Si-Woo Kim

About

I am a second-year integrated M.S./Ph.D. student in the Department of Data Science at Hanyang University. My research focuses on Vision-Language Models, Zero-shot Image Captioning, and Computer Vision. I’m particularly interested in bridging synthetic and real data for zero-shot learning scenarios.

Research Keywords: VLM, Image Captioning, Video Captioning, Synthetic Data, Zero-shot Learning, Cross-modal Retrieval

News

Feb 2026 1 paper accepted to CVPR 2026

Jan 2026 1 paper accepted to IEEE Access

Sep 2025 Awarded NRF Graduate Research Fellowship

Jul 2025 3 papers accepted to ACM MM 2025 - including 1 first authored paper

Jun 2025 Best Paper Award (2nd rank) at IEIE, sponsored by Samsung Electronics

Sep 2025 1 paper accepted to EMNLP 2025

Dec 2024 1 paper accepted to AAAI 2025

Sep 2024 1 paper accepted to EMNLP 2024 — first publication!

Publications

* denotes equal contribution. Full list on Google Scholar.

2026

C.7

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, HynGee Kim, Dong-Jin Kim

CVPR 2026

J.1

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

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

IEEE Access 2026

2025

C.6

Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioning

MinJu Jeon, Si-Woo Kim, Ye-Chan Kim, HyunGee Kim, Dong-Jin Kim

EMNLP 2025

Also at ICCV 2025 Workshop — "Multi-Modal Reasoning for Agentic Intelligence"

Paper

C.5

CatchPhrase representative method figure

CatchPhrase: EXPrompt-Guided Encoder Adaptation for Audio-to-Image Generation

Hyunwoo Oh, SeungJu Cha, Kwanyoung Lee, Si-Woo Kim, Dong-Jin Kim

ACM MM 2025

Paper

C.4

SIDA: Synthetic Image Driven Zero-shot Domain Adaptation

Ye-Chan Kim, SeungJu Cha, Si-Woo Kim, Taewhan Kim, Dong-Jin Kim

ACM MM 2025

Also at ICCV 2025 Workshop — "Curated Data for Efficient Learning"

Paper

C.3

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, Dong-Jin Kim

ACM MM 2025 First Author

Also at ICCV 2025 Workshop — "Curated Data for Efficient Learning"

Paper Code

C.2

ViPCap: Retrieval Text-Based Visual Prompts for Lightweight Image Captioning

Taewhan Kim, Soeun Lee, Si-Woo Kim, Dong-Jin Kim

AAAI 2025

Also at NeurIPS 2024 Workshop — "Adaptive Foundation Models"

Paper

2024

C.1

IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning

Soeun Lee*, Si-Woo Kim*, Taewhan Kim, Dong-Jin Kim

EMNLP 2024 Co-first Author

Also at NeurIPS 2024 Workshops — "Adaptive Foundation Models" & "Video-Language Models"

Paper Code

Education & Experience

Integrated M.S./Ph.D. in Data Science

Hanyang University Sep 2024 — Present

GPA 4.44/4.50 · Advisor: Prof. Dong-Jin Kim

B.S. in Computer Science

Hanyang University Feb 2018 — Aug 2024

GPA 4.22/4.50 (Major 4.31) · Summa Cum Laude

Research Intern

KIST — Center for AI Sep 2021 — Feb 2022

Multi-person 3D pose estimation & action recognition

Summer Intern — Memory Division

Samsung Electronics Mar 2022 — Jun 2022

Developed deadline functionality on CI/CD system

Honors & Grants

Best Paper Award (Excellence, 2nd rank) — IEIE — Samsung Electronics , 2025

NRF Graduate Research Fellowship — National Research Foundation of Korea (12M KRW) , 2025–2026

AI SeoulTech Graduate School Scholarship — Seoul Scholarship Foundation (5M KRW) , 2025

Master's Scholarship for Excellence in Science & Engineering — Korea Student Aid Foundation (KOSAF) (7.5M KRW) , 2025–2026

Misc

When I’m not training models or writing papers, I enjoy cooking and knitting. I believe the patience required for both translates well to research.

Conference Oct 2025

Cooking Jul 2025

Knitting Mar 2026

Academic Service

Reviewer: 2025 — ACL SRW. 2026 — AAAI, CVPR, ECCV, NeurIPS.