Youngjun Kwak (곽영준)

Education

• 2020.3 - Present         Ph.D. (School of Electrical Engineering), Korea Advanced Institute of Science and Technology, South Korea

• 2013.3 - 2015.2          M.S. (Dept. of Computer Science), Yonsei Univerisity, South Korea

• 2005.3 - 2013.2          B.S. (Dept. of Computer Engineering), Hongik Univerisity, South Korea 

Research Interests

• Deep Learning, Computer Vision

Publications

• H. Kim*, Youngjun Kwak*, M. Jung, J. Shin, Y. Kim, and Changick Kim. “ProtoFL: Unsupervised Federated Learning via Prototypical Distillation,” in Proc. IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, Oct. 02 - 06, 2023. (* These two authors contributed equally)

• Youngjun Kwak, M. Jung, H. Yoo, J. Shin, Changick Kim, "Liveness Score-Based Regression Neural Networks for Face Anti-Spoofing," Proc. the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Rhodes Island, Greece, Jun. 4-10, 2023.

• T. Guo, H. Zhang, B. Yoo, Y. Liu, Youngjun Kwak, J. Han, "Order Regularization on Ordinal Loss for Head Pose, Age and Gaze Estimation," in Proc. the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), February 2-9, 2021.

• S. Jung, C. Son, S. Lee, J. Son, J. Han, Youngjun Kwak, S. Hwang, C. Cho, "Learning to Quantize Deep Networks by Optimizing Quantization Intervals With Task Loss," in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, Jun. 16-20, 2019.

• B. Yoo*, Youngjun Kwak*, Y. Kim, C. Choi, J. Kim, "Deep Facial Age Estimation Using Conditional Multitask Learning With Weak Label Expansion," IEEE Signal Processing Letters. 25(6): 808-812 (2018).(* These two authors contributed equally)

Awards

• ICCV 2023 Workshops "Workshop on Resource Efficient Deep Learning for Computer Vision" Challenge Track 1 : 1st Place.