Minsu Cho Minsu Cho (조 민수)
Assistant Professor
Dept. of Computer Science and Engineering
POSTECH (Pohang Univ. of Science and Technology, 포항공과대학교)
77 Cheongam-ro, Nam-gu, Pohang, Gyeongbuk, South Korea 37673

Email: mscho at postech dot ac dot kr
Tel: +82 054 279 2385
Fax: +82 054 279 2299

I am an assistant professor at the department of Computer Science and Engineering at POSTECH, South Korea, working as a faculty member of POSTECH Computer Vision Lab. My research lies in the areas of computer vision and machine learning, especially in the problems of object discovery, weakly-supervised learning, semantic correspondence, and graph matching. In general, I am interested in the relationship between correspondence and supervision in visual learning.

Before joining POSTECH in the fall of 2016, I was a researcher (starting research position) in the Inria WILLOW team at École Normale Supérieure (ENS), Paris, France, where I have worked with Jean Ponce and closely collaborated with Cordelia Schmid in the Inria LEAR team. I completed my Ph.D. in 2012, under the supervision of Kyoung Mu Lee at Seoul National University, Korea.

POSTECH CV Lab Publications - Software - Students - Teaching - CV - Google Scholar


NEWS 
  • I am serving as an Area Chair and also a Web Chair for ICCV 2019.
  • `Attentive Semantic Alignment with Offset-Aware Correlation Kernels'  has been accepted in ECCV 2018.
  • `Action Recognition'  journal paper has been accepted in PRL.
  • I am serving as an Area Chair for ACCV 2018.
  • I am serving as a Guest Editor of the PRL Special Issue on "Advances in Visual Correspondence".
          See the Call for Papers (Submission deadline: May 31, 2018).
  • I won MSRA Collaborative Research 2018 Grant Awards.
  • I am serving as a Web Chair for ACM Multimedia 2018.
  • `SCNet: Learning Semantic Correspondence'  paper has been accepted in ICCV 2017.
  • I am serving as an Area Chair for CVPR 2018.
  • I am serving as an Area Chair for WACV 2018.
  • `Proposal Flow'  journal paper has been accepted in TPAMI.
  • `Multi-Object Tracking with Quadruplet Convolutional Neural Networks'  has been accepted in CVPR 2017.
  • `Nonconvex Potential Guided Image Filtering'  paper has been accepted in TPAMI.
  • `Text-guided attention model for image captioning'  paper has been accepted in AAAI 2017.
  • I joined POSTECH as an assistant professor at the department of Computer Science and Engineering.


    RECENT & SELECTED PUBLICATIONS (Click here for a full list)

    Paul Hongsuck Seo, Jongmin Lee, Deunsol Jung, Bohyung Han, Minsu Cho
    Attentive Semantic Alignment with Offset-Aware Correlation Kernels   
    The European Conference on Computer Vision (ECCV), 2018, Munich, Germany.

    Heeseung Kwon, Yeonho Kim, Jin S. Lee, Minsu Cho
    First Person Action Recognition via Two-stream ConvNet with Long-term Fusion Pooling   
    Pattern Recognition Letters (PRL), Sep 2018.
    [link]

    Kai Han, Rafael S. Rezende, Bumsub Ham, Kwan-Yee K. Wong, Minsu Cho, Cordelia Schmid, Jean Ponce
    SCNet: Learning Semantic Correspondence   
    The IEEE International Conference on Computer Vision (ICCV), 2017, Venice, Italy.
    [Arxiv version] [project page]

    Bumsub Ham, Minsu Cho, Cordelia Schmid, Jean Ponce
    Proposal Flow: Semantic Correspondences from Object Proposals   
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), accepted, 2017.
    The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, Las Vegas, Nevada.
    [Arxiv TPAMI version] [ CVPR pdf] [project page]

    Jeany Son, Mooyeol Baek, Minsu Cho, Bohyung Han
    Multi-Object Tracking with Quadruplet Convolutional Neural Networks
    The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, Honolulu, HI, US.
    [pdf]

    Bumsub Ham, Minsu Cho, Jean Ponce
    Robust Guided Image Filtering Using Nonconvex Potentials
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Feb 2017.
    [link]

    Jonghwan Mun, Minsu Cho, Bohyung Han
    Text-Guided Attention Model for Image Captioning
    AAAI Conference on Artificial Intelligence (AAAI), 2017, San Francisco, CA, US.
    [pdf]

