Hello! I’m Inpyo Song, a master’s student researching computer vision and artificial intelligence, advised by Prof. Jangwon Lee. My goal is to develop AI that truly works in the real world. Rather than models that only perform well in controlled laboratory settings, I’m focused on creating vision systems that can operate reliably in complex, unpredictable real-world environments. Currently, I’m working on object tracking, anomaly detection, human pose estimation, and traffic accident anticipation in autonomous driving. My research centers around one core question: how can we build AI vision models that are robust enough to handle the messy, chaotic nature of the real world? Also, I am honored to collaborate with Prof. David Crandall from Indiana University Bloomington.
You can find my CV here. I am always open to any form of collaboration. If you have any ideas for potential collaboration, or just feel like having a casual chat, please feel free to reach out!
🔥 News
- May. 2025: 🎉 Two papers accepted at ICIP 2025.
- Feb. 2025: 🏆 Selected for I-Corps Korea Program
- Dec. 2024: 🎉 One paper accepted at WACV 2025.
- Oct. 2024: 🎉 SFTrack presented as Long Oral Presentation at IROS 2024.
- Oct. 2024: 🏆 Received Excellence Award at SKKU Graduate Student Start-up Competition.
- Sep. 2024: 🎉 One paper accepted at CVIU.
- Aug. 2024: 🏆 Received President’s Award from IITP at 2024 Digital Innovation Talent Symposium.
- Jun. 2024: Thrilled to join the Indiana University Bloomington CVLab as an intern!
- Jun. 2024: 🎉 One paper accepted at IROS 2024.
📝 Publications (Selected)
-
Real-Time Traffic Accident Anticipation with Feature Reuse
Inpyo Song, Jangwon Lee
ICIP'25 [Accepted] | [Project page] | [arXiv] -
PawPrint: Whose Footprints Are These? Identifying Animal Individuals by Their Footprints
Inpyo Song, Hyemin Hwang, Jangwon Lee
ICIP'25 [Accepted] | [Project page] | [arXiv]) | [code] -
Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Camera
Inpyo Song, Sanghyeon Lee, Minjun Joo, Jangwon Lee
WACV'25 | [Project page] | [paper] | [arXiv] | [code] -
(Long Oral) SFTrack: A Robust Scale and Motion Adaptive Algorithm for Tracking Small and Fast Moving Objects
Inpyo Song, Jangwon Lee
IROS'24 | [Project page] | [paper] | [arXiv] | [code] -
Action-conditioned Contrastive Learning for 3D Human Pose and Shape Estimation in Videos
Inpyo Song, Moonwook Ryu, Jangwon Lee
CVIU'24 (IF: 4.3) | [paper] | [code] -
Motion-aware Heatmap Regression for Human Pose Estimation in Videos
Inpyo Song, Jongmin Lee, Moonwook Ryu, Jangwon Lee
IJCAI'24 (14.0 % acceptance rate) | [paper] -
Video Question Answering for People with Visual Impairments Using an Egocentric 360-Degree Camera
Inpyo Song, Minjun Joo, Joonhyung Kwon, Jangwon Lee
CVPRW'24 | [arXiv]
🎖 Honors and Awards
- Feb. 2025 Selected for I-Corps Korea Program, (VLM-based Arduino Tutor)
- Oct. 2024 Excellence Award, SKKU Graduate Student Startup Competition (Multimodal VQA-Based Tutoring System for the Digital Transformation of Hands-On Education)
- Aug. 2024 President’s Award from IITP, 2024 Digital Innovation Talent Symposium (Motion-Aware Heatmap Regression for Human Pose Estimation in Videos)
- Feb. 2024 Encouragement Award, SKKU Research Matters (Technological Social Responsibility: Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Camera)
- Dec. 2022 Grand Award from SKKU, KAU Start-up Idea Competition (Generating Digital Twin using Instance-NeRF)
💻 Internships
- Jun. 2024 - Aug. 2024, Research Intern @ Indiana University Bloomington CVLab, Bloomington, IN, USA
🤝 Services
- Emergency Reviewer, ICDL 2024
- Emergency Reviewer, WACV 2025