Kyungjun Lee

Kyungjun's headshot photo taken in the Joshua Tree National Park, California, USA.

Ph.D. Student
Computer Science
University of Maryland

kjlee -at- cs.umd.edu

[CV] [Scholar]

2117 Hornbake Bldg.
South Wing
College Park
MD 20742

About me

Hello, I am a Ph.D. student in Computer Science at University of Maryland, College Park, and a member of Human-Computer Interaction Lab and Intelligent Assistant Machines Lab, advised by Hernisa Kacorri.

My research on Teachable Interfaces through Human-Centered Artificial Intelligence focuses on enhancing AI by involving humans in the loop and building AI-powered systems to empower people with and without disabilities, which combines methods from machine learning and human-computer interaction.

I am interested in how to explore and exploit users' interactions with AI when desining a system powered by AI. My current project is to design a Teachable Object Recognizer for blind people using sonigifcation, haptic feedback, and deep learning models.

Publications

  1. Pedestrian Detection with Wearable Cameras for the Blind: A Two-way Perspective
    Kyungjun Lee, Daisuke Sato, Saki Asakawa, Hernisa Kacorri, Chieko Asakawa
    Proceedings of ACM CHI Conference on Human Factors in Computing Systems (CHI), 2020
    [ACM] [local] [arXiv]

  2. Crowdsourcing the Perception of Machine Teaching
    Jonggi Hong, Kyungjun Lee, June Xu, Hernisa Kacorri
    Proceedings of ACM CHI Conference on Human Factors in Computing Systems (CHI), 2020
    [ACM] [arXiv]

  3. Hand-Priming in Object Localization for Assistive Egocentric Vision
    Kyungjun Lee, Abhinav Shrivastava, Hernisa Kacorri
    Proceedings of IEEE Winter Conference on Applications of Computer Vision (WACV), 2020
    Best Paper Award, Applications
    [local (accessible ver.)] [CvF] [arXiv]

  4. Revisiting Blind Photography in the Context of Teachable Object Recognizers
    Kyungjun Lee, Jonggi Hong, Simone Pimento, Ebrima Jarjue, Hernisa Kacorri
    Proceedings of ACM SIGACCESS Conference on Computers and Accessibility (ASSETS), 2019
    [ACM] [local]

  5. Hands Holding Clues for Object Recognition in Teachable Machines
    Kyungjun Lee, Hernisa Kacorri
    Proceedings of ACM CHI Conference on Human Factors in Computing Systems (CHI), 2019
    [ACM] [local]

  6. Exploring Machine Teaching for Object Recognition with the Crowd
    Jonggi Hong, Kyungjun Lee, June Xu, Hernisa Kacorri
    Extended Abstracts of ACM CHI Conference on Human Factors in Computing Systems (CHI), 2019
    [ACM]

  7. Gesture and Action Discovery for Evaluating Virtual Environments with Semi-Supervised Segmentation of Telemetry Records
    Andrea Batch, Kyungjun Lee, Hanuma Teja Maddali, Niklas Elmqvist
    Proceedings of IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR), 2018
    [IEEE]

  8. Texture Synthesis with Recurrent Variational Auto-Encoder
    Rohan Chandra, Sachin Grover, Kyungjun Lee, Moustafa Meshry, Ahmed Taha
    arXiv preprint, 2017 (*authors are alphabetically ordered)
    [arXiv]

  9. Performance implications of cache flushes for non-volatile memory file systems
    Kyungjun Lee, Sungtae Ryu, Hwansoo Han
    Proceedings of ACM Symposium on Applied Computing (SAC), 2015
    [ACM]

  10. In-memory write-ahead logging for mobile smart devices with NVRAM
    Sungtae Ryu, Kyungjun Lee, Hwansoo Han
    IEEE Transactions on Consumer Electronics (TCE), 2015
    [IEEE]