Research Interests

• Computer Vision and Deep Learning.

• Diffusion based Image generation, 3D human hand pose estimation, and hand-object interaction.

Education

• M.S. at Artificial Intelligence Graduate School, Ulsan National Institute of Science and Technology (UNIST), Ulsan, South Korea.

  • Advisor: Seungryul Baek

  • Mar. 2022~

• B.S. at Dept. of Computer Science Engineering, Ulsan National Institute of Science and Technology (UNIST), Ulsan, South Korea.

  • Mar. 2018~ Feb. 2022.

Publications

International

• Junuk Cha, Jihyeon Kim, Jae Shin Yoon*, Seungryul Baek*, "Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction", in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Seattle, USA, 2024. (accepted)

• Junsu Kim, Hoseong Cho, Jihyeon Kim, Yihalem Yimolal Tiruneh, Seungryul Baek, "SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection", in Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Seattle, USA, 2024. (accepted)

• Junsu Kim, Sumin Hong, Chanwoo Kim, Jihyeon Kim, Yihalem Yimolal Tiruneh, Jeongwan On, Jihyun Song, Sunhwa Choi, Seungryul Baek, "Class-wise Buffer Management for Incremental Object Detection: An Effective Buffer Training Strategy", in Proc. of IEEE conf. on International Conference on Acoustic, Speech and Signal Processing (ICASSP), Seoul, Korea, 2024. [paper]

• Hoseong Cho, Chanwoo Kim, Jihyeon Kim, Seongyeong Lee, Elkhan Ismayilzada, Seungryul Baek, "Transformer-based Unified Recognition of Two Hands Manipulating Objects", in  Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, 2023. [paper]

• Seongyeong Lee, Hansoo Park, Dong Uk Kim, Jihyeon Kim, Muhammadjon Boboev, Seungryul Baek, "Image-free Domain Generalization via CLIP for 3D Hand Pose Estimation", in Proc. of IEEE Winter Conf. on Applications of Computer Vision (WACV), Hawaii, USA, 2023. [paper]

Domestic

• Junsu Kim, Sumin Hong, Jihyeon Kim, Jeongwan On, Chanwoo Kim, Yihalem Yimolal Tiruneh, Jihyun Song, Sunhwa Choi, Seungryul Baek, "Reducing data imbalancing for Object Detection", in Proc. 2023 Summer Conference of Institute of Electronics and Information Engineers (IEIE), 2023.

• Elkhan Ismayilzada, Muhammadjon Boboev, Jihyeon Kim, Junuk Cha, Mubarrat Chowdhury, Juheon hwang, Dukhyun Kim, Jinwoo Park, Seungryul Baek, "Human mask generation using pose estimator and salient object detector", in Proc. 2023 Summer Conference of Institute of Electronics and Information Engineers (IEIE), 2023.

• Hansoo Park, Jihyeon Kim, Junsu Kim and Seungryul Baek, "Temporal MANO based Video Hand Pose and Shape Estimation", JKAIA, 2022.

• Jihyeon Kim, Junuk Cha, Yeongjun Choo, Minjae Lee, Jitae Yoo, Yeonghun Oh, Hoseong Cho, Eunseo Kim, Chungseok Choi, Honggyu Lim, Donguk Min, Eugene Shin, Seokun Kang and Seungryul Baek, "Free-form Masked Facial Image Inpainting via Exploiting 2D and 3D Information", CKAIA, 2022.

• Hoseong Cho, Jihyeon Kim, Yunhoe Ku, Eunseo Kim, GeonU Kim and Seungryul Baek, "A Survey of Hand Pose Estimation", CKAIA, 2022.

• Jihyeon Kim, Changhwa Lee, Seongyeong Lee, Junuk Cha, Hansoo Park, Donguk Kim and Seungryul Baek, "Finger Bendedness Classification from 3D Pose Regression", JKAIA, 2021.

Patents 

• Dangerous Region Approaching Worker Detection and Machine Breaking Device Based on Thermal Images, 2023.
  -  Applicant : UNIST and Hyundai

Activities

• Internship of CUop Program at UNIST Industry Company, UIsan, South Korea, Dec. 2020 ~ Feb. 2021.

• Internship of Machine Learning and Vision Lab at UNIST AIGS, Ulsan South Korea, Jun. 2020 ~ Aug. 2020.

• A Basic CS skill Camp (The Missing Semester of Your CS Education by MIT) at UNIST Computer Science Engineering, Ulsan, South Korea, Dec. 2021 ~ Feb. 2022. 

Projects

• Development of Vision Recognition Module for ARTG Control, Ministry of Oceans and Fisheries, 2023 ~
  -  Development of Driving Autosteering Algorithm and Module through Vision part

• Development of an optimized human detection system algorithm for production factory environments, Hyundai, 2022.06~
  -  Implementation of algorithms for detecting segmentation masks and bounding boxes of people from thermal camera images
  -  Performance improvement for corner cases such as occluded people

• Research on high-speed hand pose estimation based on single RGB image, ETRI (Electronics and Telecommunications Research Institute), 2022.1~2022.12
  -  Lightweight hand pose model optimization (using tflite conversion)
  -  Development of additional training algorithm for heatmap to improve overall 3D hand pose performance
  -  Generation of hand joint 3D data for hand poses suitable for AR glasses

• Development of control intent recognition technology for non-contact long-distance virtual touch panels that block the source of contact infections, Seoul Business Agency, 2021.03~2021.11 (Joint project with V-Touch Co., Ltd.)
  -  Development of hand pose detection and posture classification algorithms using depth sensors
  -  Generation and augmentation of hand pose estimation training data through graphic programs
  -  Application of a non-contact user experience interface through various motion classifications

Teaching Assistant & Mentoring

• Mentoring 

   -  2nd Ulju AI 4.0 Studio at UNIST, Ulsan, South Korea, Mar. 2022 ~ Nov. 2022.

   -  2022 Ulju Science Mentoring at UNIST, Ulsan, South Korea, Feb. 2022. 

        -  Tutoring Program at UNIST, Ulsan, South Korea, Aug. 2021 ~ Dec. 2021 

   -  17th Ulju Science Mentoring at UNIST, Ulsan, South Korea, Feb. 2021. 

        -  Club to Club (C-to-C) at UNIST, Ulsan, South Korea, May. 2021 ~ Oct. 2021.

• TA 

   -  Naval AI Professional Training at UNIST AI Innovation Park, Ulsan, South Korea, Sep. 2023. (Anomaly detection)

        -  5th AI Novatus Academia PBL (Computer Vision part) at UNIST AI Innovation Park, Ulsan, South Korea,  Mar. 2023 ~ June. 2023.

        -  AI challenger Program(AICP) at UNIST, Ulsan, South Korea,  Apr. 2023 ~ 

        -  Naval AI Professional Training at UNIST AI Innovation Park, Ulsan, South Korea, May. 2022.

• Lecture TA 

        - 2022 Spring AI51801 Deep Generative Models & Advanced Computer Vision.

        - 2021 Fall ITP11701 Introduction to AI Programming 2.

        - 2020 Spring MGT102 Entrepreneurship & Big Data.

Skills & Languages

• Python, C/C++, Pytorch, Tensorflow, Keras, OpenCV so on.

• English : TOEIC Speaking Advanced low (160), TOEIC (890, 2023.02 expired)