Follow
Kensho Hara
Title
Cited by
Cited by
Year
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
20962018
Learning spatio-temporal features with 3D residual networks for action recognition
K Hara, H Kataoka, Y Satoh
Proceedings of the ICCV Workshop on Action, Gesture, and Emotion Recognition …, 2017
6702017
Would mega-scale datasets further enhance spatiotemporal 3D CNNs?
H Kataoka, T Wakamiya, K Hara, Y Satoh
arXiv preprint arXiv:2004.04968, 2020
1072020
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
312018
Rethinking training data for mitigating representation biases in action recognition
K Hara, Y Ishikawa, H Kataoka
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2021
92021
Learning spatiotemporal 3d convolution with video order self-supervision
T Suzuki, T Itazuri, K Hara, H Kataoka
Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 0-0, 2018
92018
Personal multi-view viewpoint recommendation based on trajectory distribution of the viewing target
X Wang, K Hara, Y Enokibori, T Hirayama, K Mase
Proceedings of the 24th ACM international conference on Multimedia, 471-475, 2016
92016
Predicting vehicles appearing from blind spots based on pedestrian behaviors
K Hara, H Kataoka, M Inaba, K Narioka, R Hotta, Y Satoh
2020 IEEE 23rd International Conference on Intelligent Transportation …, 2020
72020
User Group Based Viewpoint Recommendation Using User Attributes for Multiview Videos
X Wang, Y Enokibori, T Hirayama, K Hara, K Mase
Proceedings of the Workshop on Multimodal Understanding of Social, Affective …, 2017
72017
Predicting appearance of vehicles from blind spots based on pedestrian behaviors at crossroads
K Hara, H Kataoka, M Inaba, K Narioka, R Hotta, Y Satoh
IEEE transactions on intelligent transportation systems 23 (8), 11917-11929, 2021
62021
Personal viewpoint navigation based on object trajectory distribution for multi-view videos
X Wang, K Hara, Y Enokibori, T Hirayama, K Mase
IEICE TRANSACTIONS on Information and Systems 101 (1), 193-204, 2018
62018
映像特徴を用いたサッカー選手のプレー認識
壁谷勇磨, 原健翔, 間瀬健二
電子情報通信学会技術研究報告= IEICE technical report: 信学技報 114 (90), 19-23, 2014
62014
Transformer-based ripeness segmentation for tomatoes
R Shinoda, H Kataoka, K Hara, R Noguchi
Smart Agricultural Technology 4, 100196, 2023
42023
Recent advances in video action recognition with 3d convolutions
K Hara
IEICE Transactions on Fundamentals of Electronics, Communications and …, 2021
42021
VirtualHome Action Genome: A Simulated Spatio-Temporal Scene Graph Dataset with Consistent Relationship Labels
Y Qiu, Y Nagasaki, K Hara, H Kataoka, R Suzuki, K Iwata, Y Satoh
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2023
32023
Spatiotemporal initialization for 3d cnns with generated motion patterns
H Kataoka, K Hara, R Hayashi, E Yamagata, N Inoue
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2022
32022
Recognizing people in blind spots based on surrounding behavior
K Hara, H Kataoka, M Inaba, K Narioka, Y Satoh
Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 0-0, 2018
32018
RoseTracker: A system for automated rose growth monitoring
R Shinoda, K Motoki, K Hara, H Kataoka, R Nakano, T Nakazaki, ...
Smart Agricultural Technology 5, 100271, 2023
22023
Simultaneous action recognition and localization based on multi-view Hough voting
K Hara, T Hirayama, K Mase
2013 2nd IAPR Asian Conference on Pattern Recognition, 616-620, 2013
22013
Trend-sensitive hough forests for action detection
K Hara, T Hirayama, K Mase
2014 IEEE International Conference on Image Processing (ICIP), 1475-1479, 2014
12014
The system can't perform the operation now. Try again later.
Articles 1–20