Minki Jeong(정민기)

Education

• 2016.3 - Present     Combined(M.S. & Ph.D.) (School of Electrical Engineering), Korea Advanced Institute of Science Technology, South Korea 

• 2012.3 - 2016.2       B.S. (School of Electrical Engineering), Korea Advanced Institute of Science Technology, South Korea 

Research Interests

• Computer Vision

• Few-shot learning

• Representation learning

Publications

• Minki Jeong and Changick Kim, "A Parameter Efficient Multi-Scale Capsule Network", Accepted to The 28th IEEE International Conference on Image Processing (ICIP), Anchorage, USA, Sep. 19-22, 2021.

• Minki Jeong, Seokeon Choi, and Changick Kim, "Few-shot Open-set Recognition by Transformation Consistency," Accepted to IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 19-25, 2021.

• Seokeon Choi, Taekyung Kim, Minki Jeong, Hyoungseob Park, and Changick Kim, "Meta Batch-Instance Normalization for Generalizable Person Re-Identification," Accepted to IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 19-25, 2021. 

• Hyoungseob Park, Minki Jeong, Youngeun Kim, and Changick Kim, "Self-Training of Graph Neural Networks using Similarity Reference for Robust Training with Noisy Labels", in Proc. The 27th IEEE International Conference on Image Processing (ICIP), Abu Dhabi, UAE, Oct. 22-28, 2020.

• Jaehoon Choi, Minki Jeong, Taekyung Kim, and Changick Kim, "Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation," British Machine Vision Conference (BMVC), Cardiff, UK, Sep. 9-12, 2019. 

• Taekyung Kim, Minki Jeong, Seunghyeon Kim, Seokeon Choi, and Changick Kim, "Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection," in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, Jun. 16-20, 2019.

• Minki Jeong and Changick Kim, "Effect of Using Object Shape Prior on Visual Object Shape Prior on Visual Object Counting," in Proc. IEEE International Conference on Visual Communications and Image Processing, Taichung, Taiwan, Dec. 9-12, 2018.

• J. Lee, Yoonhyung Kim, Minki Jeong, Changick Kim, D. Nam, J. Lee, S. Moon, and W. Yoo, "3D convolutional neural networks for soccer object motion recognition." 2018 20th International Conference on Advanced Communication Technology (ICACT). IEEE, 2018.

• Minki Jeong and Changick Kim, "Depth estimation from a single image with a communication module between global network and local network", in Proc. International Conference on 3D Systems and Applications (3DSA), Busan, Korea, Aug. 28-31, 2017.

• 구인용, 정민기, 김창익, "극소수 예시 오픈 세트 식별 문제에서의 비관측 범주 이미지 검출 성능 향상," 대한전자공학회 추계학술대회, 김대중컨벤션센터 광주, Nov. 27-28, 2020.

• 박근철, 정민기, 김창익, "메트릭 학습 기반 오픈세트 극소수 학습에 대한 분류 성능 향상," 대한전자공학회 추계학술대회, 김대중컨벤션센터 광주, Nov. 27-28, 2020. 

• 정민기, 김창익, "저랭크 근사를 활용한 파라미터 효율적인 캡슐 네트워크", 제29회 신호처리합동학술대회, 대전, 대한민국, Sep. 26-27, 2019. 15-17

• 박형섭, 정민기, 김창익, "캡슐 네트워크 경량화를 위한 지식의 증류에 대한 연구", 제29회 신호처리합동학술대회, 대전, 대한민국, Sep. 26-27, 2019.

Awards

• 제 27회 휴먼테크논문대상 은상 (2021)

• 대한전자공학회 추계학술대회 우수논문상 (2020)

Workshops

• Large-scale 3d shape reconstruction and segmentation from shapenet core55 (ICCV 2017)