Grand Challenge: Answering Visual Questions from Blind People (ECCV '18), Sep 2018
Title: Bilinear Attention Networks for VizWiz Challenge
Naver Ph.D. Fellowship, Sep 2017
Ph.D. student who has published outstanding papers as the first author in an international top-tier conferences or journals
Outstanding Teaching Assistant Award, KAIST, Feb 2017
Role: Python programming instructor for undergraduates
LG Electronics Paper Award at IEEK Conference, IEEK, Jun 2016
Title: Deep CNN-based Person Identification using Facial and Clothing Features
Winner of Idea Contest for R&D Development Special Zone Support Division, Apr 2012
Title: Research complex childcare system
Award: Special Award
Winner of Future Idea Competition, KOLON-KAIST Life Style Innovation Center, Oct 2011
Title: Realistic sports broadcasting through sharing senses between athletes and viewers
Award: Grand Prize (10,000$)
Patents
Interpretable Face Image Quality Assessment, Dec 16, 2022, 10-2479841 [PDF]
Cross-modal Spatio-channel Attention Blocks for Crowd Counting, Nov 11, 2022, C-2022-047209 [PDF]
Method and Apparatus for Generative Domain Adaptation for Low-Resolution Face Recognition, Oct 6, 2022, 10-2454443 [PDF]
Method and Apparatus for Face Super-resolution using Adversarial Distillation of Facial Region Dictionary, Aug 17, 2022, 10-2434969 [PDF]
Method and Apparatus for Privacy-Preserving Domain Adaptation, Aug 9, 2022, 10-2432003 [PDF]
Adaptive Graph Adversarial Networks for Partial Domain Adaptation, Apr 18, 2022, 10-2389368 [PDF]
Method and Apparatus for Editing of Personalized Face Age via Self-Guidance in Generative Adversarial Networks, Jun 11, 2021, 10-2266165 [PDF]
Apparatus and Method for Providing Heterogeneous Contents Recommendation Model, Oct 15, 2019, 10-2034668 [PDF]
Partial Face Based Person Identification Across Poses, Jul 27, 2018, 10-1884874 [PDF]
System and Method for Compressing Vehicle Image for Detection of License Plate, Nov 6, 2013, 10-1328533 [PDF]
A License Plate Recognition System Under Various Environmental Conditions, Oct 29, 2012, C-2012-021243 [PDF]