Zobrazeno 1 - 10 of 94 pro vyhledávání: '"Kaoru Hiramatsu"'
1
Akademický článek
Non-Gaussian Filters for Nonlinear Continuous-Discrete Models
Autor: Masaya Murata, Kaoru Hiramatsu
Publikováno v: SICE Journal of Control, Measurement, and System Integration, Vol 10, Iss 2, Pp 53-61 (2017)
In this paper, we propose using an ensemble Kalman filter (EnKF) and particle filters (PFs) to obtain superior state estimation accuracy for nonlinear continuous-discrete models. We discretize the Ito-type stochastic differential system model by mean
Externí odkaz: https://doaj.org/article/2efacb23db9848a4804c48f975ea7567
Zobrazit plný text záznamu
3
Non-Gaussian Filter for Continuous-Discrete Models
Autor: Kaoru Hiramatsu, Masaya Murata
Publikováno v: IEEE Transactions on Automatic Control. 64:5260-5264
We propose a new particle filter for nonlinear continuous-discrete models. The proposed filter is based on the multiple distribution estimation with a bank of extended Kalman–Bucy filters. Compared to the simple application of a particle filter, i.
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9f7e964b482e2b08db82ca93b402ae67
https://doi.org/10.1109/tac.2019.2914953
Zobrazit plný text záznamu
4
Label Propagation with Ensemble of Pairwise Geometric Relations: Towards Robust Large-Scale Retrieval of Object Instances
Autor: Xiaomeng Wu, Kaoru Hiramatsu, Kunio Kashino
Publikováno v: International Journal of Computer Vision. 126:689-713
Spatial verification methods permit geometrically stable image matching, but still involve a difficult trade-off between robustness as regards incorrect rejection of true correspondences and discriminative power in terms of mismatches. To address thi
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::f9c7c16a55ccaf6c7c712b0a3e750a4b
https://doi.org/10.1007/s11263-018-1063-9
Zobrazit plný text záznamu
5
Modular representation of layered neural networks
Autor: Kunio Kashino, Kaoru Hiramatsu, Chihiro Watanabe
Publikováno v: Neural Networks. 97:62-73
Layered neural networks have greatly improved the performance of various applications including image processing, speech recognition, natural language processing, and bioinformatics. However, it is still difficult to discover or interpret knowledge f
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a72047ff6f703b215f94dc985fc13f7e
https://doi.org/10.1016/j.neunet.2017.09.017
Zobrazit plný text záznamu
10
Weighted Generalized Mean Pooling for Deep Image Retrieval
Autor: Kunio Kashino, Go Irie, Kaoru Hiramatsu, Xiaomeng Wu
Publikováno v: ICIP
Spatial pooling over convolutional activations (e.g., max pooling or sum pooling) has been shown to be successful in learning deep representations for image retrieval. However, most pooling techniques assume that every activation is equally important
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9c686f59a87ae17e62efc33467a6ee7f
https://doi.org/10.1109/icip.2018.8451317
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje