Hello! I am a Ph.D student in CSE at Seoul National University, and studying under the supervision of Prof. Gunhee Kim.

My research focuses on Visual Localization and 3D Dense Captioning for enhanced 3D scene understanding, with particular interest in: (i) understanding complex scenes from images and point clouds, (ii) effectively handling multi-modalities, and (iii) achieving a comprehensive understanding of 3D scenes through natural language.

Education

account_balance Seoul National University (SNU), Seoul, Korea ^{2018.03 - 2025.02}

• Integrated M.S./Ph.D. student in Computer Science and Engineering
• Cumulative GPA: 4.03 / 4.3 (4.23 / 4.5)
• Advisor: Prof. Gunhee Kim

school Sogang University, Seoul, Korea ^{2014.03 - 2018.02}

• B.S. in Computer Science and Engineering
• Cumulative GPA: 3.58 / 4.3 (3.88 / 4.5), Magna Cum Laude
• Advisor: Prof. Hyukjun Lee

Publications

• Bi-directional Contextual Attention for 3D Dense Captioning
  Minjung Kim, Hyung Suk Lim, Soonyoung Lee, Bumsoo Kim^*, Gunhee Kim^*
  ECCV 2024 (Oral presentation) [arXiv] [pdf] [poster] [HTML]

• Rethinking the Role of Queries in 3D Dense Captioning
  Minjung Kim, Gunhee Kim
  KCC 2024 [pdf]

• See It All: Contextualized Late Aggregation for 3D Dense Captioning
  Minjung Kim, Hyung Suk Lim, Seung Hwan Kim, Soonyoung Lee,
  Bumsoo Kim^*, Gunhee Kim^*
  ACL 2024 Findings [OpenReview] [arXiv] [pdf] [Underline]

• EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localization
  Minjung Kim, Junseo Koo, Gunhee Kim
  ICCV 2023 [arXiv] [pdf] [code]

• Indoor/Outdoor Transition Recognition Based on Door Detection
  Seohyun Jeon, Minjung Kim, Seunghwan Park, Jaeyoung Lee
  UR 2022 [pdf]

• Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration
  Jaekyeom Kim, Minjung Kim, Dongyeon Woo, Gunhee Kim
  ICLR 2021 [OpenReview] [arXiv] [pdf] [talk] [code]

• Logo Detection and Recognition Algorithm using YOLO-v3 Model
  Minjung Kim, Sungen Kim, Gunhee Kim
  CICS 2020 [pdf]

• Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks
  Youngjin Kim, Minjung Kim, Gunhee Kim
  ICLR 2018 [OpenReview] [arXiv] [pdf] [code]

• Machine Learning for Determining Duplicate Question
  Minjung Kim, Yeongjoon Park, Hyung Suk Lim, Jihoon Yang
  KCS 2017 [pdf]

• Sketch based Face Image Generation with Text Mapping
  Minjung Kim, Hyung Suk Lim, Yeongjoon Park, Yeseul Joo, Myoung Wan Koo
  KCS 2017 [pdf]

Experiences

work LG AI Research, Seoul, Korea ^{2023.06 - 2024.05}

• Vision and Multimodal Lab
• Research intern

Awards & Scholarships

• YoulChon AI Star Fellowship at YoulChon Foundation, Nongshim Group, 2024
• Animal Datathon Korea (2nd place, 2021)
• Samsung Humantech Paper Award (Silver Prize in Signal Processing, 2021)
• KSC 2017 Paper Award (Encouragement Award, 2018)
• Magna Cum Laude Honor at Sogang University, 2018
• Academic Excellence Scholarship at Sogang University, 2017 and 2018.
• Windows 10 IoT Core & Microsoft Azure for Microsoft IoT Solution Competition (10th place, 2017)

Professional Activities

• Reviewer of International Conferences
  European Conference on Computer Vision (ECCV) 2024
  International Conference on Computer Vision (ICCV) 2023
  Conference on Computer Vision and Pattern Recognition (CVPR) 2023, 2025
  Asian Conference on Computer Vision (ACCV) 2022
  International Conference on Learning Representations (ICLR) 2022, 2023
  Neural Information Processing Systems (NeurIPS) 2021, 2022, 2023, 2024
  

• Reviewer of International Journals
  International Journal of Computer Vision (IJCV) 2024
  

• Technical Coaching
  2022-3 SK hynix ML Engineer Technical Coaching