Seunghan Yang (양승한)

Tel: +82-42-350-7521

E-Mail: seunghan[at]kaist.ac.kr


Education

  • 2019.3 - Present M.S. (School of Electrical Engineering), Korea Advanced Institute of Science and Technology, South Korea
  • 2013.3 - 2019.2 B.S. (Dept. of Electronic Engineering), Sogang University, South Korea


Research Interests

  • Weakly-supervised learning
  • Domain adaptation
  • Graph CNNs
  • Federated learning


Publications

  • Dongki Jung, Seunghan Yang, Jaehoon Choi, and Changick Kim, “Arbitrary Style Transfer Using Graph Instance Normalization,” in The 27th IEEE International Conference on Image Processing (ICIP), Abu Dhabi, UAE, Oct. 22-28, 2020.
  • Seunghan Yang, Yoonhyung Kim, Youngeun Kim, and Changick Kim, "Combinational Class Activation Maps for Weakly Supervised Object Localization," in Proc. IEEE Winter Conference on Applications of Computer Vision (WACV), Colorado, USA, Mar. 2-5, 2020.
  • Seunghan Yang, Seungjun Jung, Heekwang Kang, and Changick Kim, "The Korean Sign Language Dataset for Action Recognition," in Proc. 26th International Conference on MultiMedia Modeling (MMM), Daejeon, Korea, Jan. 5-8, 2020.
  • 양승한, 김영은, 김창익, "그래프 합성곱 신경망을 이용한 부분 도메인 적응 기법," 대한전자공학회 추계학술대회, 라카이 샌드파인 리조트(강원도 강릉시), Nov. 22-23, 2019.
  • 고지은, 양승한, 김창익, "그래프 합성곱 신경망을 이용한 세부 이미지 분류," 대한전자공학회 추계학술대회, 라카이 샌드파인 리조트(강원도 강릉시), Nov. 22-23, 2019.
  • 양승한, 정승준, 강희광, 김창익, "한국 수화 인식을 위한 데이터셋," 대한전자공학회 하계종합학술대회, 메종글래드 제주, Jun.26-28, 2019