Zobrazeno 1 - 10
of 76
pro vyhledávání: '"Tsubasa, Hirakawa"'
Publikováno v:
IEEE Access, Vol 12, Pp 86553-86571 (2024)
Deep reinforcement learning (DRL) can learn an agent’s optimal behavior from the experience it gains through interacting with its environment. However, since the decision-making process of DRL agents is a black-box, it is difficult for users to und
Externí odkaz:
https://doaj.org/article/a0acec4c95a94ddc964cdfde2001b234
Autor:
Yuzhi Shi, Takayoshi Yamashita, Tsubasa Hirakawa, Hironobu Fujiyoshi, Mitsuru Nakazawa, Yeongnam Chae, Bjorn Stenger
Publikováno v:
IEEE Access, Vol 12, Pp 63995-64005 (2024)
Most video anomaly detection approaches are based on non-semantic features, which are not interpretable, and prevent the identification of anomaly causes. Therefore, we propose a caption-guided interpretable video anomaly detection framework that exp
Externí odkaz:
https://doaj.org/article/5d02f50d0f0e4ff198b294daaf4af7fc
Publikováno v:
IEEE Access, Vol 11, Pp 62986-62997 (2023)
The Prototypical Part Network (ProtoPNet) is an interpretable deep learning model that combines the strong power of deep learning with the interpretability of case-based reasoning, thereby achieving high accuracy while keeping its reasoning process i
Externí odkaz:
https://doaj.org/article/27821a01e07d4bca8bcf032f8825c109
Publikováno v:
Frontiers in Public Health, Vol 10 (2022)
Introduction:Coronavirus disease (COVID-19) rapidly spread from Wuhan, China to other parts of China and other regions/countries around the world, resulting in a pandemic due to large populations moving through the massive transport hubs connecting a
Externí odkaz:
https://doaj.org/article/d5432347563943709248bbc9d1b6fb3a
Autor:
Anno, Sumiko, Tsubasa, Hirakawa, Sugita, Satoru, Yasumoto, Shinya, Lee, Ming-An, Sasaki, Yoshinobu, Oyoshi, Kei
Publikováno v:
Geo-Spatial Information Science; Aug2024, Vol. 27 Issue 4, p1155-1161, 7p
Publikováno v:
IATSS Research, Vol 43, Iss 4, Pp 244-252 (2019)
Various image recognition tasks were handled in the image recognition field prior to 2010 by combining image local features manually designed by researchers (called handcrafted features) and machine learning method. After entering the 2010, However,
Externí odkaz:
https://doaj.org/article/54a125a3133d43959f8d743e43c3cf4f
Publikováno v:
IEEE Transactions on Intelligent Vehicles. 8:836-850
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f2b93bdc8236a58b87713a7a122f8dc0
https://doi.org/10.1109/tiv.2022.3157126
https://doi.org/10.1109/tiv.2022.3157126
Autor:
Suraj Prakash Pattar, Thomas Killus, Tsubasa Hirakawa, Takayoshi Yamashita, Tetsuya Sawanobori, Hironobu Fujiyoshi
Publikováno v:
Advanced Robotics. 37:241-256
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::28cc4ca6881846554bd304daf66b301c
https://doi.org/10.1080/01691864.2022.2136504
https://doi.org/10.1080/01691864.2022.2136504
Autor:
Tsubasa Hirakawa, Toru Tamaki, Takio Kurita, Bisser Raytchev, Kazufumi Kaneda, Chaohui Wang, Laurent Najman
Publikováno v:
IEEE Access, Vol 5, Pp 13617-13634 (2017)
In this paper, we propose a method for texture image labeling that works with a small number of training images. Our method is based on a tree of shapes and histogram features computed on the tree structure. Labeling results could be obtained by simp
Externí odkaz:
https://doaj.org/article/ed3e7228bf604ce5a7c36b8a9572c2cd
Publikováno v:
Advanced Robotics. 36:373-387
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::505b7f346ff81b5db2cc06888aa7f669
https://doi.org/10.1080/01691864.2022.2043183
https://doi.org/10.1080/01691864.2022.2043183