Inseop Chung

Inseop Chung (정인섭) 서울대학교 융합과학부 석박통합과정 (2019.03 ~ ) 연세대학교 창의기술경영/컴퓨터과학 학사 졸업 (2019.02) Tel: +82-31-888-9579 e-mail: jis3613@snu.ac.kr Google Scholar

Research Interests

Deep Learning, Computer Vision, Knowledge Distillation, Domain Adaptation

Work Experience

• June 2020 ~ December 2020:

  Research Intern at Naver Webtoons Corporation, Korea.

Education

• Mar. 2019 ~ Present:

  M.S./Ph.D. Student in Graduate School of Convergence Science and Technology, Seoul National University, Korea.

• Feb. 2019:

  B.S. in Computer Science / Creative Technology Management (Double Major), Yonsei University, Korea.

• Oct. 2016 ~ Aug. 2017:

  Exchange Student at Informatik (Computer Science) Department of Technische Universität München (Technical University of Munich), Germany.

Publications

International Conferences

• Kyuewang Lee*, Inseop Chung*, Daeho Um, Jaeseok Choi, Yeji Song, Seunghyeon Seo, Nojun Kwak, Jin Young Choi "Multi-modal Object Detection, Tracking, and Action Classification for Unmanned Outdoor Surveillance Robots", The 21st International Conference on Control, Automation and Systems (ICCAS 2021), Oct. 2021, * indicates equal contribution.
• Inseop Chung, Daesik Kim, Nojun Kwak, "Maximizing Cosine Similarity Between Spatial Features for Unsupervised Domain Adaptation in Semantic Segmentation", arXiv, Feb. 2021.
• Jaeyoung Yoo, Hojun Lee, Inseop Chung, Geonseok Seo, Nojun Kwak, "Training Multi-Object Detector by Estimating Bounding Box Distribution for Input Image", International Conference on Computer Vision 2021 (ICCV 2021), Oct. 2021.
• Inseop Chung, SeongUk Park, Jangho Kim, Nojun Kwak, "Feature-map-level Online Adversarial Knowledge Distillation", Thirty-seventh International Conference on Machine Learning (ICML 2020), July 2020.
• Jangho Kim, Minsung Hyun, Inseop Chung, Nojun Kwak, "Feature Fusion for Online Mutual Knowledge Distillation", 25th International Conference on Pattern Recognition (ICPR 2020), Jan. 2021.

Domestic Conferences

• Hojun Lee, ***Inseop Chung***, Nojun Kwak, "Multi-modal sensor based framework for object detection", The 16th Korea Robotics Society Annual Conference (KRoC 2021), May. 2021

Projects

• Development of multimodal sensor-based intelligent systems for outdoor surveillance robots, 2019.3 ~ present