• Mar. 2012 - Aug. 2019 Ph.D. in Computer Science and Engineering, Pohang University of Science and Technology (POSTECH)

Adviser: Daijin Kim

Dissertation: Building and Understanding Latent Structure for Object Detection

Intelligent Media Lab.

• Mar. 2008 - Feb. 2012 B.S. in Computer Engineering, Korea Aerospace University (Summa Cum Laude)

• Jun. 2021 - Present Senior Applied Scientist in GaussLabs Inc.

• Dec. 2019 - Jun. 2021 Research Scientist in Kakao Enterprise

• Aug. 2019 - Dec. 2019 Research Scientist in Kakao Corp.

• Reviewer - ICCV 2019, CVPR 2019, AAAI 2020, CVPR 2020, ECCV 2020, WACV 2021, Neurips 2020, ACCV 2020, AAAI 2021, CVPR 2021

Papers

• Yonghyun Kim* and Wonpyo Park*, "Multi-level Distance Regularization for Deep Metric Learning," in AAAI Conference on Artificial Intelligence (AAAI), 2021. (*equal contribution) [page][code]

• Yonghyun Kim*, Wonpyo Park* and Jongju Shin, "BroadFace: Looking at Tens of Thousands of People at Once for Face Recognition," in Proceedings of the European Conference on Computer Vision (ECCV), 2020. (*equal contribution) [page][code]

• Yonghyun Kim, Wonpyo Park, Myung-Cheol Roh and Jongju Shin, "GroupFace: Learning Latent Groups and Constructing Group-based Representations for Face Recognition," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020. [page]

• Taewook Kim, Yonghyun Kim, Inhan Kim and Daijin Kim, "BASN: Enriching Feature Representation Using Bipartite Auxiliary Supervisions for Face Anti-Spoofing," in Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVW), 2019. [pdf]

• Bong-Nam Kang, Yonghyun Kim, Bongjin Jun and Daijin Kim, "Attentional Feature-Pair Relation Networks for Accurate Face Recognition," in Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2019.

• Bong-Nam Kang, Yonghyun Kim, Bongjin Jun and Daijin Kim, "Hierarchical Feature-Pair Relation Networks for Face Recognition," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2019.

• Bong-Nam Kang, Yonghyun Kim, and Daijin Kim, "Pairwise Relational Networks using Local Appearance Features for Face Recognition," in the Neural Information Processing Systems Workshops (NIPSW), 2018.

• Yonghyun Kim, Taewook Kim, Bong-Nam Kang, Jieun Kim and Daijin Kim, "BAN: Focusing on Boundary Context for Object Detection," in Proceedings of the Asian Conference on Computer Vision (ACCV), 2018.

• Yonghyun Kim, Bong-Nam Kang and Daijin Kim, "SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection," in Proceedings of the European Conference on Computer Vision (ECCV), 2018.

• Bong-Nam Kang, Yonghyun Kim and Daijin Kim, "Pairwise Relational Networks for Face Recognition," in Proceedings of the European Conference on Computer Vision (ECCV), 2018.

• Yonghyun Kim, Bong-Nam Kang and Daijin Kim, "Detector with focus: Normalizing gradient in image pyramid," in Proceedings of the IEEE International Conference on Image Processing (ICIP), 2017.

• Bong-Nam Kang, Yonghyun Kim, and Daijin Kim, "Deep Convolutional Neural Network Using Triplets of Faces, Deep Ensemble, and Score-Level Fusion for Face Recognition" in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017.

• YongJoong Kim, Yonghyun Kim, and Daijin Kim, "Integrating hidden Markov models based on Mixture-of-Templates and k-NN 2 ensemble for activity recognition," in Proceedings of the International Conference on Pattern Recognition (ICPR), 2016.

• Bong-Nam Kang, Yonghyun Kim, and Daijin Kim, "Deep convolution neural network with stacks of multi-scale convolutional layer block using triplet of faces for face recognition in the wild," in Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2016.

• Jangho Kim, Yongjoong Kim, Yonghyun Kim, and Daijin Kim, "Detecting Korean characters in natural scenes by alphabet detection and agglomerative character construction," in Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2016.

