Yoonhyung Kim (김윤형)

Education

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

• 2014.3 - 2016.2          M.S. (School of Electrical Engineering), Korea Advanced Institute of Science and Technology, South Korea

• 2009.3 - 2013.8          B.S. (School of Electrical Engineering), Korea Advanced Institute of Science and Technology, South Korea

Research Interests

• Image Understanding

• Computer Vision

Publications

• Yoonhyung Kim and Changick Kim, "Semi-Supervised Domain Adaptation via Selective Pseudo Labeling and Progressive Self-Training," Accepted to The 25th International Conference on Pattern Recognition (ICPR), Milan, Italy, Jan., 10-15, 2021.

• Yoonhyung Kim, H. Jang, S. Park, J. Lee, and Changick Kim, "Semi-Supervised Synthetic-to-Real Domain Adaptation for Fine-grained Naval Ship Image Classification," in Proc. the 26th International Workshop on Frontiers of Computer Vision (IW-FCV), Ibuski, Japan, Feb. 20-22, 2020.

• Yoonhyung Kim, Chanho Jung, and Changick Kim, "Motion Recognition of Assistant Referees in Soccer Games via Selective Color Contrast Revelation," in Proc. the 26th International Workshop on Frontiers of Computer Vision (IW-FCV), Ibuski, Japan, Feb. 20-22, 2020.

• Seunghan Yang, Yoonhyung Kim, Youngeun Kim, and Changick Kim, "Combinational Class Activation Maps for Weakly Supervised Object Localization," Winter Conference on Applications of Computer Vision (WACV), Colorado, USA, Mar. 2-5, 2020.

• Yoonhyung Kim, Hyunjun Eun, Chanho Jung, and Changick Kim, "A Quad Edge-Based Grid Encoding Model for Content-Aware Image Retargeting," IEEE Transactions on Visualization and Computer Graphics (TVCG), vol. 25, no. 12, pp. 3202-3215, Dec. 2019.

• S. Moon, Yoonhyung Kim, D. Nam, W. Yoo, and Changick Kim, "A Comprehensive Study on the Ship Classification Performance of the Deep Learning Model According to Dataset Difference," International Conference on ICT Convergenge (ICTC), pp. 1428-1430, Jeju, Korea, Oct. 16-18, 2019.

• Yoonhyung Kim and Changick Kim, "2D Pose Recognition for Automatic Basketball Video Analysis," in Proc. the 25th International Workshop on Frontiers of Computer Vision (IW-FCV), Gangneung, Korea, Feb. 20-22, 2019.

• Yoonhyung Kim, Seungjun Jung, Chanho Jung, and Changick Kim, "A Structure-Aware Axis-Aligned Grid Deformation Approach for Robust Image Retargeting," Multimedia Tools and Applications, Vol. 77, no. 6, pp. 7717-7739, Mar. 2018.

• Hyunjun Eun, Yoonhyung Kim, Chanho Jung, and Changick Kim, "Saliency Refinement: Towards a Uniformly Highlighted Salient Object," Signal Processing: Image Communication, vol 62, pp. 16-32, Mar. 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," in Proc. International Conference on Advanced Communication Technology (ICACT), Chuncheon, Korea, Feb. 11-14, 2018.

• Jinsu Kim, Yoonhyung Kim, and Changick Kim, "A Robust Ensemble of ResNets for Character Level End-to-end Text Detection in Natural Scene Images," in Proc. ACM Content-Based Multimedia Indexing (CBMI), Firenze, Italy, Jun. 19-21, 2017.

• 문성원, 김윤형, 이지원, 남도원, 유원영, 김창익, "도메인 적응화를 통한 퓨샷 환경에서의 대한민국 군함 식별 성능향상에 대한 연구", 대한전자공학회 하계종합학술대회, 롯데호텔 제주, Aug. 20, 2020.

• 김창익, 김윤형, "콘텐츠 기반 이미지 리사이징 방법 및 장치", 등록번호: 10-2007738-0000. 등록일자: 2019.07.31.

• 김윤형, 정찬호, 김창익, "영상 리사이징이 심층 신경망 기반 영상 분류기 성능에 미치는 영향에 관한 연구," 한국통신학회논문지, vol. 44, no. 7, pp. 1299-1302, July 2019.

• 김윤형, 김창익, "내용 기반 영상 리타겟팅 기술 동향," 전자공학회지, 제 46권, 제 2호, pp. 28-36, Feb. 2019.

• 김윤형, 은현준, 정찬호, 김창익, "조건부 무작위장을 사용한 세그넷의 시맨틱 영상 분할 성능 향상," 한국통신학회논문지, 제 43권, 제 3호, pp.519-521, Mar. 2018.

• 은현준, 김윤형, 정찬호, 김창익, "단순선형반복군집을 위한 적응적 초기 군집 중심 샘플링 방법," 한국통신학회논문지, 제 43권, 제 1호, pp.20-23, Jan. 2018.

• 김윤형, 최준향, 김종희, 김창익 외 4인, "수정된 안개 제거 기법을 이용한 수중영상 화질 개선", 대한전자공학회 추계학술대회, 한양대학교, Nov. 29, 2014.