InPyo Song

In-Pyo Song

Computer Vision with Artificial Intelligence

Hello I'm InPyo Song, a M.S. student at Sungkyunkwan University. I'm interested in computer vision and deep learning. Specifically, I'm working on human pose estimation, anomaly detection and video question answering.

Education

Sungkyunkwan University (SKKU)

Sep. 2023 - Current
M.S., Major in Immersive Media
Intelligence and Interactive Systems Lab, Directed by Prof. Jangwon Lee

Korea AeroSpace University (KAU)

Mar. 2016 - Feb. 2023
B.S., Major in Mechanical Engineering

Internship

Indiana University Bloomington / Bloomington, IN, US

Jun. 2024 – Aug. 2024
Research Intern

Publications

"Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Camera", InPyo Song, Sanghyun Lee, Minjoon Joo, and Jangwon Lee

Feb. 2025
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025)

"SFTrack: A Robust Scale and Motion Adaptive Algorithm for Tracking Small and Fast Moving Objects", InPyo Song, and Jangwon Lee

Oct. 2024
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024) [Selected Oral]
SFTrack Demonstration

"Action-Conditioned Contrastive Learning for 3D Human Pose and Shape Estimation in Videos", InPyo Song, Moonwook Ryu, and Jangwon Lee

Sep. 2024
Elsevier Computer Vision and Image Understanding (CVIU), IF: 4.3, Q1(2023)
ACMR Demonstration

"Motion-Aware Heatmap Regression for Human Pose Estimation in Videos", InPyo Song, Jongmin Lee, Moonwook Ryu, and Jangwon Lee

Aug. 2024
International Joint Conferences on Artificial Intelligence (IJCAI 2024)
MTPose image

"Video Question Answering for People with Visual Impairments Using an Egocentric 360-Degree Camera", InPyo Song, Minjun Joo, Joonhyung Kwon, and Jangwon Lee

Jun. 2024
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2024) Workshop on First Joint Egocentric Vision (EgoVis)
VIEWQA Sample
Additional Publications

"Scale and Motion Adaptive Multi-Object Tracking Algorithm for Unmanned Aerial Vehicles", InPyo Song, and Jangwon Lee

Aug. 2023
IEEE International Conference on Robot & Human Interactive Communication (RO-MAN 2023), Late-Breaking Reports
  • Accepted for Poster Presentation, Not Published

"Smooth and Consistent Pose Estimation with Intersections Module", Jongmin Lee*, InPyo Song* (Equal Contribution), Moonwook Ryu, Jangwon Lee

Jun. 2024
The Korean Institute of Broadcast and Media Engineers (KIBME 2024) Summer Conference

"Multi-task Learning in Facial Kinship Verification", Inpyo Song, and Jangwon Lee,

Jun. 2023
The Korean Institute of Broadcast and Media Engineers (KIBME 2023) Summer Conference

Honors & Awards

Excellence Award, Jongmin Lee, InPyo Song, and Hanna Cho, “2024 SKKU Graduate Student Startup Competition”

Oct. 2024
SKKU Startup Support Center

President’s Award from IITP, Jongmin Lee, and Inpyo Song, “Motion-Aware Heatmap Regression for Human Pose Estimation in Videos”

Aug. 2024
Digital Innovation Talent Symposium

Encouragement Award, Inpyo Song, “Technological Social Responsibility: Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Camera”

Feb. 2024
SKKU Research Matters

Grand Award, Heetae Lee, Inpyo Song, and Suho Jang, “Generating Digital Twin using Instance-NeRF”

Dec. 2022
KAU Start-up Idea Competition

Services

Emergency Reviewer :
  • IEEE International Conference on Development and Learning (ICDL), 2024
  • IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025

Reference

Jangwon Lee
  • Associate Professor, SungKyunKwan University, Department of Immersive Media Engineering
David J. Crandall
  • Luddy Professor of Computer Science, Indiana University Bloomington