Home

Home

πŸ‘‹ Introduction

I’m SangEun Lee, a research scientist at ETRI in South Korea. My research aims to develop robust vision-language models capable of understanding, reasoning, and generating in complex real-world scenarios. I am particularly interested in emotion recognition, 3D vision, and multimodal representation learning, with a focus on designing effective data and learning frameworks for enhanced interpretability, efficiency, and generalization.

🌐 Contact

πŸ’Ό Experiences

AI Researcher, ETRI | 2023.01. – Present
Research on 3D object generation and webtoon-style image generation using diffusion models

Research Assistant, KT R&D Center | 2022.07. – 2022.08.
Research for improvement of Question Answering system with contrastive learning

πŸ† Awards & Honors

  • NEW 1st place in ABAW VA prediction challenge @ ICCV 2025, media
  • Outstanding Presentation Paper Award (μš°μˆ˜λ°œν‘œλ…Όλ¬Έμƒ) @ Korea Computer Congress, 2023
  • Honorable Mention in S-HERO Practical Problem-Solving Competition @ Sungkyunkwan University, 2021
  • 2nd Prize in In-school software development with AI contest @ Sungkyunkwan University, 2021
  • 3rd Prize in 2020 Bookathon Contest @ Sungkyunkwan University, 2020
  • 2nd Prize in Lifestyle Improvement App Development Contest @ Sungkyunkwan University, 2020

πŸ”§ Projects

πŸ“„ Publications

International (J: Journal / C: Conference)

  • NEW [C8] Lee, S., Lee, Y., Park, E.*, & Chae W. MASP: Multi-Aspect Guided Emotion Reasoning with Soft Prompt Tuning in Vision-Language Models. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI β€˜26), AAAI. (accepted)

  • [C7] Lee, Y., Lee, S., Park, C., Cha, J., Yang, J., & Park, E. (2025). BOVIS: Bias-Mitigated Object-Enhanced Visual Emotion Analysis. In Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM β€˜25), ACM. (accepted)

  • [C6] Lee, Y., Lee, S., Park, C., Cha, J., & Park, E*. (2025). Dynamic Temporal Gating Networks for Cross-Modal Valence-Arousal Estimation. In Proceedings of the 9th Workshop and Competition on Affective & Behavior Analysis in-the-wild (ABAW, ICCV Workshop β€˜25, pp. 61-70), IEEE.

  • [C5] Lee, S., Lee, Y., & Park, E.* (2025). EmoVLM-KD: Fusing Distilled Expertise with Vision-Language Models for Visual Emotion Analysis. In Proceedings of 8th Workshop and Competition on Affective & Behavior Analysis in-the-wild (ABAW, CVPR Workshop β€˜25, pp. 5633-5642), IEEE.

  • [J6] Lee, S., Kim, S., Lee, Y., Yang, J., & Park, E.* (2025). Enhancing Dimensional Image Emotion Detection with a Low-resource Dataset via Two-stage Training. IEEE Transactions on Cognitive and Developmental Systems (SCIE, JCR 2023 IF=5.0, Q1 in Neuroscience).

  • [C4] Lee, S., Chae, W., Kim, H. (2024). Retrieve-and-generate: Image-to-3D framework with mesh retrieval and texture generation. In Proceedings of the 15th International Conference on ICT Convergence.

  • [J5] Lee, S., Kim, S., Chu, Y., Choi, J., Park, E*. (2024). EAE-GAN: Emotion-Aware Emoji Generative Adversarial Network for Computational Modeling Diverse and Fine-Grained Human Emotions. IEEE Transactions on Computational Social Systems, 11(3), 3862-3872 (SCIE, JCR 2022 IF=5.0, Q1 in Computer Science, Cybernetics)

  • [C3] Yu, H., Lee, S., Yeo, B., Han, J., Park, E*. Pack, S. (2024). Towards a Lightweight Object Detection through Model Pruning Approaches In Proceedings of the 14th International Conference on ICT Convergence.

  • [C2] Lee, S., Chae, W., Kim, H. (2023). Generating Webtoon Scene Images with Latent Diffusion Models. In Proceedings of the 19th International Conference on Multimedia Information Technology and Applications.

  • [J4] Lee, S., Ryu, C., Park, E.* (2023) OSANet: Object Semantic Attention Network for Visual Sentiment Analysis. IEEE Transactions on Multimedia, 25, 7139-7148 (SCIE, JCR 2021 IF=8.182, Q1 in Computer Science, Information Systems).

