Jaeseok Choi

Jaeseok Choi (최재석) 서울대학교 융합과학부 석박사통합과정 ( 2017.3 ~ ) 성균관대학교 컴퓨터공학과 졸업 ( 2017. 2 ) Tel: +82-31-888-9579 e-mail: jaeseok.choi@snu.ac.kr Google Scholar

Research interests : Object Detection, Reinforcement Learning, Deep learning.

Education

• Mar. 2017 ~ Present:

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

• Feb. 2017:

  B.S. in Computer Engineering, SungKyunKwan University, Korea.

Publications

International Journals

[1] Jaeseok Choi, Yeji Song, Yerim Kim, Jaeyoung Yoo, Nojun Kwak, "MD3D: Mixture-Density-based 3D Object Detection in Point Clouds", IEEE Access, vol. 10, pp. 104011-104022, 2022, doi: 10.1109/ACCESS.2022.3210108. (Code)
[2] DongKi Noh, ChangKi Sung, Taeyoung Uhm, Wooju Lee, Hyungtae Lim, Jaeseok Choi, Kyuewang Lee, Dasol Hong, Daeho Um, Inseop Chung, Hochul Shin, Min-Jung Kim, Hyoung-Rock Kim, Seung-Min Baek, Hyun Myung, "X-MAS: Extremely Large-Scale Multi-Modal Sensor Dataset for Outdoor Surveillance in Real Environments", IEEE Robotics and Automation Letters (RA-L), vol. 8, no. 2, pp. 1093-1100, Feb. 2023, doi: 10.1109/LRA.2023.3236569.

International Conferences

[1] Simyung Chang, John Yang, Jaeseok Choi and Nojun Kwak, "Genetic-Gated Networks for Deep Reinforcement Learning", Thirty-second Conference on Neural Information Processing Systems (NeurIPS2018), Montreal, Canada, December 2018. (Poster)
[2] Simyung Chang, YoungJoon Yoo, Jaeseok Choi and Nojun Kwak,"BOOK: Storing Algorithm-Invariant Episodes for Deep Reinforcement Learning", 8th International Conference on Pattern Recognition Applications and Methods (ICPRAM2019), Prague, Czech Republic, February 2019. (Oral)
[3] Jaeseok Choi*, Kyoungmin Lee*, Jisoo Jeong and Nojun Kwak, "Two-Layer Residual Feature Fusion for Object Detection", 8th International Conference on Pattern Recognition Applications and Methods (ICPRAM2019), Prague, Czech Republic, February 2019. (Oral)
[4] Geonseok Seo, Jaeyoung Yoo, Jaeseok Choi, Nojun Kwak, "KL-divergence-based Region Proposal Network for Object Detection", IEEE International Conf. on Image Processing (ICIP 2020), Abu Dhabi, UAE, Oct. 2020. (Poster)
[5] Jaeseok Choi, Yeji Song, Nojun Kwak, "Part-Aware Data Augmentation for 3D Object Detection in Point Cloud", 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021), Prague, Czech Republic, Sep. 2021. (Code)
[6] Kyuewang Lee*, Inseop Chung*, Daeho Um, Jaeseok Choi, Yeji Song, Seunghyeon Seo, Nojun Kwak, Jinyoung Choi, "Multi-modal Object Detection, Tracking, and Action Classification for Unmanned Outdoor Surveillance Robots", 2021 The 21st International Conference on Control, Automation and Systems (ICCAS 2021), Jeju, Korea, Oct. 2021.

Domestic Conferences

[1] 서건석, 유재영, 최재석, 곽노준, " 쿨백-라이블러 발산을 이용한 후보영역 추출 네트워크와 객체 검출", 제 29회 신호처리합동학술대회, 2019년 9월 26일.

Projects

• 파노라마 영상과 사각지대경보(BSD) 기능을 제공하는 카메라 기반의 측후방 통합안전지원 시스템 개발, 산업통상자원부 (2017. 3 ~ 2019. 12)
• 딥러닝 기반 객체 인식 기술성능 고도화, (주)삼성전자 (2017. 9 ~ 2018. 9)
• 실외 무인 경비 로봇을 위한 멀티모달 지능형 정보분석 기술 개발, 과기정통부 (2020. 5 ~ 2021. 12)