Publications
(Last update: 2023.08.30.)
You can also find my articles on Google Scholar profile.
Journal Papers
Youngseok Kim, Sanmin Kim, Sangmin Sim, Jun Won Choi and Dongsuk Kum “Boosting Monocular 3D Object Detection with Object-Centric Auxiliary Depth Supervision,” IEEE Transactions on Intelligent Transportation Systems (T-ITS), 2022. [Paper, Video Demo]
* Ranked 1st/3rd among published monocular methods on KITTI BEV/3D detection benchmark as of 2021 April
* Introduced in KAIST breakthroughs 2021
Conference Papers
Youngseok Kim, Sanmin Kim, Juyeb Shin, Jun Won Choi, and Dongsuk Kum, “CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perception,” IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, 2023. [Paper, Video Demo]
* Preliminary version is published in ICLR SR4AD Workshop [Paper, Presentation]
* Ranked 1st among camera-radar methods on nuScenes detection benchmark as of March 2023
* Presented at 2023 KAIST Future Mobility Conference (Korean)
Sanmin Kim, Youngseok Kim, In-Jae Lee, Dongsuk Kum, “Predict to Detect: Prediction-guided 3D Object Detection using Sequential Images,” IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, 2023. [Paper]
Youngseok Kim, Sanmin Kim, Jun Won Choi and Dongsuk Kum, “CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer,” AAAI Conference on Artificial Intelligence (AAAI), Washington, DC, USA, 2023. [Paper, Presentation, Video Demo]
* Ranked 1st among camera-radar methods on nuScenes detection benchmark as of July 2022
* Introduced in 2023 KAIST Annual R&D Report (English), 대표연구성과 (Korean)
Sihwan Hwang, Sanmin Kim, Youngseok Kim and Dongsuk Kum, “Joint Semi-Supervised and Active Learning via 3D Consistency for 3D Object Detection,” IEEE International Conference on Robotics and Automation (ICRA), London, UK, 2023. [Paper]
Sangmin Sim, Youngseok Kim and Dongsuk Kum, “Sequential Image-based 3D Object Detection with Location Refinement,” IEEE 26th International Conference on Pattern Recognition (ICPR), Montréal, Québec, 2022. [Paper]
Youngseok Kim, Jun Won Choi and Dongsuk Kum, “GRIF Net: Gated Region of Interest Fusion Network for Robust 3D Object Detection from Radar Point Cloud and Monocular Image,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vagas, NV, USA (Virtual), 2020. [Paper, Presentation, Video Demo]
* Presented at Seoul Mobility Show 2021 Conference (Virtual)
Jinhyeong Kim*, Youngseok Kim* and Dongsuk Kum, “Low-level Sensor Fusion Network for 3D Vehicle Detection using Radar Range-Azimuth Heatmap and Monocular Image,” Asian Conference on Computer Vision (ACCV), Kyoto, Japan (Virtual), 2020. [Paper, Presentation]
Youngseok Kim and Dongsuk Kum, “Deep Learning based Vehicle Position and Orientation Estimation via Inverse Perspective Mapping Image,” IEEE Intelligent Vehicles Symposium (IV), Paris, France, 2019. [Paper, Video Demo]
* Oral presentation, 5.8% acceptance rate for oral-presentation papers
Patents
Dongsuk Kum, Youngseok Kim, “Electronic Device for Obtaining Three-Dimension Object Based on Camera and Radar Sensor Fusion, and Operating Method Thereof,” US, DE, PCT, Application Number: 17199043, 10 2021 106 518.6, PCT/KR2021/002916.
Dongsuk Kum, Youngseok Kim, “Electronic Device for Obtaining Three-Dimension Object Based on Camera and Radar Sensor Fusion, and Operating Method Thereof,” KR, Registration Number: 10-2168753-0000.
Dongsuk Kum, Youngseok Kim, “Simultaneous Traffic Participants Detection and Localization vis Bird’s Eye View Image,” KR, Registration Number: 10-2003387-0000.
Dongsuk Kum, Youngseok Kim, Seoung Jun Lee, “Distance Measuring Device Using Mono Infrared Camera and Method Thereof,” KR, Registration Number: 10-1918887-0000.
Domestic Papers
Sanmin Kim, Youngseok Kim, Hyeongseok Jeon, Dongsuk Kum and Kibeom Lee “Autonomous Driving Technology Trend and Future Outlook: Powered by Artificial Intelligence,” Transactions of Korean Society of Automotive Engineers (Trans. KSAE), 2022. [Paper]
Youngseok Kim and Dongsuk Kum, “Vehicle Distance Estimation using Convolutional Neural Network on Inverse Perspective Mapping Image,” Korean Society of Automotive Engineers (KSAE) 2019 Annual Autumn Conference, Gyeongju, Korea, 2019.
Youngseok Kim and Dongsuk Kum, “Fault Tolerant Vehicle Detection Using Camera-LiDAR Sensor Fusion: Multi-channel Faster R-CNN,” Korean Society of Automotive Engineers (KSAE) 2018 Annual Spring Conference, Busan, Korea, 2018.