Projects

• AI/SW Project for Commissioned Education (Ministry of National Defense (MND), Jul.'22 – Dec.'26)

• Synthetic Military Target Data Generation for Domain Adaptive Object Detection (LIGNex1, Oct.'22 – Sep.'23) 

Publications

• Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks.
  Hunmin Yang, Jongoh Jeong and Kuk-Jin Yoon.
  European Conference on Computer Vision (ECCV), Sep. 2024. [Page]

• FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks.
  Hunmin Yang*, Jongoh Jeong* and Kuk-Jin Yoon. *Equal contribution.
  The 38th Annual AAAI Conference on Artificial Intelligence (AAAI), Feb. 2024. [Page]

• FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks
  Hunmin Yang*, Jongoh Jeong*, Kuk-Jin Yoon. *Equal contribution.
  ICCV 2023 Workshop on Adversarial Robustness In the Real World (AROW 2023) [Extended Abstract]
  PD

Projects

• Development of Artificial Intelligence Technology that Continuously Improves Itselfas the Situation Changes in the Real World (Korea MSIT No.2020-0-00440, Sep.’20 –Aug.’22)

• Development of Real-time Smart Solution for Solder Mount Technology (SMT) (Koh-Young Tech., Sep.’20 – Aug.’22)

Publications

• Cognitive TransFuser: Semantics-guided Transformer-based Sensor Fusion for Improved Waypoint Prediction.
  Hwan-Soo Choi*, Jongoh Jeong*, Young Hoo Cho, Kuk-Jin Yoon, and Jong-Hwan Kim. *Equal contribution.
  Robot Intelligence Technology and Applications (RiTA), Dec. 2023. [Page]

• Adaptive Bayesian Optimization for Fast Exploration Under Safety Constraints
  Guk Han, Jongoh Jeong and Jong-Hwan Kim.
  IEEE Access. Apr. 2023. [Page]

• End-to-end Real-time Obstacle Detection Network for Safe Self-driving via Multi-task Learning
  Taek-jin Song*, Jongoh Jeong* and Jong-Hwan Kim. *Equal contribution.
  IEEE Transactions on Intelligent Transportation Systems (IEEE T-ITS), Sept. 2022. [Page]

• Doubly Contrastive End-to-End Semantic Segmentation for Autonomous Driving under Adverse Weather
  Jongoh Jeong and Jong-Hwan Kim.
  British Machine Vision Conference (BMVC), Nov. 2022. [Page]

Projects

• Developed a system to extracte digit texts using OCR and detect target motions using structural similarity metric from task-specific videos in order to analyze and compare the performance of exoskeletons and exosuits to that of bare body joints in Python (OpenCV) and MATLAB

• Project with Azure Kinect™: Development of a low-cost motion capture system, and synchronizing and controlling/tracking drones by human pose [Project]

Projects

• Investigated a novel approach to a SVM classifier with temporally expanding privileged information (LUPI) from the electronic health records ("MFMU", pre-term birth clinical dataset from NICHD)

• Explored necessary conditions for performance improvements of time-sequenced SVM classifier with LUPI in algorithmic and data pre-processing techniques for data imputation and imbalances

Publication

• Using Privileged Information to Improve Prediction in Health Data: A Case Study.
  Jongoh Jeong, Do Hyung Kwon, Min Joon So, Anita Raja, Shivani Ghatge, Nicolae Lari, Ansaf Salleb-Aouissi.
  NeurIPS 2019 Workshop on Information Theory and Machine Learning.  [Page]

Projects

• Built alpha prototype of Interactive Smartwatch and Docking System, showcased at EurekaFest 2019 (MIT)

• Extensive research on presently available technologies, UI/UX designs based on direct surveys by current patients, and mechanisms to detect wandering and anomalous behavior of Alzheimer's patients

• Utilized GPS/GPRS over GSM network through web app, Arduino sensors for locating patients and warning caretakers, and developed professional writing as Admin Lead

[Presentation][BOE Presentation][Mid-Grant Technical Review][Documents]