Sungyeon Kim

Ph.D. @ POSTECH | Upcoming Applied Research Scientist @ Amazon

  sungyeon.kim@postech.ac.kr

I will join Amazon Visual Search Team as an Applied Research Scientist starting in August 2025. I completed Ph.D. at Computer Science and Engineering, POSTECH under the supervision of Prof. Suha Kwak. My research focuses on deep metric learning, representation learning, retrieval, and their applications.



News

[Jun, 2025] Our Generative Universal Retrieval, GENIUS code is published in github.
[Apr, 2025] 📄 Our video-text retrieval paper has been selected for an oral presentation in CVPR 2025.
[Mar, 2025] 🎓 Selected to present at Doctoral Consortium in CVPR 2025.
[Mar, 2025] 📄 Two papers are accepted in CVPR 2025.
[Feb, 2025] 🎉 I will join Amazon Visual Search Team as an Applied Research Scientist.
[Feb, 2025] 🎉 I graduated as a recipient of Alumni Award at POSTECH.

Publications

Conference Papers

GENIUS: A Generative Framework for Universal Multimodal Search

Sungyeon Kim, Xinliang Zhu, Xiaofan Lin, Muhammet Bastan, Douglas Gray, Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

Paper Code Project Page Bibtex

Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval

Boseung Jeong, Jicheol Park, Sungyeon Kim, Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Oral Presentation (3.3% acceptance rate)

Paper Bibtex

Learning Unified Distance Metric Across Diverse Data Distributions
with Parameter-Efficient Transfer Learning

Sungyeon Kim, Donghyun Kim, Suha Kwak
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025

Paper Bibtex

Efficient and Versatile Robust Fine-Tuning of Zero-shot Models

Sungyeon Kim, Boseung Jeong, Donghyun Kim, Suha Kwak
European Conference on Computer Vision (ECCV) , 2024

Paper Project Page Bibtex

FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditions

Sohyun Lee, Namyup Kim, Sungyeon Kim, Suha Kwak
European Conference on Computer Vision (ECCV) , 2024

Paper Project Page Bibtex

PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization

Junhyeong Cho, Gilhyun Nam, Sungyeon Kim, Hunmin Yang, Suha Kwak
International Conference on Computer Vision (ICCV), 2023

Paper Project Page Bibtex

HIER: Metric Learning Beyond Class Labels via Hierarchical Regularization

Sungyeon Kim, Boseung Jeong, Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Qualcomm Innovation Fellowship Finalist

Paper Code Project Page Bibtex

Cross-Domain Ensemble Distillation for Domain Generalization

Kyungmoon Lee, Sungyeon Kim, Suha Kwak
European Conference on Computer Vision (ECCV), 2022

Paper Code Bibtex

Combating Label Distribution Shift for Active Domain Adaptation

Sehyun Hwang, Sohyun Lee, Sungyeon Kim, Jungseul Ok, Suha Kwak
European Conference on Computer Vision (ECCV), 2022
IPIU Best Paper Award, BK21 Best Paper Award, Qualcomm Innovation Fellowship Winner

Paper Code Bibtex

Self-Taught Metric Learning without Labels

Sungyeon Kim, Dongwon Kim, Minsu Cho, Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
BK21 Best Paper Award, Qualcomm Innovation Fellowship Winner

Paper Code Project Page Bibtex

Learning to Generate Novel Classes for Deep Metric Learning

Kyungmoon Lee, Sungyeon Kim, Seunghoon Hong, Suha Kwak
British Machine Vision Conference (BMVC), 2021

Paper Bibtex

Embedding Transfer with Label Relaxation for Improved Metric Learning

Sungyeon Kim, Dongwon Kim, Minsu Cho, Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
BK21 Best Paper Award, IPIU Best Paper Award Winner

Paper Code Project Page Bibtex

Proxy Anchor Loss for Deep Metric Learning

Sungyeon Kim, Dongwon Kim, Minsu Cho, Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020

Paper Code Project Page Bibtex

Deep Metric Learning Beyond Binary Supervision

Sungyeon Kim, Minkyo Seo, Ivan Laptev, Minsu Cho, Suha Kwak
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Oral Presentation (5.6% acceptance rate), Qualcomm Innovation Fellowship Winner

