Minkuk Kim

PhD Student (2024.9~)
Master Student (2022.9~2024.8)

Department of Artificial Intelligence, Kyung Hee University

Contact
asdjklfgh97@khu.ac.kr
Personal Homepage
#351, Electronic Information College Building, 1732 Deogyeong-daero, Giheung-gu, Yongin, Gyeonggi-do, 17104, South Korea

Research Interest

  • Dense Video Captioning
  • Retrieval Augmented Generation
  • Long Video Understanding

Publication

  • [C4] ReQuest: Rethinking-based Question-Aware Frame Selection for Long-Form Video QA
    Minkuk Kim†, Suyong Yun†, Young Tae Kim, Jinyoung Moon, Jinwoo Choi, Seong Tae Kim
    European Conference on Computer Vision (ECCV), 2026 (Malmö)

  • [C3] HiCM2: Hierarchical Compact Memory Modeling for Dense Video Captioning
    Minkuk Kim, Hyeon Bae Kim, Jinyoung Moon, Jinwoo Choi, Seong Tae Kim
    AAAI Conference on Artificial Intelligence (AAAI), 2025 (Philadelphia)
    Paper | Poster | GitHub

  • [C2] Retrieval-Augmented Natural Language Reasoning for Explainable Visual Question Answering
    Su Hyeon Lim, Minkuk Kim, Hyeon Bae Kim, Seong Tae Kim
    Integrating Image Processing with Large-Scale Vision/Language Models for Advanced Visual Understanding Workshop at International Conference on Image Processing (ICIPW), 2024 (Abu Dhabi)

  • [C1] Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval
    Minkuk Kim, Hyeon Bae Kim, Jinyoung Moon, Jinwoo Choi, Seong Tae Kim
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 (Seattle)
    Paper | Poster | GitHub

  • [J1] Exploiting Recollection Effects for Memory-based Video Object Segmentation
    Enki Cho, Minkuk Kim, Hyung-Il Kim, Jinyoung Moon, Seong Tae Kim
    Image and Vision Computing, 2023