Dae Ung Jo
Google ScholarLinkedIn
← Members
Dae Ung Jo
Assistant Professor
School of Electronics Engineering, Kyungpook National University
Research Interests
  • Deep Learning and Machine Learning
  • Multi-Modal / Cross-Modal Learning
  • Representation Learning
  • Computer Vision
  • Out-of-distribution Detection
  • Active Learning
Contact
Email
daeung [dot] jo [at] knu [dot] ac [dot] kr
Tel
+82-53-950-5526
Office
Room 527, IT Building 1, Kyungpook National University, Daegu, South Korea
Education
2016 – 2022
Ph.D., Department of Electrical and Computer Engineering, Seoul National University, Seoul, Korea (Integrated Ph.D. program)
2012 – 2016
B.S., Department of Electrical and Computer Engineering, Seoul National University, Seoul, Korea
Experience
2025 – Present
Assistant Professor, School of Electronics Engineering, Kyungpook National University
2022 – 2025
Staff Engineer, Samsung Advanced Institute of Technology (SAIT), Samsung Electronics (Autonomous Driving Team)

Publications & Patents

Preprint

  1. Preprint
    PreprintUnderstanding Dimensional Collapse in Cross-Modal Feature Distillation
    Dae Ung Jo, Sujin Jang, Jay Heo, and Sung Ju Hwang
    Preprint , 2025
    PDF
  2. arXiv
    PreprintInfluential Rank: A New Perspective of Post-training for Robust Model against Noisy Labels
    Seulki Park, Hwanjun Song, Daeho Um, Dae Ung Jo, Sangdoo Yun, and Jin Young Choi
    arXiv preprint arXiv:2106.07217 , 2021
    arXiv

2026

  1. NeurIPS
    jo2026codebook.png
    ConferenceCodebook-Guided Cross-Modal Knowledge Distillation for Structurally Heterogeneous Features
    Dae Ung Jo, Jongin Lim, YoungJoon Yoo, and Daeho Um
    In Conference on Neural Information Processing Systems (NeurIPS), 2026
    arXiv
  2. NeurIPS
    youn2026final.png
    ConferenceFinAl: Fine-grained Alignment for Detail-Preserving Medical Vision-Language Pretraining
    Jongsu Youn, Dongyoung Lee, JaeHyeong Bae, Sang-Il Choi*, Sangtae Choi*, Dae Ung Jo*, and Jongwon Choi*
    In Conference on Neural Information Processing Systems (NeurIPS), 2026
  3. IEEE Access
    JournalCross-Modal Feature Distillation via Sample-Aware Adaptive Masking
    Dae Ung Jo and Daeho Um
    IEEE Access, 2026
    HTML

2025

  1. IEEE Access
    JournalMulti-Agent Visual Reasoning for Out-of-Distribution Detection in Complex Road Environments
    Jeonghyo Song, Kimin Yun, Dae Ung Jo, Jinyoung Kim, and YoungJoon Yoo
    IEEE Access, 2025
    HTML
  2. AVSS
    ConferenceDistributional Uncertainty for Out-of-Distribution Detection
    Jinyoung Kim, Dae Ung Jo, Kimin Yun, Jeonghyo Song, and YoungJoon Yoo
    In IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS), 2025
    HTML
  3. AVSS
    ConferenceCoT-Segmenter: Enhancing OOD Detection in Dense Road Scenes via Chain-of-Thought Reasoning
    Jeonghyo Song, Kimin Yun, Dae Ung Jo, Jinyoung Kim, and YoungJoon Yoo
    In IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS), 2025
    DOI HTML
  4. AVSS
    ConferenceActive Learning for Finely-Categorized Image-Text Retrieval by Selecting Hard Negative Unpaired Samples
    Dae Ung Jo, Kyuewang Lee, and JaeHo Chung
    In IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS), 2025
    arXiv HTML
  5. PRL
    JournalGenerating Visual-adaptive Audio Representation for Audio Recognition
    Jongsu Youn, Dae Ung Jo, Seungmo Seo, Sukhyun Kim, and Jongwon Choi
    Pattern Recognition Letters, 2025
    DOI HTML

2024

  1. IEEE Access
    JournalC2I-CAT: Class-to-Image Cross Attention Transformer for Out-of-Distribution Detection
    JaeHo Chung, SeokHo Cho, HyunJun Choi, Dae Ung Jo, YoonHo Jung, and Jin Young Choi
    IEEE Access, 2024
    HTML

2023

  1. NeurIPS
    jang2023stxd.png
    ConferenceSTXD: Structural and Temporal Cross-Modal Distillation for Multi-View 3D Object Detection
    Sujin Jang*, Dae Ung Jo*, Sung Ju Hwang, Dongwook Lee, and Daehyun Ji
    In Conference on Neural Information Processing Systems (NeurIPS), 2023
    HTML PDF Poster

2022

  1. IEEE Access
    JournalHow Much a Model Be Trained by Passive Learning Before Active Learning?
    Dae Ung Jo, Sangdoo Yun, and Jin Young Choi
    IEEE Access, 2022
    HTML
  2. IEEE Access
    JournalCongestion-aware Bayesian Loss for Crowd Counting
    Jiyeoup Jeong, Jongwon Choi, Dae Ung Jo, and Jin Young Choi
    IEEE Access, 2022
    HTML

2021

  1. AAAI
    ConferenceClass-Attentive Diffusion Network for Semi-supervised Classification
    Jongin Lim, Daeho Um, Hyung Jin Chang, Dae Ung Jo, and Jin Young Choi
    In 35th AAAI Conference on Artificial Intelligence (AAAI), 2021
    arXiv

2020

  1. AAAI
    jo2020associative.png
    ConferenceAssociative Variational Auto-encoder with Distributed Latent Spaces and Associators
    Dae Ung Jo, ByeongJu Lee, Jongwon Choi, Haanju Yoo, and Jin Young Choi
    In 34th AAAI Conference on Artificial Intelligence (AAAI), 2020
    HTML Supp

2019

  1. AAAI
    ConferenceBackbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-Identification
    Youngmin Ro, Jongwon Choi, Dae Ung Jo, Byeongho Heo, Jongin Lim, and Jin Young Choi
    In 33rd AAAI Conference on Artificial Intelligence (AAAI), 2019
    HTML Website

2017

  1. ICCAS
    ConferenceReal-time Scheme for 3-Dimensional Localizing and Tracking of People in Multiple Camera Settings
    Moonsub Byeon, Sangdoo Yun, Youngmin Ro, Dae Ung Jo, Kikyung Kim, and Jin Young Choi
    In International Conference on Control, Automation and Systems (ICCAS), 2017
    HTML
  2. ISIS
    ConferenceEffect of Learning Rate to Generalization Power
    Dae Ung Jo, Jongwon Choi, and Jin Young Choi
    In International Symposium on Advanced Intelligent Systems (ISIS), 2017
    PDF