Paper Code Project Page Bibtex

Education

Computer Vision Lab, POSTECH (Pohang University of Science and Technology)

Ph.D at Computer Science and Engineering
  • Advised by Prof. Suha Kwak.
  • Recipient of the Alumni Award.
  • Dissertation: Towards Retrieval at Scale via Compact Embeddings and Generative Modeling
  • Committee: Suha Kwak, Minsu Cho, Seungyong Lee, Jungseul Ok, Bohyung Han
    • Pohang, S.Korea
    Sep. 2018 - Feb. 2025

    DGIST (Daegu Gyeongbuk Institute of Science and Technology)

    B.S at Undergraduate Studies
    Daegu, S.Korea
    Mar. 2014 - Feb. 2018

    Experience

    Applied Scientist Intern, Amazon

    Research Intern
  • Research with Xinliang Zhu.
  • Researched on generative multimodal retrieval framework.
    • Palo Alto, CA
    Jun. 2024 - Sep. 2024

    MIT-IBM Watson AI Lab

    Research Collaboration
  • Research with Donghyun Kim.
  • Researched on parameter-efficient learning and deep metric learning.
    • Cambridge, MA (Remote)
    Dec. 2022 - Sep. 2023

    Vision Team, Naver

    Research Intern
  • Research with Geonmo Gu, Byungsoo Ko.
  • Researched on self-supervised learning.
    • Seongnam, S.Korea (Remote)
    Apr. 2022 - Jul. 2022

    Awads & Honors

    2025
  • Alumni Award, POSTECH
    • 2024
  • Qualcomm Innovation Fellowship Korea, Qualcomm Technologies Inc.
      Winner - Efficient and Versatile Robust Fine-Tuning of Zero-shot Models
    • 2023
  • Google PhD Fellowship Program, Google
  • BK21 Best Paper Award, Dept.CSE, POSTECH
      Winner - Self-Taught Metric Learning without Labels
  • BK21 Best Paper Award, Dept.CSE, POSTECH
      Winner - Combating Label Distribution Shift for Active Domain Adaptation
    • 2022
  • Qualcomm Innovation Fellowship Korea, Qualcomm Technologies Inc.
      Winner - Self-Taught Metric Learning without Labels
  • Qualcomm Innovation Fellowship Korea, Qualcomm Technologies Inc.
      Winner - Combating Label Distribution Shift for Active Domain Adaptation
  • BK21 Best Paper Award, Dept.CSE, POSTECH
      Winner - Embedding Transfer with Label Relaxation for Improved Metric Learning
  • IPIU Best Paper Award, Workshop on Image Processing and Image Understanding (IPIU)
      Gold Prize - Offline Active Domain Adaptation
  • CVPR Outstanding Reviewer, IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2021
  • ICT Paper contest, Etnews, Webcash Group, and KSFC
      2nd place Prize - Deep Metric Learning Beyond Binary Supervision
  • SKT AI Fellowship, SK Telecom Co., Ltd
  • POSTECHIAN Fellowship, POSTECH
  • IPIU Best Paper Award, Workshop on Image Processing and Image Understanding (IPIU)
      Grand Prize - Embedding Transfer with Label Relaxation for Improved Metric Learning
    • 2020
  • Naver Ph.D Fellowship, NAVER Corp.
  • Qualcomm Innovation Fellowship Korea, Qualcomm Technologies Inc.
      Winner - Deep Metric Learning Beyond Binary Supervision

    • Academic Services

    International Conference Reviewer

  • IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
      (Outstanding Reviewer in 2022 and 2025)
  • International Conference on Computer Vision (ICCV)
  • European Conference on Computer Vision (ECCV)
  • International Conference on Machine Learning (ICML)
  • International Conference on Learning Representations (ICLR)
  • Conference on Neural Information Processing Systems (NeurIPS)
  • AAAI Conference on Artificial Intelligence (AAAI)
  • IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
  • Asian Conference on Computer Vision (ACCV)
  • International Conference on Machine Vision Applications (MVA)
  • International Conference on Pattern Recognition (ICPR)


    • International Journal Reviewer

  • Transactions on Pattern Analysis and Machine Intelligence (TPAMI), IEEE
  • International Journal of Computer Vision (IJCV)