Paul Hongsuck Seo

Research Interest
Deep Learning & Neural Network
Multimodal Representation Learning
Computer Vision & Image Processing
Natural Language Processing
Machine Learning and Intelligent Systems

Sep. 2016 - Present Ph.D. in Computer Science and Engineering, Pohang University of Science and Technology (POSTECH)
Mar. 2011 - Feb. 2013 M.S. in Computer Science and Engineering, Pohang University of Science and Technology (POSTECH)
Mar. 2006 - Feb. 2011 B.S. (Summa Cum Laude) in Computer Engineering, Changwon National University

Work Experiences and Academic Services
Academic Services:I have been serveing as a reviewer for CVPR, NeurIPS, ICLR, ICML, ICCV and ACL
I am serving as a technical committee of Conceptual Captions Challenge in CVPR 2019.
May. 2019 -Research Intern, Google LAX (I will be working with Piyush Sharma and Radu Soricut)
Jun. 2017 - Dec. 2017Tech Intern, Google LAX (worked with Tobias Weyand and Jack Sim)
Feb. 2017 - May. 2017Lab Associate, Disney Research Pittsburgh (worked with Andreas Lehrmann and Leonid Sigal)
Aug. 2013 - Jan. 2015 Lecturer, in Information Technology Department, Mongolia International University (MIU)

Honors and Awards
2019CVPR 2019 Doctoral Consortium
2017Naver Ph.D. Fellowship
2015 Best Team Project Award, SUNY Korea Hot Topics in Computer Science Workshop 2015
2006 - 2011 Academic Scholarship, Kyobo Foundation for Education and Culture
2007 - 2008 Academic Scholarship, Bakyeop Foundation
2007 Grand Prize, CNU Venture Item Contest
2006 First Runner Up, CNU Programming Contest


  • Masters Thesis: Multiple User Intent Understanding for Spoken Dialog System [pdf]
    Department of Computer Science and Engineering, POSTECH (Pohang University of Science and Technology), December 2012
    Adviser: Gary Geunbae Lee; Committee: Jonghyeok Lee, Hwanjo Yu
  • Learning for Single-Shot Confidence Calibration in Deep Neural Networks through Stochastic Inferences [pdf]
    Seonguk Seo*, Paul Hongsuck Seo*, Bohyung Han (* equal contribution)
    To appear in CVPR 2019, Long Beach, June 2019
  • CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps [pdf]
    Paul Hongsuck Seo, Tobias Weyand, Jack Sim, Bohyung Han
    In ECCV 2018, Munich, Sep 2018
  • Attentive Semantic Alignment with Offset-Aware Correlation Kernels [pdf] [project page]
    Paul Hongsuck Seo, Jongmin Lee, Deunsol Jung, Bohyung Han, Minsu Cho
    In ECCV 2018, Munich, Sep 2018
  • Progressive Attention Networks for Visual Attribute Prediction [pdf]
    Paul Hongsuck Seo, Zhe Lin, Scott Cohen, Xiaohui Shen, Bohyung Han
    In BMVC 2018, Newcastle, Sep 2018
  • Visual Reference Resolution using Attention Memory for Visual Dialog [pdf] [project page]
    Paul Hongsuck Seo, Andreas Lehrmann, Bohyung Han, Leonid Sigal
    In NIPS 2017, Long Beach, Dec 2017
  • MarioQA: Answering Questions by Watching Gameplay Videos [pdf] [project page]
    *Jonghwan Mun, *Paul Hongsuck Seo, Ilchae Jung, Bohyung Han (* equal contribution)
    In ICCV 2017, Venice, Oct 2017
  • Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction (oral) [pdf] [project page]
    Hyeonwoo Noh, Paul Hongsuck Seo, Bohyung Han
    In CVPR 2016
    , Las Vegas, June 2016
  • A Corpus for a Multimodal Dialog System for Presentation Controls
    Paul Hongsuck Seo, Gary Geunbae Lee
    In proceedings of the International Workshop Series on Multimodal Corpora, Portorož, Slovenia, May, 2016
  • Conversational Knowledge Teaching Agent that Uses a Knowledge Base [pdf]
    Kyusong Lee, Paul Hongsuck Seo, Junhwi Choi, Sangjun Koo, Gary Geunbae Lee
    In Proceedings of the 16th Annual SIGdial Meeting on Discourse and Dialogue (SIGDIAL 2015), Prague, September 2015
  • Grammatical Error Correction based on Learner Comprehension Model in Oral Conversation [pdf]
    Kyusong Lee, Seonghan Ryu, Paul Hongsuck Seo, Seokhwan Kim, Gary Geunbae Lee
    In Proceedings of the IEEE Workshop on Spoken Language Technology (SLT 2014), Nevada, December 2014
  • Generating Grammar Questions using Corpus Data in L2 Learning [pdf]
    Kyusong Lee, Soo-ok Kweon, Hongsuck Seo, Gary Geunbae Lee
    In Proceedings of the 2012 IEEE Workshop on Spoken Language Technology (SLT 2012), Miami, December 2012
  • A Meta-Learning Approach to Grammatical Error Correction [pdf]
    Hongsuck Seo, Jonghoon Lee, Seokhwan Kim, Kyusong Lee, Sechun Kang, Gary Geunbae Lee
    In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (ACL 2012), Jeju, Korea, July 2012
  • Grammatical Error Annotation for Korean Learners of Spoken English [pdf]
    Hongsuck Seo, Kyusong Lee, Gary Geunbae Lee, Soo-ok Kweon
    In Proceedings of the 8th International Conference on Language Resources and Evaluation (LREC 2012), Istanbul, May 2012
  • Apparatus for grammatical error correction and method for grammatical error correction using the same (PCT/KR2013/004079)
    Hongsuck Seo,  Kyusong Lee, Sechun Kang, Jisoo Bang, Jonghoon Lee, Gary Geunbae Lee
  • Stress studying system and method for studying foreign language (Korean Domestic; 1011889820000)
    Hongsuck Seo, Jinsik Lee, Jonghoon Lee, Gary Geunbae Lee
  • Apparatus and method for generating corpus for training phrase break prediction (Korean Domestic; 1012617540000)
    Hongsuck Seo, Jinsik Lee, Jonghoon Lee, Gary Geunbae Lee
  • Apparatus for language learning and method thereof (Korean Domestic; 1012832710000)
    Hongsuck Seo, Jonghoon Lee, Jinsik Lee, Gary Geunbae Lee
  • Method and apparatus of machine learning for generation of multiple answer (Korean Domestic; 1012948820000)
    Hongsuck Seo, Jonghoon Lee, Jinsik Lee, Gary Geunbae Lee