Daesik Kim

From MIPAL
Jump to: navigation, search
Kds.jpg Daesik Kim (김대식)

서울대학교 융합과학부 석박사통합과정 (2014.09 ~ )
포항공과대학교 산업경영공학과 졸업 (2007.08)


Tel: +82-31-888-9579
e-mail: daesik.kim@snu.ac.kr


Research Interests

  • Machine Learning, Multi-modal Deep Learning, Knowledge based Deep learning


Education

  • B.Sc. Industrial Engineering and Management, Pohang University of Science and Technology, 2007


Employment

  • System developer, Programmer(Powerbuilder, Oracle), Mega IT. 2002-2005
  • Assistant Manager ,Tresury department, Kookmin bank, 2007-2014
  • Founder & CTO in V.DO, 2017~


Publication

  • Seo, J., Kim, D., Suh, B., & Lee, J. (2015, April). Design of a Smart TV Logging System Using Beacons and Smartphones. In Proceedings of the 33rd Annual ACM Conference Extended Abstracts on Human Factors in Computing Systems (pp. 2157-2162). ACM.
  • 멀티모달 딥러닝을 이용한 음악 장르 분류. HCI KOREA 2016
  • Daesik Kim, Myunggi Lee and Nojun Kwak, "Matching Video Net: Memory-based embedding for video action recognition", International Joint Conference on Neural Networks 2017 (IJCNN2017), Anchorage, AK, May 2017.
  • Sangkuk Lee, Daesik Kim, Myunggi Lee, Jihye Hwang and Nojun Kwak, "Where to Play: Retrieval of video segments using natural-language queries", arXiv, July 2017


Competition

  • 4th place of "Textbook Question Answering Challenge", CVPR 2017 Workshop on Visual Understanding Across Modalities


Teaching

  • Tensorflow tutorial at OSIA (Aug. 2016)
  • Tensorflow tutorial at CONTECH (Apr. 2017)