jhcho5.png

I am a researcher passionate about computer vision and machine learning, who studied at POSTECH, Stanford, UIUC and UC Berkeley. I received my B.S. degree from POSTECH with Summa Cum Laude in 2022. I have published research papers at CVPR, ICCV and ECCV, and been recognized as an outstanding reviewer at ICCV 2023.

My research aims to achieve human-level AI systems that perceive and understand the 3D world for effective interactions with humans. To this end, I focus on (i) 3D/4D reconstruction from everyday photo/video in real time and (ii) Autonomous reasoning on human behavior and interactions with surrounding objects and scenes. These questions guide my research:

  • 3D Vision: How could we enable AI to comprehend the 3D world as humans do?
  • Model Robustness: How could we build robust AI suitable for deployment in real-world scenarios?
  • Multi-modal Learning: How could we exploit various modalities for effective interactions with humans?
  • Self-supervised Learning: How could we encourage AI to comprehend the underlying structure of the world?
  • Efficient Learning: How could we efficiently utilize large-scale models or deploy AI in real time?

Education

Feb. 2018 - Feb. 2022 POSTECH, Pohang, South Korea
B.S. in Computer Science and Engineering
Summa Cum Laude
June 2021 - Aug. 2021 Stanford University, California, United States
International Exchange Program (Summer 2021)
GPA: 4.3/4.3
Jan. 2021 - May 2021 UIUC, Illinois, United States
International Exchange Program (Spring 2021)
GPA: 4.0/4.0
Aug. 2018 - Dec. 2018 UC Berkeley, California, United States
International Exchange Program (Fall 2018)

Selected Publications

  1. PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
    Junhyeong Cho, Gilhyun Nam, Sungyeon Kim, Hunmin Yang, and Suha Kwak
    IEEE/CVF International Conference on Computer Vision (ICCV), 2023
    Paper Project Page
  2. Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers
    Junhyeong Cho, Kim Youwang, and Tae-Hyun Oh
    European Conference on Computer Vision (ECCV), 2022
    Paper Project Page
  3. Collaborative Transformers for Grounded Situation Recognition
    Junhyeong Cho, Youngseok Yoon, and Suha Kwak
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
    Paper Project Page

Honors and Awards

ICCV Outstanding Reviewer (2023), IEEE/CVF International Conference on Computer Vision
  • Selected as top 1.89% among 6990 reviewers at ICCV 2023
Best Research Project Award (2022), POSTECH
  • Selected as the first place among 48 undergraduate CSE research projects
Stanford International Honors Program Student (2021), Stanford University
  • Selected as one of 2 distinguished POSTECH students for Stanford’s acadmeic program
Minister Award (2021), Ministry of Science and ICT
  • Selected as the first place among 5 research projects
University Representative of POSTECH (2021), Young Engineers Honor Society
  • Selected as the university representative in 2021
KFAS Undergraduate Student Scholarship (2020-2022), Korea Foundation for Advanced Studies
  • Selected as one of outstanding undergraduate students nationwide
Young Engineers Honor Society Member (2019-2022), The National Academy of Engineering of Korea
  • Selected as one of 3 distinguished POSTECH students

Professional Services

Conference Reviewer
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • IEEE/CVF International Conference on Computer Vision (ICCV) [Outstanding Reviewer in 2023]
  • European Conference on Computer Vision (ECCV)
  • Advances in Neural Information Processing Systems (NeurIPS)
  • AAAI Conference on Artificial Intelligence (AAAI)
  • British Machine Vision Conference (BMVC)
  • Asian Conference on Computer Vision (ACCV)