About me

I'm Junho Koh, Ph.D. candidate at Hanyang University, advised by Prof. Jun Won Choi. Previously, I graduated from Hanyang University with a B.S. degree under Prof. Jun Won Choi. My research interests are in machine learning, computer vision, and Intelligent vehicles, with a focus on object detection with deep learning, 2D/3D Video object detection, and Sensor fusion based on 3D object detection and tracking.

Research Interests

My research interest areas as followed

• Perception for intelligent vehicles and mobile robots

• LiDAR and camera based 3 dimensional object detection

• Sensor fusion-based perception

• Object tracking and video object detection

Publications (* indicates equal contributions)

• MGTANet: Encoding sequential LiDAR points using long short-term motion-guided temporal attention for 3D object detection

Junho Koh*, Junhyung Lee*, Youngwoo Lee, Jaekyum Kim, Jun Won Choi

Association for the Advancement of Artificial Intelligence (AAAI), 2023 (Acceptance: 1,721/8,777 < 20%, Oral presentation)

(ranked 3rd among LiDAR methods on nuScenes object detection benchmark as of August 2022)

• D-Align: Dual query co-attention network for 3D object detection based on multi-frame point cloud sequence

Junhyung Lee, Junho Koh, Youngwoo Lee, Jun Won Choi

IEEE International Conference on Robotics and Automation (ICRA), 2023.

• Joint 3D object detection and tracking using spatio-temporal representation of camera image and LiDAR point clouds 

Junho Koh*, Jaekyum Kim*, Jinhyuk Yoo, Yecheol Kim, Dongsuk Kum, Jun Won Choi

Association for the Advancement of Artificial Intelligence (AAAI), 2022 (Acceptance: 1,349/9,251 < 15%)

• Joint representation of temporal image sequences and object motion for video object detection

Junho Koh*, Jaekyum Kim*, Younji Shin, Byeongwon Lee, Seungji Yang, Jun Won Choi

IEEE International Conference on Robotics and Automation (ICRA), 2021. (Oral presentation)

• Video object detection using object's motion context and spatio-temporal feature aggregation

Junho Koh*, Jaekyum Kim*, Jun Won Choi

IEEE International Conference on Pattern Recognition (ICPR), 2020

• Enhanced object detection in bird's eye view using 3D global context inferred from Lidar point data

Yecheol Kim, Jaekyum Kim, Junho Koh, Jun Won Choi

IEEE Intelligent Vehicles Symposium (IV), 2019

• Robust deep multi-modal learning based on gated information fusion network

Jaekyum Kim, Junho Koh, Yecheol Kim, Youngbae Hwang, Jun Won Choi

Asian Conference on Computer Vision (ACCV), 2018

• Robust camera lidar sensor fusion via deep gated fusion network

Jaekyum Kim, Jaehyung Choi, Yecheol Kim, Junho Koh, Chung Choo Chung, and Jun Won Choi

IEEE Intelligent Vehicles Symposium (IV), 2018 (among 5% selected as single track oral presentation)