| Human behavior prediction for smart homes using deep learning S Choi, E Kim, S Oh RO-MAN 2013, 173, 2013 | 86 | 2013 |
| NestedNet: Learning Nested Sparse Structures in Deep Neural Networks E Kim, C Ahn, S Oh Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2018 | 65 | 2018 |
| Elastic-net regularization of singular values for robust subspace learning E Kim, M Lee, S Oh Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2015 | 54 | 2015 |
| Efficient -norm-based low-rank matrix approximations for large-scale problems using alternating rectified gradient method E Kim, M Lee, CH Choi, N Kwak, S Oh IEEE Transactions on Neural Networks and Learning Systems 26 (2), 237-251, 2015 | 49 | 2015 |
| Deep Elastic Networks with Model Selection for Multi-Task Learning C Ahn, E Kim, S Oh Proceedings of the IEEE Conference on Computer Vision (ICCV), 2019 | 45 | 2019 |
| Real-time navigation in crowded dynamic environments using Gaussian process motion control S Choi, E Kim, S Oh 2014 IEEE International Conference on Robotics and Automation (ICRA), 3221-3226, 2014 | 42 | 2014 |
| Real-time nonparametric reactive navigation of mobile robots in dynamic environments S Choi, E Kim, K Lee, S Oh Robotics and Autonomous Systems 91, 11-24, 2017 | 25 | 2017 |
| Leveraged non-stationary Gaussian process regression for autonomous robot navigation S Choi, E Kim, K Lee, S Oh 2015 IEEE International Conference on Robotics and Automation (ICRA), 473-478, 2015 | 13 | 2015 |
| Deep Virtual Networks for Memory Efficient Inference of Multiple Tasks E Kim, C Ahn, PHS Torr, S Oh Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2019 | 12 | 2019 |
| Robust elastic-net subspace representation E Kim, M Lee, S Oh IEEE Transactions on Image Processing 25 (9), 4245-4259, 2016 | 11 | 2016 |
| Robust orthogonal matrix factorization for efficient subspace learning E Kim, S Oh Neurocomputing 167, 218-229, 2015 | 6 | 2015 |
| A robust autoregressive gaussian process motion model using l1-norm based low-rank kernel matrix approximation E Kim, S Choi, S Oh 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2014 | 6 | 2014 |
| Helpful or Harmful: Inter-task Association in Continual Learning H Jin, E Kim European Conference on Computer Vision, 519-535, 2022 | 4 | 2022 |
| Structured low-rank matrix approximation in Gaussian process regression for autonomous robot navigation E Kim, S Choi, S Oh 2015 IEEE International Conference on Robotics and Automation (ICRA), 69-74, 2015 | 4 | 2015 |
| Stacked encoder–decoder transformer with boundary smoothing for action segmentation G Kim, E Kim Electronics Letters 58 (25), 972-974, 2022 | 3 | 2022 |
| Improving Augmentation Efficiency for Few-Shot Learning W Cho, E Kim IEEE Access 10, 17697-17706, 2022 | 3 | 2022 |
| Structured kernel subspace learning for autonomous robot navigation E Kim, S Choi, S Oh Sensors 18 (2), 582, 2018 | 3 | 2018 |
| GhostNeXt: Rethinking Module Configurations for Efficient Model Design K Hong, G Kim, E Kim Applied Sciences 13 (5), 3301, 2023 | 1 | 2023 |
| Incremental Learning With Adaptive Model Search and a Nominal Loss Model C Ahn, E Kim, S Oh IEEE Access 10, 16052-16062, 2022 | 1 | 2022 |
| Auto-VirtualNet: Cost-adaptive dynamic architecture search for multi-task learning E Kim, C Ahn, S Oh Neurocomputing 442, 116-124, 2021 | 1 | 2021 |
Songhwai OhDepartment of Electrical and Computer Engineering, Seoul National University, KoreaVerified email at snu.ac.kr