• Wontaek Chung, Yonghyun Kim, Yongjoong Kim, and Daijin Kim, "A two-stage foreground propagation for moving object detection in a non-stationary," in Proceedings of the IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), 2016.

• Yongjoong Kim, Yonghyun Kim, Bong-Nam Kang, and Daijin Kim, "Combined Document/Business Card Detector for Proactive Document-Based Services on the Smartphone," in Proceedings of the International Conference on Neural Information Processing (ICONIP), 2015.

• Hak Kyoung Kim, Yonghyun Kim, and Daijin Kim, "Adaptive Deformation Handling for Pedestrian Detection," in Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), 2008.

• Yonghyun Kim, Jieun Kim, and Daijin Kim, "Temporal Pyramid for Fast Pedestrian Detection," in Korea Computer Congress, 2015.

• Yonghyun Kim and Daijin Kim, "Pedestrian Detection using Channel MCT-AdaBoost," in Korea Computer Congress, 2015.

• Yongjoong Kim, Yonghyun Kim, and Daijin Kim, "Business Card Region Detection using Image Segmentation based Line Fitting," in Workshop on Image Processing and Image Understanding, 2015.

• Jiman Kim, Yonghyun Kim, and Daijin Kim, "Sequential Pose Classification for Automatic Diagnosis of Cow,"in Workshop on Image Processing and Image Understanding, 2014.

• Yonghyun Kim and Daijin Kim, "Multi-Pose Pedestrian Detection using HybridFeatures and AdaBoost," in Korea Computer Congress, 2014.

• Yonghyun Kim and Daijin Kim, "Multi-Pose Pedestrian Detection using MCT-AdaBoost," in Korea Computer Congress, 2013.

• Bong-Nam Kang, Yonghyun Kim, and Daijin Kim, "Eye and Iris Center Point Detection using Radial Symmetric Feature," in Workshop on Image Processing and Image Understanding, 2013.

Patents

• "CNN을 이용하여 크기 독립적으로 물체를 검출하는 방법 및 장치,'' 등록번호 (10-2213-6000000), 2021.02.

• "이미지 학습을 수행하는 장치, 프로그램 및 그것의 제어 방법,'' 출원번호 (10-2021-0012104), 2021.01.

• "대량의 얼굴 특징을 이용하여 얼굴을 인식하는 장치 및 그것의 학습 제어 방법,'' 출원번호 (10-2020-0101421), 2020.08.

• "그룹 기반 얼굴 인식 방법 및 장치,'' 출원번호 (10-2020-0059683), 2020.05.

• "CNN을 이용하여 크기 독립적으로 물체를 검출하는 방법 및 장치,'' 출원번호 (10-2018-0101128), 2018.08.

• "Development of Open Informal Dataset and Dynamic Object Recognition Technology Affecting Autonomous Driving," Institute for Information and Communications Technology Promotion, 2018 ~ 2019.

• "Development of Predictive Visual Intelligence Technology (DeepView)," Institute for Information and Communications Technology Promotion, 2016 ~ 2019.

• "Development of Core Technologies for Intelligence Information Processing SW (ITRC)," Institute for Information and Communications Technology Promotion, 2016 ~ 2017.

• "Development of Object Detection and Recognition for Intelligent Vehicles (StarLab)," Institute for Information and Communications Technology Promotion, 2017 ~ 2019.

• "Development of Upper Body of Human Detection," Samsung Techwin, 2015.

• "Development of Real-time Pedestrian Recognition based on Embedded System," Hyundai NGV, 2013 ~ 2015.

• "Development of Human Detection in Robot Environment," KT, 2013.

• "Development of Real-time Automatic Inspection System for Individual Livestock and Reliable Diagnostic Products," Pohang Institute of Intelligent Robotics, 2012 ~ 2013.

• "Development of Pedestrian Detection," POSCO, 2012 ~ 2013, 2015.

• "Development of Surveillance System for Wearing Working Clothes," POSCO, 2017.

• "Development of Upper Body of Human Detection," Samsung Techwin, 2015.