Wonijk Kim
Introduction
Degree
Doctor of Engineering
Affiliation
The National Institute of Advanced Industrial Science and Technology
Artificial Intelligence Research Center
Email:
kim-wonjik(at)aist.go.jp
wkim(at)ok.sc.e.titech.ac.jp
Status: Researcher of AIRC, AIST
Research interest: pattern recognition, machine learning, deep learning, computer vision, AI for medical, etc...
Publication:
Journal:
Wonjik Kim, Masayuki Tanaka, Yoko Sasaki, Masatoshi Okutomi. "Deformable element-wise dynamic convolution," J. Electron. Imaging 32(5), 053029 (2023), doi: 10.1117/1.JEI.32.5.053029. [paper link] [code]
Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi, and Yoko Sasaki. "Pixelwise Dynamic Convolution Neural Network for LiDAR Depth Data Interpolation." IEEE Sensors Journal Volume: 21, Issue: 24 (2021): 27736 - 27747. [paper link] [code]
Wonjik Kim*, Asako Kanezaki*, and Masayuki Tanaka. "Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering." IEEE Transactions on Image Processing 29 (2020): 8055-8068. [paper link] [code] (* equal contribution)
Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi, and Yoko Sasaki. "Learning-Based Human Segmentation and Velocity Estimation Using Automatic Labeled LiDAR Sequence for Training." IEEE Access 8 (2020): 88443 - 88452. [paper link] [code]
Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi, and Yoko Sasaki. "Automatic Labeled LiDAR Data Generation and Distance-Based Ensemble Learning for Human Segmentation." IEEE Access 7 (2019): 55132-55141. [paper link] [code]
Wonjik Kim and Osamu Hasegawa. "Simultaneous Forecasting of Meteorological Data Based on a Self-Organizing Incremental Neural Network." Journal of Advanced Computational Intelligence and Intelligent Informatics 22.6 (2018): 900-906. [paper link]
Wonjik Kim and Osamu Hasegawa. "Time series prediction of tropical storm trajectory using self-organizing incremental neural networks and error evaluation." Journal of Advanced Computational Intelligence and Intelligent Informatics 22.4 (2018): 465-474. [paper link]
Conference:
Wonjik Kim, Masayuki Tanaka, and Masatoshi Okutomi. "Area Under Accuracy-Accuracy Curve for Evaluating Out-of-Distribution Detection.", Proceedings of Pacific-Rim Symposium on Image and Video Technology (PSIVT2023), November 2023 [code]
Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi, and Yoko Sasaki. "Adaptive Future Frame Prediction with Ensemble Network.", Proceedings of ICPR2020 Workshop : International Workshop on Pattern Forecasting (PATCAST), January 2021 [paper link] [code]
Tao Zhong, Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi. "Human Segmentation with Dynamic LiDAR Data.", International Conference on Pattern Recognition (ICPR), 2020 [paper link] [code]
Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi, and Yoko Sasaki. "Automatic Labeled LiDAR Data Generation based on Precise Human Model.", International Conference on Robotics and Automation (ICRA), 2019. [paper link] [code]
Wonjik Kim and Osamu Hasegawa. "Improved Kernel Density Estimation Self-organizing Incremental Neural Network to Perform Big Data Analysis." International Conference on Neural Information Processing. Springer, Cham, 2018. [paper link]
Wonjik Kim and Osamu Hasegawa. "Prediction of Tropical Storms Using Self-organizing Incremental Neural Networks and Error Evaluation." International Conference on Neural Information Processing. Springer, Cham, 2017. [paper link]
Awards:
Remarks:
Chair of the session: emerging modeling techniques in ICONIP 2018.
Chair of the track: Embedded Machine Learning and Data Analytics in 16th IEEE MCSoC 2023.