I am a third year Ph.D. student at SKKU(Sungkyunkwan University), South Korea, advised by Prof. Sungeun Hong in the Artificial and Medial Lab AIM Lab. My recently research interests include Multimodal Learning, Audio-Visual Recognition, Parameter-Efficient Model Tuning and Test-Time Adaptation.

🔥 News

• 2025.04: 🎉🎉 One paper is accepted to CVPR 2025 (Highlight).
• 2025.01: 🎉🎉 One paper is accepted to Pattern Recognition (Q1, JCR: Top 6.9%).
• 2023.06: 🎉🎉 One paper is accepted to ICMR 2023 (Oral).
• 2022.12: 🎉🎉 One paper is accepted to ACCV 2022 (Oral).

📝 Selected Publications

• Question-Aware Gaussian Experts for Audio-Visual Question Answering

  • Hongyeob Kim*, Inyoung Jung*, Dayoon Suh, Youjia Zhang, Sangmin Lee and Sungeun Hong
  • CVPR 2025 [Highlight] [Project page]

• Memory-Efficient Cross-Modal Attention for RGB-X Segmentation and Crowd Counting

  • Youjia Zhang, Soyun Choi, and Sungeun Hong
  • Pattern Recognition 2025 [Q1] [DOI]

• Intra-inter modal attention blocks for RGB-D semantic segmentation

  • Soyun Choi, Youjia Zhang, and Sungeun Hong
  • ICMR 2023 [Oral] [Project page]

• Spatio-channel attention blocks for cross-modal crowd counting

  • Youjia Zhang, Soyun Choi, and Sungeun Hong
  • ACCV 2022 [Oral] [Project page]

📂 Projects

• RGB-X Path Networks for Multi-modal Multi-task Learning (2023.03 ~ 2026.02)

  • Funded by National Research Foundation of Korea (NRF)
  • Develop path networks for RGB-X data (e.g., depth, thermal, tactile, text) to enable efficient multi-modal fusion and knowledge transfer across tasks and environments, thereby supporting generalization and adaptability in complex real-world settings

• Visuo-Tactile Perception for Human-Like Manipulation of Deformable Objects with Dynamic Center of Mass (2021.09 ~ 2023.08)

  • Funded by Samsung Research Funding & Incubation Center for Future Technology
  • Develop core technologies for stable grasping and manipulation of soft, deformable objects through “visual-tactile fusion” and “visual-tactile perception” for robots to manipulate objects at the human level.

💡 Patents

• Spatio-channel attention blocks for cross-modal crowd counting (Registration number C-2022-055027)

🏆 Honors & Awards

• IEIE Encouraging Paper Award, 2024
• SKKU Full Scholarship, 2024 – Present
• Oral Presentation, ACCV 2022
• 2BK21 Excellent Research Award, Inha University, 2023
• Global Vision Scholarship, Inha University, 2021 – 2023
• Mathematical Contest in Modeling(MCM), Meritorious Winners，2017

📚 Academic Activities

• Reviewer
  • ACM International Conference on Multimedia (ACM MM)
  • Neural Information Processing Systems (NeurIPS)
• Teaching Assistant
  • Introduction to Deep Learning, Spring 2025
  • Advanced Computer Vision, Fall 2024
  • Computer Vision, Fall 2021

🎓 Education

• 2024–Present: Ph.D. Student, Department of Immersive Media Engineering, Sungkyunkwan University, advised by Prof. Sungeun Hong
• 2021–2024: Ph.D. Student, Department of Electrical and Computer Engineering, Inha University, advised by Prof. Sungeun Hong
• 2018–2021: M.S., School of Computer Science and Technology, CQUPT, advised by Prof. Xu Zhang
• 2014–2018: B.S., School of Mathematics and Statistics, Chongqing University of Posts and Telecommunications (CQUPT)