Avatar

Jae Won Cho

Postdoctoral Research Associate

Electrical Engineering, KAIST


CV


I am currently a Postdoctoral Research Associate at Multimodal AI Lab at KAIST with Prof. Joon Son Chung. I received my PhD degree at the Electrical Engineering department at KAIST and was advised by Prof. In So Kweon. I earned my B.S. in Electrical Engineering from Georgia Institute of Technology in 2018. My current research interests lie in the general areas of computer vision and deep learning with a particular focus on:

  • Vision & Language
  • Visual Question Answering
  • Active Learning

Contact

  • chojw [at] kaist.ac.kr

  • Bldg N1, Rm 211, 291 Daehak-ro, Yuseong-gu, Daejeon, Korea, 34141

Education

  • Ph.D. in Electrical Engineering

    Aug 2018 - Aug 2023

    KAIST, South Korea

    Advisor: Prof. In So Kweon

  • B.S. in Electrical Engineering

    Aug 2014 - May 2018

    Georgia Institute of Technology, USA

Research Experiences

  • KAIST, Daejeon, South Korea
    Aug 2023 - Present

    Postdoctoral Research Associate, Multimodal AI Lab.
  • KAIST, Daejeon, South Korea
    Aug 2018 - Aug 2023

    Research Assistant, Robotics and Computer Vision Lab.
  • KAIST, Daejeon, South Korea
    Jun 2017 - Aug 2017

    Research Intern, Robotics and Computer Vision Lab.
  • KAIST, Daejeon, South Korea
    Jun 2016 - Aug 2016

    Research Intern, Robotics and Computer Vision Lab.

Publications

  • Empirical study on using Adapters for debiased Visual Question Answering

    Jae Won Cho, Dawit Mureja Argaw, Yeongtaek Oh, Dong-Jin Kim, In So Kweon

    Computer Vision and Image Understanding (CVIU), 2023 (Impact Factor 4.5)

    [ Paper ]

  • Counterfactual Mix-Up for Visual Question Answering

    Jae Won Cho*, Dong-Jin Kim*, Yunjae Jung, In So Kweon (* Equal Contribution)

    IEEE Access, 2023 (Impact Factor 3.9)

    [ Paper ]

  • Technical Report of NICE Challenge at CVPR 2023: Retrieval-based Data Discovery and Fusion for Zero-shot Image Captioning

    Youngtaek Oh, Jae Won Cho, Dong-Jin Kim, In So Kweon, Jumno Kim

    preprint, 2023

    [ Paper ] [ Code ]

  • Generative Bias for Robust Visual Question Answering

    Jae Won Cho, Dong-Jin Kim, Hyeonggon Ryu, In So Kweon

    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2023

    [ Paper ] [ Code ]

    Received Bronze Prize, 28th Samsung Humantech Paper Awards (Top 2.8%)

    Excellent Paper Award IW-FCV

    Also presented at "Workshop on Open-Domain Reasoning Under Multi-Modal Settings" in conjunction with CVPR 2023

  • Self-Sufficient Framework for Continuous Sign Language Recognition

    Youngjoon Jang, Youngtaek Oh, Jae Won Cho, Myungchul Kim, Dong-Jin Kim, In So Kweon, Joon Son Chung

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

    [ Paper ] [ Project ]

    Top 3% recognition of all accepted papers

  • Signing Outside the Studio: Benchmarking Background Robustness for Continuous Sign Language Recognition

    Youngjoon Jang, Youngtaek Oh, Jae Won Cho, Dong-Jin Kim, Joon Son Chung, In So Kweon

    British Machine Vision Conference (BMVC), 2022

    [ Paper ] [ Project ]

  • MCDAL: Maximum Classifier Discrepancy for Active Learning

    Jae Won Cho*, Dong-Jin Kim*, Yunjae Jung, In So Kweon (* Equal Contribution)

    IEEE Transactions on Neural Networks and Learning Systems (TNNLS) 2022 (Impact Factor 14.255)

    [ Paper ]

    Also presented at "The Workshop on Fine-Grained Visual Categorization" in conjunction with CVPR 2022

  • Investigating Top-k White-box and Transferable Black-box Attack

    Chaoning Zhang, Philipp Benz, Adil Karjauv, Jae Won Cho, Kang Zhang, In So Kweon

    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2022

    [ Paper ]

  • Single-Modal Entropy based Active Learning for Visual Question Answering

    Dong-Jin Kim*, Jae Won Cho*, Jinsoo Choi, Yunjae Jung, In So Kweon (* Equal Contribution)

    British Machine Vision Conference (BMVC), 2021

    [ 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

    IEEE International Conference on Computer Vision (ICCV), 2021 [Oral] (acceptance rate 3%)

    [ Paper ]

  • Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation

    Antyanta Bangunharcana, Jae Won Cho, Seokju Lee, In So Kweon, Kyung-Soo Kim, Soohyun Kim

    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021

    [ Paper ] [ Project ] [ Code ]

  • Dealing with Missing Modalities in the Visual Question Answer-Difference Prediction Task through Knowledge Distillation

    Jae Won Cho, Dong-Jin Kim, Jinsoo Choi, Yunjae Jung, In So Kweon

    CVPR Multimodal Learning and Applications Workshop (CVPRW), 2021

    [ Paper ]

    Also presented at "Visual Question Answering Workshop" and "VizWiz Grand Challenge Workshop" in conjunction with CVPR 2021.

  • Optical Flow Estimation from a Single Motion-blurred Image

    Dawit Mureja Argaw, Junsik Kim, Francois Rameau, Jae Won Cho, In So Kweon

    Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021

    [ Paper ] [ Poster ] [ Code ]

Awards & Honors

  • 2nd place in NICE Challenge ($5000), NICE Workshop at CVPR 2023, Jun 2023 [Codalab]
  • Bronze Prize, 28th HumanTech Paper Award, Samsung Electronics Co., Ltd ($5,000), Feb 2022
  • KAIST Scholarship, Full scholarship Ph.D. program, 2018-Present
  • Eta Kappa Nu (HKN), Beta Mu Chapter, Member, 2018
  • High Honor, Georgia Institute of Technology Electrical Engineering, 2018
  • Scholarship of In-State-Tuition Waiver ($10,000 USD), Fall 2017-Spring 2018
  • Georgia Tech Faculty Honors, Spring 2017
  • Georgia Tech Dean's List, Fall 2017, Spring 2015, Fall 2014