Geuntaek Lim

I'm M.S student at Robotics and Computer Vision Lab. at Sejong University.

gtlim.jpg

Sejong University, AI Center 437

Seoul, South Korea

I am currently pursuing my master’s degree under the supervision of professor Yukyung Choi at the Robotics and Computer Vision Lab. My research focuses on Computer Vision, specifically Video Understanding. I am deeply interested in exploring the following three key areas for a comprehensive understanding of videos:

  1. Human Action Understanding: I view distinguishing dynamic human behaviors as a foundational task that necessitates temporal modeling.

  2. Scene Graph Representation: I believe it offers essential frameworks for organizing and interpreting the intricate visual data present in videos.

  3. Open-Vocabulary Learning: I consider it crucial for enabling robust inference in various unseen scenarios, which is vital for practical applications.

news

Jul 15, 2024 📃 A paper on weakly supervised temporal action localization got accepted to ACM MM 2024.
Dec 09, 2023 📃 A paper on content-based video retrieval got accepted to AAAI 2024.

education

Mar 02, 2023 M.S. Dept. of Intelligent Mechatronics Engineering in Sejong University.
Mar 02, 2017 B.S. Dept. of Intelligent Mechatronics Engineering in Sejong University. (GPA 4.15/4.5)

selected publications

  1. MM
    fig_PVLR.png
    Probabilistic Vision-Language Representation for Weakly Supervised Temporal Action Localization
    Geuntaek Lim, Hyunwoo Kim, Joonsoo Kim, and Yukyung Choi†
    In ACM Multimedia (MM) , 2024
  2. AAAI
    fig_VVS.png
    VVS: Video-to-video retrieval with irrelevant frame suppression
    Won Jo, Geuntaek Lim, Gwangjin Lee, Hyunwoo Kim, Byungsoo Ko, and Yukyung Choi†
    In Association for the Advancement of Artificial Intelligence (AAAI) , 2024
  3. IEEE Access
    fig_SRA.png
    Simultaneous Video Retrieval and Alignment
    Won Jo, Geuntaek Lim, Yujin Hwang, Gwangjin Lee, Joonsoo Kim, Joungil Yun, Jiyoung Jung, and Yukyung Choi†
    IEEE Access, 2023
  4. IEEE Access
    fig_tnip.png
    Exploring the temporal cues to enhance video retrieval on standardized cdva
    Won Jo, Geuntaek Lim, Joonsoo Kim, Joungil Yun, and Yukyung Choi†
    IEEE Access, 2022