World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
48
Citations
8994
World Ranking
6197
National Ranking
47

Overview

Changick Kim is affiliated with the Korea Advanced Institute of Science and Technology in South Korea. Their research primarily focuses on computer science, with significant contributions in computer vision and pattern recognition, as well as artificial intelligence. They have a substantial record of publications in these fields, totaling over 210 works.

Their subfields of study include:

  • Computer Vision and Pattern Recognition
  • Artificial Intelligence
  • Media Technology
  • Biomedical Engineering
  • Radiology, Nuclear Medicine and Imaging

Changick Kim's main research topics cover a diverse range of areas related to machine learning and imaging technology:

  • Human Pose and Action Recognition
  • Domain Adaptation and Few-Shot Learning
  • Multimodal Machine Learning Applications
  • Anomaly Detection Techniques and Applications
  • Adversarial Robustness in Machine Learning
  • Video Surveillance and Tracking Methods
  • Advanced Vision and Imaging

The scientist has published extensively in several academic venues, which reflect the impact and scope of their contributions:

  • arXiv (Cornell University)
  • 2022 IEEE International Conference on Image Processing (ICIP)
  • SSRN Electronic Journal
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • The Journal of Korean Institute of Communications and Information Sciences

Some recent publications include:

  • Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization, 2022, International Journal of Computer Vision
  • Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Input, 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • Towards Good Practices for Missing Modality Robust Action Recognition, 2023, Proceedings of the AAAI Conference on Artificial Intelligence
  • SAFENet: Self-Supervised Monocular Depth Estimation with Semantic-Aware Feature Extraction, 2020, arXiv (Cornell University)
  • Dual Back-Projection-Based Internal Learning for Blind Super-Resolution, 2020, IEEE Signal Processing Letters

Frequent collaborators in their research include Sangmin Woo, Sumin Lee, Junyoung Byun, Hyojun Go, and Seungju Cho. These coauthors have worked with Kim across multiple projects and publications, contributing to the breadth of topics mentioned.

Best Publications

  • The sixth visual object tracking VOT2018 challenge results

    Matej Kristan;Aleš Leonardis;Jiří Matas;Michael Felsberg

  • Fast and automatic video object segmentation and tracking for content-based applications

    Changick Kim;Jenq-Neng Hwang

  • Spatiotemporal sequence matching for efficient video copy detection

    Changick Kim;B. Vasudev

  • Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection

    Taekyung Kim;Minki Jeong;Seunghyeon Kim;Seokeon Choi

  • Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification

    Seokeon Choi;Sumin Lee;Youngeun Kim;Taekyung Kim

  • Segmenting Clustered Nuclei Using H-minima Transform-Based Marker Extraction and Contour Parameterization

    Chanho Jung;Changick Kim

  • Self-Ensembling With GAN-Based Data Augmentation for Domain Adaptation in Semantic Segmentation

    Jaehoon Choi;Taekyung Kim;Changick Kim

  • Content-based image copy detection

    Changick Kim

  • Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection

    Seunghyeon Kim;Jaehoon Choi;Taekyung Kim;Changick Kim

  • Unsupervised Segmentation of Overlapped Nuclei Using Bayesian Classification

    Chanho Jung;Changick Kim;Seoung Wan Chae;Sukjoong Oh

  • A New Approach for Overlay Text Detection and Extraction From Complex Video Scene

    Wonjun Kim;Changick Kim

  • Meta Batch-Instance Normalization for Generalizable Person Re-Identification

    Seokeon Choi;Taekyung Kim;Minki Jeong;Hyoungseob Park

  • Object-based video abstraction for video surveillance systems

    Changick Kim;Jenq-Neng Hwang

  • Adaptive determination of filter scales for edge detection

    H. Jeong;C.I. Kim

  • Reducing blocking and ringing artifacts in low-bit-rate coding

    Changick Kim

  • An integrated scheme for object-based video abstraction

    Changick Kim;Jenq-Neng Hwang

  • Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization

    Myung-Joon Kwon;Seung-Hun Nam;In-Jae Yu;Heung-Kyu Lee

  • Background Subtraction for Dynamic Texture Scenes Using Fuzzy Color Histograms

    Wonjun Kim;Changick Kim

  • Spatiotemporal Saliency Detection and Its Applications in Static and Dynamic Scenes

    Wonjun Kim;Chanho Jung;Changick Kim

  • Segmenting a low-depth-of-field image using morphological filters and region merging

    Changick Kim

  • A Unified Spectral-Domain Approach for Saliency Detection and Its Application to Automatic Object Segmentation

    Chanho Jung;Changick Kim

  • Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation

    Taekyung Kim;Changick Kim

Frequent Co-Authors

Jenq-Neng Hwang
Jenq-Neng Hwang University of Washington
Xiaojun Wu
Xiaojun Wu University of Science and Technology of China
Jitendra Malik
Jitendra Malik University of California, Berkeley
Amir Said
Amir Said Qualcomm (United States)
Ming-Hsuan Yang
Ming-Hsuan Yang University of California, Merced
Efstratios Gavves
Efstratios Gavves University of Amsterdam
Andrea Vedaldi
Andrea Vedaldi University of Oxford
Michael Felsberg
Michael Felsberg Linköping University
Shubham Tulsiani
Shubham Tulsiani Carnegie Mellon University
Richard Bowden
Richard Bowden University of Surrey

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring computer science isn’t just about traditional degrees—there are many flexible options to build skills and advance your career online. Specialized programs, such as an electrical engineering degree online admissions, provide technical depth while letting you study remotely and fit your education into a busy schedule.

If you’re looking for a quicker credential, there are easy licenses and certifications to get that can rapidly open the door to high-paying tech roles. These certifications are especially ideal for students or professionals wanting to upskill fast without a long-term commitment.

For graduates aiming for leadership roles or specialized positions, pursuing one of the quickest online masters degree can accelerate your journey and help you stay competitive. Among graduate paths, those classified as the most valuable masters degrees tend to offer the highest return on investment and the greatest job market demand.

With flexible online learning and targeted credentials, there are more ways than ever to launch or advance your tech career in the USA.

Best Scientists Citing Changick Kim

Trending Scientists

Recently Published Articles