Avatar

Kwanyong Park

Ph.D Candidate

Electrical Engineering, KAIST


CV | Google Scholar | Github


I am a Ph.D. student advised by Professor In So Kweon, at Electrical Engineering, KAIST.

I am broadly interested in computer vision and machine learning. Specifically, my research interests include

  • Simulated Learning and Domain Adaptation
  • Unsupervised and Self-supervised Learining
  • Image and Video Processing (Synthesis, Translation)
but not limited to.

Contact

  • pkyong7 [at] kaist.ac.kr

  • Bldg N1, Rm 211, 291 Daehak-ro, Yuseong-gu, Daejeon, Korea, 34141

Education

  • MS, Major in Electrical Engineering, 2019

    KAIST, Korea

    Thesis: "Learning unpaired video-to-video translation for domain adaptation"

    Advisor: Prof. In So Kweon

  • BS, Double Major in Mechanical Engineering and Electrical Engineering, 2018

    KAIST, Korea

Research Experiences

  • KAIST, Daejeon, Korea
    Mar 2018 - Present

    Research Assistant, Robotics and Computer Vision Lab.

Publications

  • Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation

    Kwanyong Park, Sanghyun Woo, Inkyu Shin, Inso Kweon

    NeurIPS 2020

    [ paper ]

  • Align-and-Attend Network for Globally and Locally Coherent Video Inpainting

    Sanghyun Woo, Dahun Kim, KwanYoung Park, Joon-Young Lee, In So Kweon

    BMVC 2020

    [ paper ]

  • Preserving Semantic and Temporal Consistency for Unpaired Video-to-Video Translation

    Kwanyong Park, Sanghyun Woo, Dahun Kim, Donghyeon Cho, In So Kweon

    MM 2019

    [ paper ]

Awards & Honors

  • SIGMM Student Grants, ACM SIGMM ($1,500)
  • Best M.S students entering 2018, Eun Chong-Kwan Scholarship, KAIST ($2,000)

Academic Activities

Reviewer

  • British Machine Vision Conference (BMVC) 2020