H
Hirokatsu Kataoka
Researcher at National Institute of Advanced Industrial Science and Technology
Publications - 119
Citations - 3245
Hirokatsu Kataoka is an academic researcher from National Institute of Advanced Industrial Science and Technology. The author has contributed to research in topics: Convolutional neural network & Computer science. The author has an hindex of 15, co-authored 104 publications receiving 1973 citations. Previous affiliations of Hirokatsu Kataoka include Japan Society for the Promotion of Science & Keio University.
Papers
More filters
Proceedings ArticleDOI
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet
TL;DR: Whether current video datasets have sufficient data for training very deep convolutional neural networks with spatio-temporal three-dimensional (3D) kernels is determined and it is believed that using deep 3D CNNs together with Kinetics will retrace the successful history of 2DCNNs and ImageNet, and stimulate advances in computer vision for videos.
Proceedings ArticleDOI
Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition
TL;DR: 3D-ResNets as mentioned in this paper proposed a 3D convolutional neural network based on ResNets to extract spatio-temporal features from videos for action recognition.
Posted Content
Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition
TL;DR: Wang et al. as discussed by the authors proposed a 3D ResNets based on residual networks (ResNets) to extract spatio-temporal features from videos for action recognition.
Proceedings ArticleDOI
Anticipating Traffic Accidents with Adaptive Loss and Large-Scale Incident DB
TL;DR: A novel approach for traffic accident anticipation through (i) Adaptive Loss for Early Anticipation (AdaLEA) and (ii) a large-scale self-annotated incident database for anticipation is proposed.
Posted Content
Alleviating Over-segmentation Errors by Detecting Action Boundaries
TL;DR: A framework for temporal action segmentation, the ASRF, which divides temporal action segmentsation into frame-wise action classification and action boundary regression, and refines frame-level hypotheses of action classes using predicted action boundaries is proposed.