Youngtaek Oh

Contact: {firstname}.{lastname} [at] kaist.ac.kr

yto.jpg

I am a Ph.D. student co-advised by Prof. In So Kweon and Prof. Junmo Kim at KAIST, and am currently working as a research intern at LG AI Reseach.

My research interest aims to build robust recognition system for image and video understanding under limited and/or biased data. Towards this goal, I have been working on data-efficient learning techniques in image and video domain. In addition, I have interest in vision and language models, specifically for enhancing visual understanding tasks.

Publications

  1. 2023_cviu_badapters.png
    Empirical study on using Adapters for debiased Visual Question Answering
    Computer Vision and Image Understanding (CVIU), 2023
  2. nice_teaser.png
    NICE 2023 Zero-shot Image Captioning Challenge
    Taehoon Kim, Pyunghwan Ahn, Sangyun Kim, Sihaeng Lee, Mark Marsden, Alessandra Sala, Seung Hwan Kim, Honglak Lee, Kyounghoon Bae, and 33 more authors
    preprint, 2023
  3. self_sufficient.png
    Self-Sufficient Framework for Continuous Sign Language Recognition
    International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023
    Oral presentation, Top 3% recognition of all accepted papers
  4. signing_outside.png
    Signing Outside the Studio: Benchmarking Background Robustness for Continuous Sign Language Recognition
    British Machine Vision Conference (BMVC), 2022
  5. daso.png
    DASO: Distribution-Aware Semantics-Oriented Pseudo-Label for Imbalanced Semi-Supervised Learning
    Youngtaek OhDong-Jin KimIn So Kweon
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
  6. 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 ParkYoungjoon JangYoungtaek Oh, Seokmin Yun, Sukwon Yoon, Chang Jo KimHan-Mu ParkIn So Kweon
    International Conference on Automatic Face and Gesture Recognition (FG), 2021
  7. sideguide.png
    SideGuide: A Large-scale Sidewalk Dataset for Guiding Impaired People
    {Kibaek ParkYoungtaek Oh, Soomin HamKyungdon Joo}*, Hyokyoung Kim, Hyoyoung KumIn So Kweon (*: equally contributed)
    International Conference on Intelligent Robots and Systems (IROS), 2020

Honors and Awards

Jun 2023 Top 3% Recognition Certificates, ICASSP 2023   [Certificate]
May 2023 2nd place in NICE Challenge ($5000), NICE Workshop at CVPR 2023   [Press] [Code]
Oct 2022 Outstanding reviewer award, ECCV 2022.