Seong Joon Oh (PhD Student)

Dr. Seong Joon Oh

Address
Max-Planck-Institut für Informatik
Saarland Informatics Campus
Campus
Location
-
Phone
+49 681 9325 2000
Fax
+49 681 9325 2099
Email
Get email via email

Personal Information

Research Interests

Analysing and exploiting out-of-domain behaviour of learned models.

  • Generalisation and domain adaptation.
  • Machine learning security.
  • Privacy in machine learning.
  • Explainable models and weakly supervised localisation.
  • Bayesian deep learning.

Education

  • 2007-2010 Hankuk Academy of Foreign Studies (HAFS), South Korea.
  • 2010-2013 BA in Mathematics (First Class, top 20%), University of Cambridge, U.K.
  • 2013-2014 Part III in Mathematics (Honours with Distinction, top 20%), University of Cambridge, U.K.
  • 2014-Present PhD student in computer vision, Max-Planck Institute for Informatics, Germany

Internship

  • 2018 Google Summer Research Intern, Mountain View, U.S.A.

Publications

2018

  • Sequential Attacks on Agents for Long-Term Adversarial Goals
    Edgar Tretschk, Seong Joon Oh, Mario Fritz.
    ACM Computer Science in Cars Symposium (CSCS), 2018.
    [Paper(PDF)] [Bibtex]
  • Understanding and Controlling User Linkability in Decentralized Learning
    Tribhuvanesh Orekondy, Seong Joon Oh, Bernt Schiele, Mario Fritz.
    arXiv, 2018.
    [Paper(PDF)] [Bibtex]
  • Natural and Effective Obfuscation by Head Inpainting
    Qianru Sun, Liqian Ma, Seong Joon Oh, Luc Van Gool, Bernt Schiele, Mario Fritz.
    Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
    [Paper(PDF)] [Bibtex]

 

2017

  • Person Recognition in Social Media Photos
    Seong Joon Oh, Rodrigo Benenson, Mario Fritz, Bernt Schiele.
    arXiv, 2017.
    [Paper(PDF)] [Bibtex]
  • Adversarial Image Perturbation for Privacy Protection -- A Game Theory Perspective
    Seong Joon Oh, Mario Fritz, Bernt Schiele.
    International Conference on Computer Vision (ICCV), 2017.
    [Paper(PDF)] [Poster(PDF)] [Code] [Bibtex]
  • From Understanding to Controlling Privacy against Automatic Person Recognition in Social Media
    Seong Joon Oh, Mario Fritz, Bernt Schiele.
    The Bright and Dark Sides of Computer Vision: Challenges and Opportunities for Privacy and Security. CVPR Workshop, 2017.
    [Extended Abstract(PDF)] [Poster(PDF)] [Bibtex].
  • Exploiting Saliency for Object Segmentation from Image Level Labels
    Seong Joon Oh, Rodrigo Benenson, Anna Khoreva, Zeynep Akata, Mario Fritz, Bernt Schiele.
    Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
    [Paper(PDF)] [Poster(PDF)] [Code] [Bibtex]
  • Generating Descriptions with Grounded and Co-Referenced People
    Anna Rohrbach, Marcus Rohrbach, Siyu Tang, Seong Joon Oh, Bernt Schiele.
    Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
    [Paper(PDF)] [Bibtex]

 

2016

  • I-pic: A Platform for Privacy-Compliant Image Capture
    Paarijaat Aditya, Rijurekha Sen, Peter Druschel, Seong Joon Oh, Rodrigo Benenson, Mario Fritz, Bernt Schiele, Bobby Bhattacharjee, Tong Tong Wu.
    International Conference on Mobile Systems, Applications, and Services (MobiSys), 2016.
    [Paper(PDF)] [Project] [Bibtex]

 

2015

  • Person Recognition in Personal Photo Collections
    Seong Joon Oh, Rodrigo Benenson, Mario Fritz, Bernt Schiele.
    International Conference on Computer Vision (ICCV), 2015.
    [Paper(PDF)] [Poster(PDF)] [Video] [Project] [Bibtex]