  • [J3] Lee, S., Jeong, D., Park, E.* (2022) MultiEmo: multi-task framework for emoji prediction. Knowledge-Based Systems (SCIE, JCR 2020 IF=8.038, Q1 in Computer Science, Artificial Intelligence).

  • [C1] Lee, S., Oh, S., Kim, M., Park, E.* (2022) Measuring Embedded Human-like Biases in Face Recognition Models. In Proceedings of the 2022 Artificial Intelligence with Biased or Scarce Data Workshop (AIBSD β€˜22). AAAI.

  • [J2] Kim, J., Aum, J., Lee, S., Jang, Y., Park, E., Choi, D. (2021) FibVID: Comprehensive fake news diffusion dataset during the COVID-19 period. Telematics and Informatics, 64, 101688 (SSCI, JCR 2020 IF=6.182, Q1 in Information Science \& Library Science).

  • [J1] Choi, W., Kim, J., Lee, S., Park, E.* (2021) Smart home and Internet of Things: A bibliometric study. Journal of Cleaner Production, 301, 126908 (SCIE, JCR 2020 IF=9.297, Q1 in Engineering, Environmental).

Domestic

  • μ΄μƒμ€οΌŒ μ±„μ›μ„οΌŒ 유호영， κΉ€λ‚™μš°οΌŒ κΉ€ν˜„μ§„, ν”ŒλžœνŠΈ μ‚°μ—…μ—μ„œμ˜ Image-to-3D μ„±λŠ₯ ν–₯상을 μœ„ν•œ 사전 이미지 처리 ν”„λ ˆμž„μ›Œν¬, 2025 ν•œκ΅­μ»΄ν“¨ν„°μ’…ν•©ν•™μˆ λŒ€νšŒ.

  • μ΄μƒμ€οΌŒ μ±„μ›μ„οΌŒ κΉ€ν˜„μ§„, 메쉬 검색과 ν…μŠ€μ²˜ 생성이 κ²°ν•©λœ 단일 이미지 기반 3D 객체 볡원 λͺ¨λΈ, 2024 ν•œκ΅­μ»΄ν“¨ν„°μ’…ν•©ν•™μˆ λŒ€νšŒ.

  • μ΄μƒμ€οΌŒ μ±„μ›μ„οΌŒ κΉ€ν˜„μ§„, (2024) λ‹€μ–‘ν•œ λ§₯λ½μ—μ„œμ˜ μ›Ήνˆ° 캐릭터 이미지 생성을 μœ„ν•œ 잠재 ν™•μ‚° λͺ¨λΈ μž¬ν•™μŠ΅, μ •λ³΄κ³Όν•™νšŒ μ»΄ν“¨νŒ…μ˜ μ‹€μ œ 논문지 30ꢌ 2호, 70 - 76.

  • μ΄μƒμ€οΌŒ μ±„μ›μ„οΌŒ κΉ€ν˜„μ§„, 잠재 ν™•μ‚° λͺ¨λΈ μž¬ν•™μŠ΅μ„ ν†΅ν•œ λ§₯락별 μ›Ήνˆ° 캐릭터 이미지 생성 기술, 2023 ν•œκ΅­μ»΄ν“¨ν„°μ’…ν•©ν•™μˆ λŒ€νšŒ.

  • μ΄μƒμ€οΌŒ κΉ€μ§€μˆ˜οΌŒ κΉ€μ§€λ‚˜οΌŒ 박은일*, μ—”μ €νŒŒμŠ€μΏ μ•ŒλΈν¬λΉŒ, μ†Œμ…œ λ„€νŠΈμ›Œν¬ μ„œλΉ„μŠ€ λ‚΄ λΉ„λ‚œκ³Ό 혐였 μ „νŒŒμ— λŒ€ν•˜μ—¬: COVID-19 을 μ€‘μ‹¬μœΌλ‘œ, 2021 ν•œκ΅­HCIν•™νšŒ ν•™μˆ λŒ€νšŒ.

πŸŽ“ Education

M.Sc. in Applied Artificial Intelligence
Sungkyunkwan University, Seoul, South Korea (2021.09. – 2023.02.)
Major GPA: 4.25/4.5

Bachelor of Applied Artificial Intelligence
Sungkyunkwan University, Seoul, South Korea (2018.03. - 2021.08.)
Major GPA: 4.33/4.5, Cumulative GPA: 4.24/4.5
Award: Graduating with Highest Honors (Summa Cum Laude)