Research Interests

• Computer Vision and Deep Learning.

• 3D hand pose estimation.

Education

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

  • Advisor: Seungryul Baek

  • Sep. 2024~

• B.S. at Dept. of Statistics, Chonnam National University (CNU), Gwangju, South Korea.

  • Mar. 2018 ~ Feb. 2024

Publications

International 

• Zicong Fan, Takehiko Ohkawa, Linlin Yang, Nie Lin, Zhishan Zhou, Shihao Zhou, Jiajun Liang, Zhong Gao, Xuanyang Zhang, Xue Zhang, Fei Li, Liu Zheng, Feng Lu, Karim Abou Zeid, Bastian Leibe, Jeongwan On, Seungryul Baek, Aditya Prakash, Saurabh Gupta, Kun He, Yoichi Sato, Otmar Hilliges, Hyung Jin Chang and Angela Yao. "Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects ", in Proc. of European Conference on Computer Vision (ECCV), 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 International Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Seoul, South Korea, 2024.

Domestic 

• Junuk Cha, Jihyeon Kim, Sangwon Choi, Jeongwan On and Seungryul Beak. “단안 비디오를 활용한 객체의 3D 바운딩 박스 추정 및 속력 계산, 움직임 예측”. In Autumn Annual Conference of IEIE, 2023.

• 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 Summer Annual Conference of IEIE, 2023.

Honors and Awards

• 3rd place at 2023 ICCV hand challenge (Consistent Motion Reconstruction), ICCV, 2023.

• Best Undergraduate Paper Award, Chonnam National University, 2023.

• 2nd prize at AI idea contest, gwangju information & culture industry promotion agency (GICON), 2023.

• 1st prize at Bigdata competition, Chonnam National University, 2022.

• 3rd prize at Bigdata competition, Chonnam National University, 2021.

Experiences

• Euclidsoft, Development Intern, Daejeon, South Korea.

  • Sep. 2022 ~ Dec. 2022

  • Model Optimization : TensorRT, CUDA Stream.

  • Object Detection.

Projects

• • "Development of Vision Recognition Module for ARTG Control", Ministry of Oceans and Fisheries.

    • Mar. 2023 ~ 

    • Development of Driving Autosteering Algorithm and Module through Vision part.

  • "Expanding Data Coverage through Incremental Learning and Development Integrated Domain Recognition Systems", LG Electronics.

    • Aug. 2022 ~ Aug. 2023

    • Conversion from pytorch model to tflite for edge device.

    • Development of Object Detection algorithm.