avatar

Junho Kim

Ph.D. Student
Korea Advanced Institute of Science and Technology
arkimjh@kaist.ac.kr


About Me

Hello, my name is Junho Kim, a Ph.D. candidate in Electrical Engineering at Korea Advanced Institute of Science and Technology. I am researching in Image and Video Systems Lab., under the supervision of Professor Yong Man Ro. I have experiences with mainly machine learning, deep learning, and computer vision. Now I am more focusing on large vision-language models, model robustness & safety, explainable ai, and causal inference.

Research Interests

Education

News

Publications

    International Journal

  1. TIP
    Robust Perturbation for Visual Explanation: Cross-Checking Mask Optimization to Avoid Class Distortion
    Junho Kim, Seongyeop Kim, Seong Tae Kim, Yong Man Ro
    IEEE Transactions on Image Processing (TIP), 2021
    PDF Code BibTex IF = 10.856

  2. Under Review
    Causal Unsupervised Semantic Segmentation
    Junho Kim*, Byung-Kwan Lee*, Yong Man Ro (* Co-First Authors)
    Under Review
    PDF Code BibTex

    3. International Conference

  3. Under Review
    ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding
    Hosu Lee*, Junho Kim*, Hyunjun Kim, Yong Man Ro (* Co-First Authors)
    Under Review
    PDF Code Project Page BibTex

  4. Under Review
    DIP-R1: Deep Inspection and Perception with RL Looking Through and Understanding Complex Scenes
    Sungjune Park*, Hyunjun Kim*, Junho Kim, Seongho Kim, Yong Man Ro (* Co-First Authors)
    Under Review
    PDF Code Project Page BibTex

  5. Under Review
    Look Every Frame All at Once: Video-Ma2mba for Efficient Long-form Video Understanding with Multi-Axis Gradient Checkpointing
    Hosu Lee*, Junho Kim*, Hyunjun Kim, Yong Man Ro (* Co-First Authors)
    Under Review
    PDF Code Project Page BibTex

  6. CVPR
    SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis
    Junho Kim*, Hyunjun Kim*, Hosu Lee, Yong Man Ro (* Co-First Authors)
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
    PDF Code Project Page BibTex

  7. NeurIPS
    CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models
    Junho Kim*, Hyunjun Kim*, Yeonju Kim, Yong Man Ro (* Co-First Authors)
    Advances in Neural Information Processing Systems (NeurIPS), 2024
    PDF Code Project Page BibTex

  8. EMNLP
    What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models
    Junho Kim, Yeonju Kim, Yong Man Ro
    Findings of the Association for Computational Linguistics: EMNLP (EMNLP), 2024
    PDF Code Project Page BibTex

  9. ICCV
    Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learning
    Byung-Kwan Lee*, Junho Kim*, Yong Man Ro (* Co-First Authors)
    IEEE/CVF International Conference on Computer Vision (ICCV), 2023
    PDF Code BibTex

  10. ICIP
    Mitigating Dataset Bias in Image Captioning through CLIP Confounder-free Captioning Network
    YeonJu Kim, Junho Kim, Byung-Kwan Lee, Sebin Shin, Yong Man Ro
    IEEE International Conference on Image Processing (ICIP), 2023
    PDF Code BibTex

  11. CVPR
    Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression
    Junho Kim*, Byung-Kwan Lee*, Yong Man Ro (* Co-First Authors)
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
    PDF Code BibTex

  12. CVPR
    Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network
    Byung-Kwan Lee*, Junho Kim*, Yong Man Ro (* Co-First Authors)
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
    PDF Code BibTex

  13. NeurIPS
    Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck
    Junho Kim*, Byung-Kwan Lee*, Yong Man Ro (* Co-First Authors)
    Advances in Neural Information Processing Systems (NeurIPS), 2021
    PDF Code BibTex

  14. ICIP
    Interpretation of Lesional Detection via Counterfactual Generation
    Junho Kim, Minsu Kim, Yong Man Ro
    IEEE International Conference on Image Processing (ICIP), 2021
    PDF Code BibTex

  15. ICPR
    Unsupervised disentangling of viewpoint and residues variations by substituting representations for robust face recognition
    Minsu Kim, Joanna Hong, Junho Kim, Hong Joo Lee, Yong Man Ro
    International Conference on Pattern Recognition (ICPR), 2020
    PDF BibTex

  16. ICIP
    Learning Style Correlation for Elaborate Few-Shot Classification
    Junho Kim, Minsu Kim, Jung Uk Kim, Hong Joo Lee, Sangmin Lee, Joanna Hong, Yong Man Ro
    IEEE International Conference on Image Processing (ICIP), 2020
    PDF BibTex

Experience

Hyundai MOBIS

Samsung Electronics

Hyundai MOBIS

Services and Talk

Program Committee & Conference Reviewers

Journal Reviewers

Invited Talk