Seokju Lee

ykchoicv




Junsik Kim

Ph.D. Candidate
Robotics and Computer Vision lab.
Korea Advanced Institute of Science and Technology (KAIST)

mibastro [at] gmail.com
jskim2 [at] rcv.kaist.ac.kr
CV | Google Scholar | LinkedIn


Research Interests

  • Deep Learning
    • Domain adaptation, Representation learning
  • Computer Vision
    • Image recognition
  • Autonomous Vehicle
    • Perception


International Journals

  • Real-time Robust Manhattan Frame Estimation: Global Optimality and Applications
    Kyungdon Joo, Tae-Hyun Oh, Junsik Kim, In So Kweon
    IEEE Transactions on Pattern Analysis and Machine Intelligence (
    TPAMI), (to appear)


International Conferences

  • Part-based Player Identification using Deep Convolutional Representation and Multi-scale Pooling
    Arda Senocak, Tae-Hyun Oh, Junsik Kim, In So Kweon
    In CVSports workshop in conjunction with CVPR, Jun 2018 (oral)
    [Paper] [Project]
  • Learning to Localize Sound Source in Visual Scenes
    Arda Senocak, Tae-Hyun Oh, Junsik Kim, Ming-Hsuan Yang, In So Kweon
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2018
    [Paper] [Project] 

  • Co-domain Embedding using Deep Quadruplet Networks for Unseen Traffic Sign Recognition
    Junsik Kim, Seokju Lee, Tae-Hyun Oh, In So Kweon
    AAAI Conference on Artificial Intelligence (AAAI), Feb 2018
    [Paper] [Project]
  • VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition 
    Seokju Lee, Junsik Kim, Jae Shin Yoon, Seunghak Shin, Oleksandr Bailo, Namil Kim, Tae-Hee Lee, Hyun Seok Hong, Seung-Hoon Han, In So Kweon
    IEEE International Conference on Computer Vision (ICCV), Oct 2017 
    [Paper] [Project]

  • Pixel-Level Matching for Video Object Segmentation Using Convolutional Neural Networks
    Jae Shin Yoon, Francois Rameau, Junsik Kim, Seokju Lee, Seunghak Shin, In So Kweon
    IEEE International Conference on Computer Vision (ICCV), Oct 2017
    [Paper] [Project

  • Globally Optimal Manhattan Frame Estimation in Real-time
    Kyungdon Joo, Tae-Hyun Oh, Junsik Kim, In So Kweon
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2016
    [Paper] [Project

Other Publications

  • Human Body Part Classification from Optical Flow
    Junsik KimKyungdon Joo Tae-Hyun Oh In So Kweon
    IEEE International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), Aug 2016
  • A Fusion Approach for Robust Visual Object Tracking in Crowd Scenes
    Tae-Hyun OhKyungdon Joo, Junsik Kim, Jaesik ParkIn So Kweon
    IEEE International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), Nov 2014





Last updated: Mar 01, 2018