Avatar

Kwanyong Park

Research Scientist

ETRI


CV | Google Scholar | Github


I am a Research Scientist at Electronics and Telecommunications Research Institute (ETRI).

I received Ph.D. and M.S. degrees in Electrical Engineering from the Korea Advanced Institute of Science and Technology (KAIST), where I was advised by In So Kweon. During my Ph.D. studies, I interned at Adobe Research and was honored with the Qualcomm Innovation Fellowship.

My research aims to build robust multi-modal AI models capable of understanding and generating complex real-world scenarios, with a specific focus on co-designing effective data and learning frameworks. My primary research interests include the following areas, but also open to exploring other challenging and impactful problems.

  • Scalable and Efficient Learning
    - Multimodal Learning & Data-efficient Learning
  • Data-centric AI
    - Effective Large-scale Dataset Collection, Generation, and Curation
  • Generative AI
    - Image/Video Generation & Multi-modal Large Language Models

Contact

  • pkyong7 [at] etri.re.kr

    pkyong7 [at] kaist.ac.kr

  • 218, Gajeong-ro, Yuseong-gu, Daejeon, Republic of Korea, 34129

Education

  • PhD, Major in EE, KAIST, 2023

    on "Towards Universal Visual Scene Understanding in the Wild"

    Advisor: Prof. In So Kweon

  • MS, Major in EE, KAIST, 2019

    on "Learning unpaired video-to-video translation for domain adaptation"

    Advisor: Prof. In So Kweon

  • BS, Double Major in ME and EE, KAIST, 2018

Research Experiences

  • ETRI, Daejeon, Korea (Military Service)
    Sep 2023 - Present

    Research Scientist, Visual Intelligence Lab
  • Adobe Research, San Jose, CA (Remote)
    Apr 2021 - Dec 2021

    Research Intern, Deep Learning Group, Creative Intelligence Lab
    Mentor : Joon-Young Lee, SeoungWug Oh
  • KAIST, Daejeon, Korea
    Mar 2018 - Aug 2023

    Graduate Student Researcher, Robotics and Computer Vision Lab.

Publications

  • A Multimodal Chain of Tools for Described Object Detection

    Kwanyong Park, Youngwan Lee, Yong-Ju Lee

    NeurIPS 2024 Workshop on Compositional Learning

    [ Paper ]

  • KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis

    Youngwan Lee, Kwanyong Park, Yoorhim Cho, Yong-Ju Lee, Sung Ju Hwang

    NeurIPS 2024

    *Also presented at CVPR 2024 Workshop on "Generative Models for Computer Vision"

    Media coverage: covered by YTN, Yonhap News, AI Times, and many local media

    [ Paper / Project page / Code ]

  • Weak-to-Strong Compositional Learning from Generative Models for Language-based Object Detection

    Kwanyong Park, Kuniaki Saito, Donghyun Kim

    ECCV 2024

    *Also presented at CVPR 2024 Workshop on "Generative Models for Computer Vision"

    3rd place in the OmniLabel Challenge @ ECCV2024

    [ Paper ]

  • MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark

    Sanghyun Woo*, Kwanyong Park*, Inkyu Shin*, Myungchul Kim*, In So Kweon

    CVPR 2024

    [ Paper / Project page ]

  • Test-time Adaptation in the Dynamic World with Compound Domain Knowledge Management

    Junha Song, Kwanyong Park, Inkyu Shin, Sanghyun Woo, Chaoning Zhang, and In So Kweon

    RAL-ICRA 2024

    [ Paper ]

  • Joint Self-supervised Learning and Adversarial Adaptation for Monocular Depth Depth Estimation from Thermal Image

    Ukcheol Shin, Kwanyong Park, Byeong-Uk Lee, Kyunghyun Lee, In So Kweon

    MVA 2023

    [ Paper ]

  • Mask-guided Matting in the Wild

    Kwanyong Park, Sanghyun Woo, Seoung Wug Oh, In So Kweon, Joon-Young Lee

    CVPR 2023

    [ Paper ]

