Sanghyun Woo

Ph.D Candidate

Robotics and Computer Vision Lab.

Korea Advanced Institute of Science and Technology (KAIST)

shwoo93 [at] kaist.ac.kr

[CV] [Google Scholar] [Github] [LinkedIn]

Hi!

I'm Sanghyun Woo, a second-year Ph.D. student at Korea Advanced Institute of Science and Technology (KAIST), advised by Prof. In So Kweon. I earned my B.S and M.S degrees in electrical engineering from Seoul National University (SNU) and KAIST in 2017 and 2019, respectively. I was a summer research intern at Adobe (San Jose, CA) working with Joon-Young Lee in 2019. I am a recipient of Microsoft Research Asia Fellowship 2020.

Research Interests

My research aims to build an AI agent that can think and learn like humans. To do so, I focus on challenging issues in the current learning system both in the 'model' and 'data' perspective. Specifically, there are two principal directions I have explored. First, apart from the current model design paradigm, I attempted to incorporate the attention mechanism, a central component of the human vision system, into the model. Second, to reduce expensive and error-prone human supervision, I tried to exploit self-supervision or simulation and scale the training data up to a billion-scale.

My work explores following areas

    • Visual Perception (Categorization, Detection, Segmentation)

    • Visual Reasoning (Scene Graph, Summarization, Stroytelling)

    • Image and Video Processing (Synthesis, Translation)

    • Unsupervised / Self-supervised Learning

    • Simulated Learning and Domain Adaptation

but not limited to.

Research Experience

  • Adobe Research, San Jose, CA

Research Intern, Deep Learning Group, Creative Intelligence Lab Jun 2019 - Sep 2019Mentor : Joon-Young Lee
  • KAIST, Daejeon, Korea

Research Assistant, Robotics and Computer Vision Lab, Mar 2017 - Present

International Publications (Google Scholar)

(* indicates equal contribution)

2021

    • The Devil is in the Boundary: Exploiting Boundary Representation for Basis-based Instance Segmentation [Paper]

Myungchul Kim, Sanghyun Woo, Dahun Kim, In So KweonWinter Conference on Computer Vision (WACV), 2021

2020

    • Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation [Paper]

Kwanyong Park, Sanghyun Woo, Inkyu Shin, In So KweonNeural Information Processing Systems (NeurIPS), 2020
    • Align-and-Attend Network for Globally and Locally Coherent Video Inpainting [Paper]

Sanghyun Woo, Dahun Kim, Kwanyong Park, Joon-Young Lee, In So KweonBritish Machine Vision Conference (BMVC), 2020
    • Two-Phase Pseudo Label Densification for Self-training based Domain Adaptation [Paper]

Inkyu Shin, Sanghyun Woo, Fei Pan, In So KweonEuropean Conference on Computer Vision (ECCV), 2020
    • Global-and-Local Relative Position Embedding for Unsupervised Video Summarization [Paper]

Yunjae Jung, Donghyeon Cho, Sanghyun Woo, In So KweonEuropean Conference on Computer Vision (ECCV), 2020
Dahun Kim, Sanghyun Woo, Joon-Young Lee, In So KweonIEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020 (Oral)
    • A Simple and Light-weight Attention Module for Convolutional Neural Networks [Paper]

Jongchan Park*, Sanghyun Woo*, Joon-Young Lee, In So KweonInternational Journal of Computer Vision (IJCV), 2020
    • Recurrent Temporal Aggregaation Framework for Deep Video Inpainting [Paper]

Dahun Kim*, Sanghyun Woo*, Joon-Young Lee, In So KweonIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020Received KAIST-Samsung Industry-University Cooperation Best Paper Award
    • Hide-and-Tell: Learning to Bridge Photo Streams for Visual Storytelling [Paper]

Yunjae Jung, Dahun Kim, Sanghyun Woo, Kyungsu Kim, Sungjin Kim, In So KweonAssociation for the Advancement of Artificial Intelligence (AAAI), 2020
    • Propose-and-Attend Single Shot Detector [Paper]

Ho-Deok Jang, Sanghyun Woo, Philipp Benz, Jinsun Park, In So KweonWinter Conference on Computer Vision (WACV), 2020

