Youngtaek Oh

Contact: {firstname}.{lastname} [at]

Room #211, N1 Bldg, KAIST.

I am currently a Ph.D. student co-advised by Prof. In So Kweon and Prof. Junmo Kim at KAIST. My research aims to effectively train deep neural networks under limited labels and data, such as long-tailed/biased labels and unlabeled data. Also, I have a broad interest in techniques for learning general representations and improving model’s robustness to distribution shifts, such as uni-/multi-modal representation learning, domain generalization, etc.


  1. self_sufficient.png
    Self-Sufficient Framework for Continuous Sign Language Recognition
    Youngjoon Jang Youngtaek OhJae Won ChoMyungchul Kim, Dong-Jin KimIn So Kweon, Joon Son Chung
    In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023.
  2. signing_outside.png
    Signing Outside the Studio: Benchmarking Background Robustness for Continuous Sign Language Recognition
    Youngjoon Jang Youngtaek OhJae Won ChoDong-Jin KimJoon Son ChungIn So Kweon
    In British Machine Vision Conference (BMVC), 2022.
  3. daso.png
    DASO: Distribution-Aware Semantics-Oriented Pseudo-Label for Imbalanced Semi-Supervised Learning
    Youngtaek OhDong-Jin KimIn So Kweon
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
  4. ksl_guide.png
    KSL-Guide: A Large-scale Korean Sign Language Dataset Including Interrogative Sentences for Guiding the Deaf and Hard-of-Hearing
    Soomin Ham, Kibaek Park, Youngjoon Jang Youngtaek OhSeokmin Yun, Sukwon Yoon, Chang Jo Kim, Han-Mu ParkIn So Kweon
    In International Conference on Automatic Face and Gesture Recognition (FG), 2021.
  5. sideguide.png
    SideGuide: A Large-scale Sidewalk Dataset for Guiding Impaired People
    {Kibaek Park,  Youngtaek OhSoomin Ham, Kyungdon Joo}*Hyokyoung Kim, Hyoyoung Kum, In So Kweon (*: equal contributions)
    In International Conference on Intelligent Robots and Systems (IROS), 2020.