I am a Research Scientist at ByteDance / TikTok TikTok Logo

I received Ph.D. degree in future vehicle (electrical engineering) from the Korea Advanced Institute of Science and Technology (KAIST), where I was co-advised by Prof. Kuk-Jin Yoon and Prof. In So Kweon.

My research interest lies in establishing a robust foundation for the field of computer vision. Current ongoing endeavors focus on pioneering advancements in beyond or human-level visual generation and recognition, while pursuing the data-efficiency for generalizability.

Contact

  • dlsrbgg33 [at] gmail.com

  • 1199 Coleman Avenue, San Jose, CA 95110

Education

  • Ph.D. in Future Vehicle Engineering, 2024

    KAIST, Korea

    MS in Future Vehicle Engineering, 2021

    KAIST, Korea

    BS in Future Vehicle Engineering, 2019

    HYU, Korea

Research Experiences

  • ByteDance / TikTok, San Jose, CA
    Aug 2024 - Current

    Research Scientist
  • ByteDance / TikTok, San Jose, CA
    Sep 2023 - Jan 2024

    Research Intern, Mentors: Liang-Chieh Chen and Qihang Yu
  • Google Research, LA, CA (virtual)
    May 2022 - April 2023

    Student Researcher Intern, Mentors: Liang-Chieh Chen and Jun Xie
  • NEC Laboratories America, Inc, San Jose, CA (virtual)
    May 2021 - Aug 2021

    Research Intern, Mentor: Yi-Hsuan Tsai
  • Korea University, Seoul, Korea
    Sep 2018 - Dec 2018

    Research Intern, Data and Visual Analytics Lab.

Publications


    Visual Generation

  • Enhancing Temporal Consistency in Video Editing by Reconstructing Videos with 3D Gaussian Splatting

    Inkyu Shin, Qihang Yu, Xiaohui Shen, In So Kweon, Kuk-Jin Yoon, Liang-Chieh Chen

    arXiv

    [ Paper | Project page | Code ]

  • Image-to-image translation via group-wise deep whitening-and-coloring transformation

    Wongwoong Cho, Sungha Choi, David Keetae Park, Inkyu Shin, Jaegul Choo

    CVPR 2019 [Oral]

    [ Paper | Code ]


  • Visual Recognition

  • MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark

    Sanghyun Woo*, Kwanyong Park*, Inkyu Shin*, Myungchul Kim*, In So Kweon (*Equal contribution)

    CVPR 2024

    [ Paper | Project page ]

  • MaXTron: Mask Transformer with Trajectory Attention for Video Panoptic Segmentation

    Ju He, Qihang Yu, Inkyu Shin, Xueqing Deng, Xiaohui Shen, Alan Yuille, Liang-Chieh Chen

    TMLR 2024

    [ Paper | Code ]

  • Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation

    Inkyu Shin, Dahun Kim, Qihang Yu, Jun Xie, Hong-Seok Kim, Bradely Green

    In So Kweon, Kuk-Jin Yoon, Liang-Chieh Chen

    WACV 2024 [Oral]

    *Also presented at CVPRW 2023 Workshop(T4V)

    [ Paper | Code | Video Demo ]

  • Moving from 2D to 3D: volumetric medical image classification for rectal cancer staging

    Joohyung Lee*, Jieun Oh*, Inkyu Shin, You-sung Kim, Dae Kyung Sohn, Tae-sung Kim, In So Kweon (*Equal contribution)

    MICCAI 2022

    [ Paper ]


  • Data-efficiency: Domain Adaptation

  • Test-time Adaptation in the Dynamic World with Compound Domain Knowledge Management

    Junha Song, Kwanyong Park, Inkyu Shin, Sanghyun Woo, Chaoning Zhang, In So Kweon

    RAL-ICRA 2024

    [ Paper ]

  • MATE: Masked Autoencoders are Online 3D Test-Time Learners

    Muhammad Jehanzeb Mirza*, Inkyu Shin*, Wei Lin*, Andreas Schriebl, Kunyang Sun, Jaesung Choe,

    Horst Possegger, Mateusz Kozinski, In So Kweon, Kuk-Jin Yoon, Horst Bischof (*Equal contribution)

    ICCV 2023

    [ Paper | Code ]

  • TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation

    Taeyeop Lee, Jonathan Tremblay, Valts Blukis, Bowen Wen, Byeong-Uk Lee, Inkyu Shin, Stan Birchfield, In So Kweon, Kuk-Jin Yoon

    CVPR 2023

    [ Paper ]

  • Bidirectional Domain Mixup for Domain Adaptive Semantic Segmentation

    Daehan Kim*, Minseok Seo*, Kwanyong Park, Inkyu Shin, Sanghyun Woo

    AAAI 2023

    [ Paper ]

  • Learning Classifiers of Prototypes and Reciprocal Points for Universal Domain Adaptation

    Sungsu Hur, Inkyu Shin, Kwanyong Park, Sanghyun Woo, In So Kweon

    WACV 2023

    [ Paper ]

  • MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation

    Inkyu Shin, Yi-Hsuan Tsai, Bingbing Zhuang, Samuel Schulter, Buyu Liu, Sparsh Garg, In So Kweon, Kuk-Jin Yoon

    CVPR 2022

    [ Project page | Paper ]

  • UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation

    Taeyeop Lee, Byeong-Uk Lee, Inkyu Shin, Jaesung Choe, Ukcheol Shin, In So Kweon, Kuk-Jin Yoon

    CVPR 2022

    [ Paper ]

  • LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation

    Inkyu Shin, Dong-Jin Kim, Jae Won Cho, Sanghyun Woo, Kwanyong Park, In So Kweon

    ICCV 2021 [Oral]

    [ Paper ]

  • Unsupervised Domain Adaptation for Video Semantic Segmentation

    Inkyu Shin*, Kwanyong Park*, Sanghyun Woo, In So Kweon (*Equal contribution)

    arXiv

    [ Paper ]

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

    Kwanyong Park, Sanghyun Woo, Inkyu Shin, In So Kweon

    NeurIPS 2020

    [ Paper ]

  • Two-phase Pseudo Label Densification for Self-training based Domain Adaptation

    Inkyu Shin, Sanghyun Woo, Fei Pan, In So Kweon

    ECCV 2020

    *Also presented at CVPR 2020 Workshop(VL3)

    [ Paper ]

  • Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision

    Fei Pan, Inkyu Shin, Francois Rameau, Seokju Lee, In So Kweon

    CVPR 2020 [Oral]

    [ Project page | Paper | Code ]

Awards

  • Qualcomm Innovation Award, Qualcomm: 2020, 2021, 2022
  • Best MS Thesis Award, Future Vehicle in KAIST: 2021

Activities

Talks

  • Title: "How to do AI Research?" @ CGCL, KAIST. Aug 2024
  • Title: "Unsupervised Domain Adaptation" @ Naver Labs. Mar 2020

Conference Reviewer

  • NeurIPS: 2021, 2022, 2023, 2024
  • AAAI: 2022
  • CVPR: 2022, 2023, 2024
  • ICCV: 2023
  • ECCV: 2024
  • ICML: 2022, 2024
  • WACV: 2024, 2025