publications

2026

1. IEEE Access

   Cap4Bridge: Caption-Guided Cross-Modal Contextualization with Stochastic Augmentation for Text-Video Retrieval

   MinJu Jeon, Hyungee Kim, Si-Woo Kim, Youngtaek Oh, Soeun Lee, and Dong-Jin Kim

   IEEE Access, 2026

   Bib

   @article{jeon2026cap4bridge,
     title = {Cap4Bridge: Caption-Guided Cross-Modal Contextualization with Stochastic Augmentation for Text-Video Retrieval},
     author = {Jeon, MinJu and Kim, Hyungee and Kim, Si-Woo and Oh, Youngtaek and Lee, Soeun and Kim, Dong-Jin},
     journal = {IEEE Access},
     year = {2026},
   }

2. CVPR

   

   Follow the Saliency: Supervised Saliency for Retrieval-augmented Dense Video Captioning

   Seunghee Choi, MinJu Jeon, Hyunwoo Oh, Jihwan Lee, and Dong-Jin Kim

   arXiv preprint arXiv:2603.11460, 2026

   Accepted at CVPR 2026

   Bib

   @article{choi2026follow,
     title = {Follow the Saliency: Supervised Saliency for Retrieval-augmented Dense Video Captioning},
     author = {Choi, Seunghee and Jeon, MinJu and Oh, Hyunwoo and Lee, Jihwan and Kim, Dong-Jin},
     journal = {arXiv preprint arXiv:2603.11460},
     note = {Accepted at CVPR 2026},
     year = {2026},
   }

3. CVPR

   

   SAIL: Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense Video Captioning

   Ye-Chan Kim, SeungJu Cha, Si-Woo Kim, MinJu Jeon, Hyungee Kim, and Dong-Jin Kim

   arXiv preprint arXiv:2603.05437, 2026

   Accepted at CVPR 2026

   Bib

   @article{kim2026sail,
     title = {SAIL: Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense Video Captioning},
     author = {Kim, Ye-Chan and Cha, SeungJu and Kim, Si-Woo and Jeon, MinJu and Kim, Hyungee and Kim, Dong-Jin},
     journal = {arXiv preprint arXiv:2603.05437},
     note = {Accepted at CVPR 2026},
     year = {2026},
   }

2025

1. EMNLP

   

   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 Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

   Bib

   @inproceedings{jeon2025sali4vid,
     title = {Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioning},
     author = {Jeon, MinJu and Kim, Si-Woo and Kim, Ye-Chan and Kim, HyunGee and Kim, Dong-Jin},
     booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
     pages = {25788--25801},
     year = {2025},
   }

2. ACM MM

   

   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 Proceedings of the 33rd ACM International Conference on Multimedia, 2025

   Bib

   @inproceedings{kim2025sync,
     title = {SynC: Synthetic Image Caption Dataset Refinement with One-to-many Mapping for Zero-shot Image Captioning},
     author = {Kim, Si-Woo and Jeon, MinJu and Kim, Ye-Chan and Lee, Soeun and Kim, Taewhan and Kim, Dong-Jin},
     booktitle = {Proceedings of the 33rd ACM International Conference on Multimedia},
     pages = {2683--2692},
     year = {2025},
   }