SJ Kim

I am an M.S. candidate at Kyung Hee University's Visual Science Lab (VSLab), advised by Prof. MyeongAh Cho.

My research focuses on motion prediction and 3D perception, specifically Multi-Object Tracking and 3D Object Detection with multi-sensor fusion. Currently, I am exploring 3D Neural Rendering for Novel-View Synthesis with 3D Gaussian Splatting (3D GS) and Neural Radiance Fields (NeRF), aiming to advance computer vision technologies for understanding dynamic 3D environments.

Email  /  CV  /  Github  /  Google Scholar

profile photo

News

[Nov. 2025] One paper got accepted at AAAI 2026! (Acceptance rate: 17.6%)

Research

plugtrack
PlugTrack: Multi-Perceptive Motion Analysis for Adaptive Fusion in Multi-Object Tracking
Seungjae Kim, SeungJoon Lee, MyeongAh Cho
AAAI, 2026
arXiv / code

PlugTrack is a plug-and-play motion prediction framework that adaptively fuses Kalman filter and any data-driven motion predictors for robust multi-object tracking.


This website's source code is borrowed from Jon Barron's website template.