2019


    • Preserving Semantic and Temporal Consistency for Unpaired Video-to-Video Translation [Paper]

Kwanyong Park, Sanghyun Woo, Dahun Kim, Donghyeon Cho and In So Kweon ACM Multimedia (MM), 2019
    • Video Retargeting: Trade-off between Content Preservation and Spatio-temporal Consistency [Paper]

Donghyeon Cho, Yunjae Jung, Francois Rameau, Dahun Kim, Sanghyun Woo and In So KweonACM Multimedia (MM), 2019
Dahun Kim*, Sanghyun Woo*, Joon-Young Lee, In So KweonIEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
    • Deep Blind Video Decaptioning by Temporal Aggregation and Recurrence [Paper] [Project] [Code]

Dahun Kim*, Sanghyun Woo*, Joon-Young Lee, In So KweonIEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019The winner method of ECCV 2018 ChaLearnLAP Inpainting Challenge [factsheet]
    • Gated Bidirectional Feature Pyramid Network for Accurate One Shot Detection [Paper]

Sanghyun Woo, Soonmin Hwang, Ho-Deok Jang, In So KweonMachine Vision And Applications (MVA), 2019
    • Discriminative Feature Learning for Unsupervised Video Summarization [Paper]

Yunjae Jung, Donghyeon Cho, Dahun Kim, Sanghyun Woo, In So KweonAssociation for the Advancement of Artificial Intelligence (AAAI), 2019 (Oral)Received Honorable Mention, 25th HumanTech Paper Award, Samsung Electronics Co., Ltd.

2018

    • LinkNet: Relational Embedding for Scene Graph [Paper]

Sanghyun Woo*, Dahun Kim*, Donghyeon Cho, In So KweonNeural Information Processing Systems (NeurIPS), 2018
    • CBAM: Convolutional Block Attention Module [Paper] [Code]

Sanghyun Woo*, Jongchan Park*, Joon-Young Lee, In So KweonEuropean Conference on Computer Vision (ECCV), 2018
Jongchan Park*, Sanghyun Woo*, Joon-Young Lee, In So KweonBritish Machine Vision Conference (BMVC), 2018 (Oral)Received Gold Prize, 24th HumanTech Paper Award, Samsung Electronics Co., Ltd.
    • StairNet: Top-Down Semantic Aggregation for Accurate One Shot Detection [Paper] [Supp]

Sanghyun Woo, Soonmin Hwang, In So KweonWinter Conference on Computer Vision (WACV), 2018 (Oral)Received Silver Prize, Best Paper Award, 30th IPIU 2018Received Honorable Mention, 24th HumanTech Paper Award, Samsung Electronics Co., Ltd.

Academic Activities

  • Journal Reviewer

-Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

-International Journal of Computer Vision (IJCV)

-Transactions on Image Processing (TIP)

-Transactions on Circuits and Systems for Video Technology (TCSVT)

-Transactions on Cybernetics

-Machine Vision Applications (MVA)

-Pattern Recognition (PR)

-Neurocomputing

-IEEE Access

  • Conference Reviewer

-CVPR 2019, 2020, 2021

-ICCV 2019, 2021

-ECCV 2020

-BMVC 2020

-WACV 2020, 2021

-ACCV 2020

-NeurIPS 2020

-ICLR 2021

-AAAI 2020

Awards & Honors

  • Awards

-KAIST-Samsung Industry-University Cooperation Best Paper Award ($3,000), July 2020

-Honorable Mention, 25th HumanTech Paper Award, Samsung Electronics Co., Ltd. ($2,000), Feb 2019

-1st Place Award in ChaLearnLAP 2018 Inpainting Challenge Track 2 – video decaptioning (ECCV2018 Challenge), Sep 2018 [factsheet]

-Gold Prize, 24th HumanTech Paper Award, Samsung Electronics Co., Ltd. ($10,000), Feb 2018

-Honorable Mention, 24th HumanTech Paper Award, Samsung Electronics Co., Ltd. ($2,000), Feb 2018

-Silver Prize, Best Paper Award, 30th IPIU 2018, Feb 2018

  • Honors

-Microsoft Research Asia Ph.D. Fellowship 2020 Winner ($10,000), Nov 2020 [Certificate]

-AI summer school (PAISS 2018), July 2018