Lab Overview

The Computational Intelligence Laboratory(CI Lab.) at KAIST, Daejeon, Korea, is part of the Signal Processing Group at the School of Electrical Engineering. The mission of the CI Lab. is to perform innovative research work in the areas of image understanding and intelligent multimedia systems. 
Members of the lab are investigating advanced technologies on a variety of multimedia system. Specifically, research has been focused on the followings. 
Image understanding, video analysis using deep learning, medical imaging, and nonlinear signal and image processing.

Publications

  • Jaehoon Choi, Minki Jeong, Taekyung Kim, and Changick Kim, "Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation," Accepted to British Machine Vision Conference (BMVC), Cardiff, UK, Sep. 9-12, 2019.
  • Hankyeol Lee, Seokeon Choi, Youngeun Kim, and Changick Kim, "Bilinear Siamese Networks with Background Suppression for Visual Object Tracking," Accepted to British Machine Vision Conference (BMVC), Cardiff, UK, Sep. 9-12, 2019.
  • Taekyung Kim, Minki Jeong, Seunghyeon Kim, Seokeon Choi, and Changick Kim, "Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection," in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, Jun. 16-20, 2019.
  • Youngeun Kim*, Seunghyeon Kim*, Taekyung Kim, and Changick Kim, "CNN-based Semantic Segmentation Using Level Set Loss", in Proc. IEEE Winter Conference on Applications of Computer Vision (WACV)
    , Hawaii, USA, Jan. 8-10, 2019.
    (* These two authors contributed equally)
  • Junyoung Byun*, Kyujin Shim*, and Changick Kim, "BitNet: Learning-Based Bit-Depth Expansion," in Proc. Asian Conference on Computer Vision (ACCV), Perth, Australia, Dec. 2-6, 2018. (* These two authors contributed equally)
  • Seungjun Jung, Muhammad Hasan, and Changick Kim, "Water-Filling: An Efficient Algorithm for Digitized Document Shadow Removal," in Proc. Asian Conference on Computer Vision (ACCV), Perth, Australia, Dec. 2-6, 2018.

News