  • Bidirectional Domain Mixup for Domain Adaptive Semantic Segmentation

    Daehan Kim*, Minseok Seo*, Kwanyong Park, Inkyu Shin, Sanghyun Woo, In So Kweon, Dong-Geol Choi

    AAAI 2023

    [ Paper ]

  • Learning Classifiers of Prototypes and Reciprocal Points for Universal Domain Adaptation

    Sungsu Hur, Inkyu Shin, Kwanyong Park, Sanghyun Woo, In So Kweon

    WACV 2023

    [ Paper ]

  • Self-supervised Monocular Depth Estimation from Thermal Images via Adversarial Multi-spectral Adaptation

    Ukcheol Shin, Kwanyong Park, Byeong-Uk Lee, Kyunghyun Lee, In So Kweon

    WACV 2023

    Received Best Student Paper Award in WACV 2023

    [ Paper ]

  • Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection

    Sanghyun Woo, Kwanyong Park, Seoung Wug Oh, In So Kweon, Joon-Young Lee

    ECCV 2022

    [ Paper ]

  • Tracking by Associating Clips

    Sanghyun Woo, Kwanyong Park, Seoung Wug Oh, In So Kweon, Joon-Young Lee

    ECCV 2022

    [ Paper ]

  • Per-Clip Video Object Segmentation

    Kwanyong Park, Sanghyun Woo, Seoung Wug Oh, In So Kweon, Joon-Young Lee

    CVPR 2022

    [ Paper / Code ]

  • Unsupervised Domain Adaptation for Video Semantic Segmentation

    Inkyu Shin*, Kwanyong Park*, Sanghyun Woo, In So Kweon (*: equal contribution)

    arXiv

    [ Paper ]

  • LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation

    Inkyu Shin, Dong-Jin Kim, Jae Won Cho, Sanghyun Woo, Kwanyong Park, In So Kweon

    ICCV 2021 [Oral]

    Received Qualcomm Innovation Award 2021

    [ Paper ]

  • Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation

    Kwanyong Park, Sanghyun Woo, Inkyu Shin, In So Kweon

    NeurIPS 2020

    Received Qualcomm Innovation Award 2021

    [ Paper ]

  • Align-and-Attend Network for Globally and Locally Coherent Video Inpainting

    Sanghyun Woo, Dahun Kim, Kwanyong Park, Joon-Young Lee, In So Kweon

    BMVC 2020

    [ Paper ]

  • Preserving Semantic and Temporal Consistency for Unpaired Video-to-Video Translation

    Kwanyong Park, Sanghyun Woo, Dahun Kim, Donghyeon Cho, In So Kweon

    MM 2019

    [ Paper ]

Awards & Honors

  • 3rd place in the OmniLabel Challenge @ ECCV2024
  • WACV Best Student Paper Awards, Jan 2023
  • Qualcomm Innovation Fellowship ($4,000), Nov 2021
  • SIGMM Student Travel Grants, ACM SIGMM ($1,500), Nov 2019
  • Best M.S students, Eun Chong-Kwan Scholarship, KAIST ($2,000), Mar 2018

Academic Activities

Reviewer

  • Conference on Computer Vision and Pattern Recognition (CVPR): 2022~
  • Conference on Neural Information Processing Systems (NeurIPS): 2024~
  • International Conference on Computer Vision (ICCV): 2023~
  • European Conference on Computer Vision (ECCV): 2022~
  • Transactions on Pattern Analysis and Machine Intelligence (TPAMI): 2022~
  • Transactions on Multimedia (TMM): 2023~
  • Association for the Advancement of Artificial Intelligence (AAAI): 2023~
  • British Machine Vision Conference (BMVC): 2020~

Invited Talks

  • Institute of Embedded Engineering of Korea, Nov 2024
  • Korea Artificial Intelligence Conference, Sep 2024