Jee-soo Kim
From MIPAL
![]() |
Jee-soo Kim (김지수)
|
Research Interests
- Machine Learning, Weakly-supervised object localization, Object detection
Education
- B.S. Biomedical Engineering, Korea University, 2015
Employment
- Intern at Qualcomm Research Korea. 2019.9 ~ 2019.12
- Intern at Clova AI research team, Naver. 2019.1 ~ 2019.7
- Intern at mechatronics and robotics laboratory, Advanced Institutes of Convergence Technology, SNU. 2014.12 ~ 2015.3
Publication
- Jeesoo Kim, Junsuk Choe, Sangdoo Yun, Nojun Kwak, "Normalization Matters in Weakly Supervised Object Localization", ICCV2021
- Jeesoo Kim, Jangho Kim and Nojun Kwak, "StackNet: Stacking Parameters for Continual learning", CVPR2020 workshop
- Jisoo Jeong, Seungeui Lee, Jeesoo Kim, Nojun Kwak, "Consistency-based Semi-supervised Learning for Object detection", NeurIPS2019
- Byeongho Heo, Jeesoo Kim, Sangdoo Yoon, Hyojin Park, Nojun Kwak, Jin Young Choi, "A Comprehensive Overhaul of Feature Distillation", ICCV2019
- Daesik Kim, Youngjoon Yoo, Jeesoo Kim, Sangkuk Lee and Nojun Kwak, "Dynamic Graph Generation Network: Generating Relational Knowledge from Diagrams", CVPR2018
- Jeesoo Kim, Jaeyoung Yoo, Jangho Kim, Nojun Kwak, "Vehicle Image Generation Going Well with The Surroundings", arXiv, July 2018.
- 김지수, 곽노준, "이동정보를 배제한 위치추정 알고리즘", 제어로봇시스템학회논문지, 22권, 11호, pp.883 - 887, 2016.11
Project
- Multi-Lane detection for autonomous car, Hyundai Motors group 2016.3 ~ 2016.12
- Intelligent system for outdoor security robot, Ministry of Science and ICT 2017.9 ~