| Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet? K Hara, H Kataoka, Y Satoh Proceedings of the IEEE conference on Computer Vision and Pattern …, 2018 | 2203 | 2018 |
| Learning spatio-temporal features with 3d residual networks for action recognition K Hara, H Kataoka, Y Satoh Proceedings of the IEEE international conference on computer vision …, 2017 | 702 | 2017 |
| Using selective correlation coefficient for robust image registration S Kaneko, Y Satoh, S Igarashi Pattern Recognition 36 (5), 1165-1173, 2003 | 182 | 2003 |
| Anticipating traffic accidents with adaptive loss and large-scale incident db T Suzuki, H Kataoka, Y Aoki, Y Satoh Proceedings of the IEEE conference on computer vision and pattern …, 2018 | 128 | 2018 |
| Would mega-scale datasets further enhance spatiotemporal 3D CNNs? H Kataoka, T Wakamiya, K Hara, Y Satoh arXiv preprint arXiv:2004.04968, 2020 | 110 | 2020 |
| Pre-training without natural images H Kataoka, K Okayasu, A Matsumoto, E Yamagata, R Yamada, N Inoue, ... Proceedings of the Asian Conference on Computer Vision, 2020 | 107 | 2020 |
| Object detection based on a robust and accurate statistical multi-point-pair model X Zhao, Y Satoh, H Takauji, S Kaneko, K Iwata, R Ozaki Pattern Recognition 44 (6), 1296-1311, 2011 | 60 | 2011 |
| Robust object detection using a Radial Reach Filter (RRF) Y Satoh, S Kaneko, Y Niwa, K Yamamoto Systems and Computers in Japan 35 (10), 63-73, 2004 | 59 | 2004 |
| An omnidirectional stereo vision-based smart wheelchair Y Satoh, K Sakaue EURASIP Journal on Image and Video Processing 2007 (1), 087646, 2007 | 52 | 2007 |
| Radial Reach Filter (RRF) によるロバストな物体検出 佐藤雄隆_金子俊一_丹羽義典_山本和彦 電子情報通信学会論文誌D-II 86 (5), 616-624, 2003 | 52 | 2003 |
| Human Action Recognition without Human Y He, S Shirakabe, Y Satoh, H Kataoka Computer Vision–ECCV 2016 Workshops, 11-17, 2016 | 48 | 2016 |
| Drive video analysis for the detection of traffic near-miss incidents H Kataoka, T Suzuki, S Oikawa, Y Matsui, Y Satoh 2018 IEEE International Conference on Robotics and Automation (ICRA), 3421-3428, 2018 | 41 | 2018 |
| Describing and localizing multiple changes with transformers Y Qiu, S Yamamoto, K Nakashima, R Suzuki, K Iwata, H Kataoka, Y Satoh Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | 37 | 2021 |
| Feature Evaluation of Deep Convolutional Neural Networks for Object Recognition and Detection H Kataoka, K Iwata, Y Satoh arXiv preprint arXiv:1509.07627, 2015 | 36 | 2015 |
| Temporal and fine-grained pedestrian action recognition on driving recorder database H Kataoka, Y Satoh, Y Aoki, S Oikawa, Y Matsui Sensors 18 (2), 627, 2018 | 35 | 2018 |
| Recognition of Transitional Action for Short-Term Action Prediction using Discriminative Temporal CNN Feature. H Kataoka, Y Miyashita, M Hayashi, K Iwata, Y Satoh BMVC, 2016 | 35 | 2016 |
| Robust event detection by radial reach filter (RRF) Y Satoh, H Tanahashi, C Wang, S Kaneko, Y Niwa, K Yamamoto 2002 International Conference on Pattern Recognition 2, 623-626, 2002 | 35 | 2002 |
| Towards good practice for action recognition with spatiotemporal 3d convolutions K Hara, H Kataoka, Y Satoh 2018 24th International Conference on Pattern Recognition (ICPR), 2516-2521, 2018 | 34 | 2018 |
| Can vision transformers learn without natural images? K Nakashima, H Kataoka, A Matsumoto, K Iwata, N Inoue, Y Satoh Proceedings of the AAAI Conference on Artificial Intelligence 36 (2), 1990-1998, 2022 | 25 | 2022 |
| Semantic Change Detection with Hypermaps H Kataoka, S Shirakabe, Y Miyashita, A Nakamura, K Iwata, Y Satoh arXiv preprint arXiv:1604.07513, 2016 | 25* | 2016 |
Hirokatsu KataokaChief Senior Researcher, AISTVerified email at aist.go.jp
