Kuhyuen Ko

  • CV Github Mail
    • Education

      MS in Electrical Engineering, 2021. 08.

      UNIST, Korea
      Thesis: Co-appearance based unsupervised clustering for person search
      Advisor: Prof. Jae-Young Sim

    • BS in Electrical and Information Engineering, 2019. 02.

      Seoul National University of Science and Technology, Korea

    • Exchange Student Program, 2018. 08.

      Czech Technical University in Prague, Czech Republic

    My research interests lie in machine learning and computer vision. Particularly, my research topics include

  • Person search (Pedestrian detection, Person re-ID)

  • Metric learning

  • Object detection

  • Unsupervised learning

    • Publications
    International conferences

  • Context-Aware Unsupervised Clustering for Person Search

    Byeong-Ju Han*, Kuhyeun Ko* and Jae-Young Sim (* equal contribution)

    BMVC 2021

    ­ [ paper / code / video ]


  • End-to-End Trainable Trident Person Search Network Using Adaptive Gradient Propagation

    Byeong-Ju Han, Kuhyeun Ko and Jae-Young Sim

    ICCV 2021

    ­ [ paper / code / video ]

    • Domestic conferences

    1. 물체 검출을 위한 색 변환을 이용한 데이터 증가

      고규현, 심재영

      대한전자공학회 하계종합학술대회 2020

    Project & Patent
    Project
    • 정보통신기획평가원, “이동 객체에 대한 증강현실 서비스 실현을 위한 정보-영상 정합기술 연구”
    Patent
    • 심재영, 고규현, “객체 검색 모델 및 그 학습 방법,” 출원번호 10-2020-0166373, 2020.12.02.