    Vadim Kantorov, Maxime Oquab, Minsu Cho, Ivan Laptev
    ContextLocNet: Context-aware Deep Network Models for Weakly Supervised Localization
    The European Conference on Computer Vision (ECCV), 2016, Amsterdam, Netherlands.
    [pdf] [project page]

    Minsu Cho, Suha Kwak, Cordelia Schmid, Jean Ponce
    Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposals
    The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, Boston, MA (oral).
    [pdf] [project page]

    Minsu Cho, Karteek Alahari, Jean Ponce
    Learning Graphs to Match
    The IEEE International Conference on Computer Vision (ICCV), 2013, Sydney, Australia (oral).
    [pdf] [project page]

    Minsu Cho, Kyoung Mu Lee
    Progressive Graph Matching: Making a Move of Graphs via Probabilistic Voting
    The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012, Providence, RI (oral).
    [pdf] [project page]

    Minsu Cho, Young Min Shin, Kyoung Mu Lee
    Unsupervised Detection and Segmentation of Identical Objects
    The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010, San Francisco, CA (oral).
    [pdf] [project page]

    Minsu Cho, Jungmin Lee, Kyoung Mu Lee
    Reweighted Random Walks for Graph Matching
    The European Conference on Computer Vision (ECCV), 2010, Crete, Greece.
    [pdf] [project page]


    SOFTWARE CODES & DATASETS
  • SCNet: Learning Semantic Correspondence (Paper)
  • ContextLocNet: ConvNet for Weakly-Supervised Object Detection (Paper)
  • Region Proposal Matching + Semantic Correspondence Benchmark (Paper, Data)
  • Unsupervised Object Discovery and Localization (Paper)
  • Graph Learning for Matching (Paper, Data)
  • Outlier-Robust Graph Matching (MPM) (Paper)
  • Progressive framework for Boosting Graph Matching Performance (Paper)
  • Robust Graph Matching (RRWM) (Paper) & Hyper-Graph Matching (RRWHM), (Paper)
  • Mode Seeking on Graphs (Paper)
  • Hierarchical Authority-Shift Clustering (Paper)
  • Deformable Object Matching via Correspondence Clustering (Paper)
  • SNU Dataset for Cosegmentation (Paper, Data)


    STUDENTS & POSTDOCS
    PhD:
  • Vadim Kantorov (co-advised with I. Laptev), 2015- at Inria Paris
  • Deunsol Jung, 2016- at POSTECH
  • Woohyeon Shim (co-advised with J. Lee), 2016- at POSTECH
  • Seungkwan Lee, 2017- at POSTECH
  • Ahyun Seo, 2018- at POSTECH
  • Jeongbeen Yoon, 2018- at POSTECH
  • Jeany Son (co-advised with B. Han), 2018- at POSTECH
  • Paul Hongsuck Seo (co-advised with B. Han), 2018- at POSTECH
  • Ilchae Jung (co-advised with B. Han), 2018- at POSTECH
  • Jonghwan Mun (co-advised with B. Han), 2018- at POSTECH
  • Jongbin Yim (co-advised with J. Han), 2017- at POSTECH
  • Yongjin Park (co-advised with S. Kwak & J. Han), 2017- at POSTECH

  • Masters:
  • Dongju Kim, 2017- at POSTECH
  • Wonpyo Park, 2017- at POSTECH
  • Kihyun You, 2018- at POSTECH

  • Interns:
  • Matthieu Toulemont (Ecole des Ponts Paristech), 2018 at POSTECH
  • Idil Kanpolat (co-advised with E. Konukoglu, ETH Zurich), 2017 at POSTECH
  • Kai Han (co-advised with J. Ponce, ENS), 2016 at Inria Paris
  • Sergiu Irimie (co-advised with J. Ponce, ENS), 2016 at Inria Paris
  • Yumin Suh (co-advised with J. Ponce, ENS), 2015 at Inria Paris

  • TEACHING
    2018 Spring: Language and Vision (at POSTECH CSE)
    2017 Fall: Automata and Formal Languages (at POSTECH CSE)
    2017 Spring: Language and Vision (at POSTECH CSE)
    2016 Fall: Introduction to Computer Vision (at POSTECH CSE)