publications

2025

  1. EMNLP
    Sali4Vid.png
    Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioning
    MinJu Jeon, Si-Woo Kim, Ye-Chan Kim, HyunGee Kim, and Dong-Jin Kim
    In Empirical Methods in Natural Language Processing EMNLP, 2025
  2. MM
    SIDA.png
    SIDA: Synthetic Image Driven Zero-shot Domain Adaptation
    Ye-Chan Kim, SeungJu Cha, Si-Woo Kim, Taewhan Kim, and Dong-Jin Kim
    In ACM Multimedia, 2025
  3. MM
    Sync.png
    SynC: Synthetic Image Caption Dataset Refinement with One-to-many Mapping for Zero-shot Image Captioning
    Si-Woo Kim, MinJu Jeon, Ye-Chan Kim, Soeun Lee, Taewhan Kim, and Dong-Jin Kim
    In ACM Multimedia, 2025
  4. CVPR
    Verbdiff.png
    VerbDiff: Text-Only Diffusion Models with Enhanced Interaction Awareness
    SeungJu Cha, Kwanyoung Lee, Ye-Chan Kim, Hyunwoo Oh, and Dong-Jin Kim
    In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2025