MinJu Jeon

At ICCV 2025, Honolulu, Hawaii

Hi! I'm MinJu Jeon, a Master's student in Data Science at Hanyang University, advised by Prof. DongJin Kim, and currently a Research Intern at Naver Cloud, Voice Tech team.
My research centers on 🧠 Multimodal learning, spanning 🎬 Vision-language understanding (dense video captioning, text-video retrieval) and 🗣️ Multilingual speech (G2P, text-to-speech). I'm also drawn to ⚙️ Data-centric methods that improve model robustness across modalities and languages.

News

June 2026Joining LG AI Research as a Research Intern at the EXAONE Lab (Incoming)

Mar 2026Cap4Bridge accepted at IEEE Access 2026

Feb 2026Two papers accepted at CVPR 2026

Dec 2025Started research internship at Naver Cloud, Voice Tech Team

Aug 2025Sali4Vid accepted at EMNLP 2025 (Long, Main)

Background

June 2026 – Incoming

Research Intern, LG AI Research · EXAONE Lab
Incoming

Dec 2025 – Present

Research Intern, Naver Cloud · Voice Tech Team
Multilingual G2P & robust TTS for non-canonical text

Sep 2024 – Present

M.S. in Data Science, Hanyang University

Mar 2020 – Aug 2024

B.S. in Industrial Engineering, Hanyang University

selected publications

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

Dense Video Captioning Data-Centric

Abs Bib

A dense video captioning framework that reweights video frames by saliency and adaptively retrieves relevant captions at inference time. By concentrating supervision on semantically important moments and grounding generation in retrieved context, Sali4Vid produces more accurate and temporally localized descriptions.
@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}, }
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

Text-Video Retrieval Data-Centric

Abs Bib

Cap4Bridge bridges the text-video modality gap by using generated captions as cross-modal context, enriched through stochastic augmentation during training. The method improves robustness and generalization in text-video retrieval without requiring additional human supervision.
@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}, }
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

Zero-shot Captioning Data-Centric

Abs Bib

SynC refines noisy synthetic image-caption datasets through a one-to-many mapping that re-aligns each image with its best-matching captions from the generated pool. This data-centric refinement boosts zero-shot image captioning performance without any additional human annotation.
@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}, }
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

Dense Video Captioning

Abs Bib

A retrieval-augmented dense video captioning approach that injects supervised saliency signals into both the retrieval and generation stages. The saliency guidance helps the model focus on temporally important moments, producing more grounded and informative captions.
@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}, }
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

Dense Video Captioning

Abs Bib

SAIL tackles weakly-supervised dense video captioning through similarity-aware guidance and inter-caption augmentation. The framework reduces reliance on dense temporal annotations while maintaining strong captioning quality.
@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}, }