Juhong Min

Ph.D.

profile
Pohang, South Korea
{first name}m999 at postech.ac.kr
Google Scholar
GitHub
CV

I am a postdoctoral researcher in Graduate School of Artificial Intelligence (GSAI) at POSTECH. My current research interest is in learning visual correspondence and foundation models for robotics. I am a member of the computer vision lab at POSTECH, working with Professor Minsu Cho.

Education

  • Pohang University of Science and Technology, Pohang, Korea
      Ph.D. (Computer Science and Engineering)
      Learning Visual Correspondence: Exploring Multi-Level Neural Features and High-Dimensional Transforms
      Advisor: Professor Minsu Cho
    • (Sep 2018 - Feb 2024)
  • The Pennsylvania State University - University Park campus, State College, PA
      B.S. (Computer Science and Engineering)
    • (Sep 2011 - Dec 2014)

    Work experience

  • Postdoctoral Researcher (Pohang University of Science and Technology, Pohang, Korea)
      Research focus: Foundation models for robotics
    • (Mar 2024 - now)
  • Student Researcher (Google Research, Grenoble, France)
      Research focus: Modular reasoning for video question answering
      Published a CVPR paper MoReVQA during the internship
    • (Jul 2023 - Mar 2024)
  • Research Intern (Microsoft Research Asia, Remote)
      Research focus: Biologically inspired image representation learning
      Published a NeurIPS paper PerViT during the internship
    • (Oct 2021 - Apr 2022)
  • Interim Associate Software Engineer (Electronic Arts Korea Inc., Seoul, Korea)
      Developed and maintained FIFA Online 3 client/front-end UI modules.
    • (Jan 2018 - Mar 2018)

    Professional services

  • Webmaster, International Conference on Computer Vision (ICCV) 2019
  • Regular reviewer, in CVPR, ICCV, ECCV, NeurIPS, ICML, AAAI, TPAMI, IJCV, WACV, MVA

    • Honors and Awards

  • IPIU Best Paper Award (2024), 3D Geometric Shape Assembly via Efficient Point Cloud Matching
  • CSE oustanding research award (2024), in CSE at POSTECH
  • Best Ph.D Dissertation Award (2024), in CSE, GSAI, EE, CITE at POSTECH
  • BK21 outstanding paper awards (2023)
  • Google PhD Fellowship (2022), Machine Perception, Speech Technology, and Computer Vision
  • Outstanding reviewer at CVPR (2022), Awarded to top 5% reviewers
  • POSTECHIAN Fellowship Award (2022)
  • BK21 outstanding paper awards (2022)
  • Qualcomm Innovation Fellowship Korea (2021), Convolutional Hough Matching Networks
  • Outstanding reviewer at ICCV (2021), Awarded to top 5% reviewers
  • The 1st POSTECH research performance contest (2021), Fourth prize
  • NAVER Ph.D Fellowship Award (2020)
  • Best term project presentation award (2019), In-class achievements

    • Publications

  • 3D Geometric Shape Assembly via Efficient Point Cloud Matching ICML 2024
  • MoReVQA: Exploring Modular Reasoning Models for Video Question Answering CVPR 2024
  • Efficient Semantic Matching with Hypercolumn Correlation WACV 2024 (oral, best paper finalist)
  • Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence TPAMI 2023
  • Peripheral Vision Transformer NeurIPS 2022
  • TransforMatcher: Match-to-Match Attention for Semantic Correspondence CVPR 2022
  • Relational Embedding for Few-Shot Classification ICCV 2021
  • Hypercorrelation Squeeze for Few-Shot Segmentation ICCV 2021
  • Convolutional Hough Matching Networks CVPR 2021 (oral)
  • Learning to Distill Convolutional Features into Compact Local Descriptors WACV 2021
  • Learning to Compose Hypercolumns for Visual Correspondence ECCV 2020
  • SPair-71k: A Large-scale Benchmark for Semantic Correspondence arXiv preprint 2019
  • Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features ICCV 2019

    • Military obligation

  • Rifleman (59 ASP & 102 Replacement Battalion, Chuncheon, Korea)
      Carried out obligatory duty of national defense.
    • (Jun 2015 - Mar 2017)

    Language skills

  • Korean (native)
  • English (fluent)