About Me

I am a Ph.D. candidate at the U-AIM (Artificial Intelligence & Machine Learning) Lab, KAIST (Korea Advanced Institute of Science and Technology), advised by Prof. Chang D. Yoo.

My primary research interests lie in the application of generative models for computer vision, with a recent focus on virtual try-on and multi-modal image/video editing.

If you want to know more about me, please refer to my CV.

News

  • Feb. 2025:   One paper accepted to CVPR 2025.
  • Oct. 2024:   1st place winner of the ‘2nd Seoul National University Bundang Hospital (SNUBH) Datathon’.
  • Jun. 2024:   Two papers accepted to ECCV 2024.

Publications

[*] equal contribution

CVPR 2025
sym

[C8] ITA-MDT:Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On

Ji Woo Hong , Tri Ton, Trung X. Pham, Gwanhyeong Koo, Sunjae Yoon, Chang D. Yoo

Computer Vision and Pattern Recognition (CVPR), 2025

[Project Page]

ECCV 2024
sym

[C7] Dilutional Noise Initialization for Dilution Video Editing

Sunjae Yoon, Gwanhyeong Koo, Ji Woo Hong , and Chang D. Yoo

European Conference on Computer Vision (ECCV), 2024

ECCV 2024
sym

[C6] FlexiEdit: Frequency-Aware Latent Refinement for Enhanced Non-Rigid Editing

Gwanhyeong Koo, Sunjae Yoon, Ji Woo Hong , and Chang D. Yoo

European Conference on Computer Vision (ECCV), 2024

CVPRW 2024
sym

[C5] Zero-shot Dual-Path Integration Framework for Open-Vocabulary 3D Instance Segmentation

Tri Ton *, Ji Woo Hong *, SooHwan Eom, Jun Yeop Shim, Junyeong Kim, and Chang D. Yoo.

Computer Vision and Pattern Recognition Workshop (OpenSUN3D: 2nd Workshop on Open-Vocabulary 3D Scene Understanding) (CVPRW), 2024

Access 2024
sym

[J5] Causal Localization Network for Radar Human Localization with micro-Doppler signature

Sunjae Yoon Gwanhyeong Koo, Jun Yeop Shim, Soohwan Eom, Ji Woo Hong , Chang D. Yoo

IEEE Access, 2024

[code]

ICASSP 2023
sym

[C4] Counterfactual Two-stage Debiasing Network for Video Corpus Moment Retrieval

Sunjae Yoon, Ji Woo Hong , SooHwan Eom, Hee Suk Yoon, Eunseop Yoon, Daehyeok Kim, Junyeong Kim, Chanwoo Kim, and Chang D. Yoo

The International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023, Oral

Access 2023
sym

[J4] Self-Supervised Visual Representation Learning via Residual Momentum

Trung X. Pham, Axi Niu, Zhang Kang, Tee Joshua Tian Jin, Ji Woo Hong , and Chang D. Yoo.

IEEE Access, 2023

Access 2023
sym

[J3] Joint Path Alignment Framework for 3D Human Pose and Shape Estimation from Video

Ji Woo Hong , Sunjae Yoon, Junyeong Kim, and Chang D. Yoo

IEEE Access, 2023

ECCV 2022
sym

[C3] Selective Query-guided Debiasing for Video Corpus Moment Retrieval

[code]

Sunjae Yoon, Ji Woo Hong , Eunseop Yoon, Dahyun Kim , Junyeong Kim, Hee Suk Yoon, and Chang D. Yoo

European Conference on Computer Vision (ECCV), 2022

ICASSP 2022
sym

[C2] SEMANTIC ASSOCIATION NETWORK FOR VIDEO CORPUS MOMENT RETRIEVAL

Dahyun Kim *, Sunjae Yoon *, Ji Woo Hong , and Chang D. Yoo

The International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022. Oral

Sensors 2022
sym

[J2] CE-BART: Cause-and-Effect BART for Visual Comonsense Generation

Junyeong Kim, Ji Woo Hong , Sunjae Yoon, and Chang D. Yoo

MDPI Sensors, 2022

Sensors 2022
sym

[J1] Dual-Scale Doppler Attention for Human Identification

[code]

Sunjae Yoon, Dahyun Kim, Ji Woo Hong , and Chang D. Yoo

MDPI Sensors, 2022

ICIP 2021
sym

[C1] WEAKLY-SUPERVISED MOMENT RETRIEVAL NETWORK FOR VIDEO CORPUS MOMENT RETRIEVAL

[code]

Sunjae Yoon *, Dahyun Kim *, Ji Woo Hong , Junyeong Kim, Kookhoi Kim and Chang D. Yoo

International Conference on Image Processing (ICIP), 2021

Awards

  • Oct. 2024 1st place winner of the ‘2nd Seoul National University Bundang Hospital (SNUBH) Datathon.’
  • Nov. 2023 Winner of Best Paper Award, Winter Conference of Korean Artificial Intelligence Association (KAIA).

Educations

Korea Advanced Institute of Science and Technology (KAIST)

  • Now : Ph.D. candidate in Electrical Engineering (Artificial Intelligence & Machine Learning).

   Advisor: Prof. Chang D. Yoo

  • Aug. 2022 : M.S. in Robotics Program (Artificial Intelligence & Machine Learning).

   Thesis: “Temporal Procrustes Alignment Framework for 3D Human Pose and Shape Estimation from Video”

   Advisor: Prof. Chang D. Yoo

Michigan State University (MSU)

  • May 2019 : B.S. in Mechanical Engineering, minor in Computer Science.

Projects

  • Development and Study of AI Technologies to Inexpensively Conform to Evolving Policy on Ethics (Operator)

   IITP grant funded by the Korea Government (MSIT): Mar. 2022 - present

  • Development of Causal AI through Video Understanding and Reinforcement Learning, and Its Applications to Real Environments (Supporter)

   IITP grant funded by the Korea Government (MSIT): Mar. 2021 - present

  • Development of framework for analyzing, detecting, mitigating of bias in AI model and training data (Operator)

    IITP grant funded by the Korea Government (MSIT): Jan. 2021 – Dec. 2022

Reviewer

  • Conference on Computer Vision and Pattern Recognition (CVPR): 2025
  • International Conference on Computer Vision (ICCV): 2025
  • European Conference on Computer Vision (ECCV): 2024
  • International Conference on Acoustics, Speech & Signal Processing (ICASSP): 2023, 2024

Teaching Assistant

  • Statistical Learning Theory: 2024 Spring, 2024 Fall
  • Introduction to Machine Learning: 2023 Fall
  • Signals and Systems: 2022 Fall, 2023 Spring
  • Seongnam-KAIST Next Generation ICT Research Center. EE Co-op+ Joint Research Program: 2023 Fall, 2024 Spring, 2024 Fall