Zobrazeno 1 - 10 of 61 pro vyhledávání: '"Kaoru Arakawa"'
7
Visual Tracking via Robust and Efficient Temporal Regularized Correlation Filters
Autor: Zhao-Qian Tang, Kaoru Arakawa
Publikováno v: ISCIT
We present a robust and efficient temporal regularized correlation filters (RETCF) model to achieve outstanding performance with hand-crafted features in visual tracking. The model of online learning is overly dependent on the fixed learning rate; Wh
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::fe80813a09aa683deff4e71ff8019703
https://doi.org/10.1109/iscit52804.2021.9590579
Zobrazit plný text záznamu
8
Object Design System by Interactive Evolutionary Computation Using GAN with Contour Images
Autor: Kaoru Arakawa, Chen Xin
Publikováno v: Human Centred Intelligent Systems ISBN: 9789811632631
KES-HCIS
This paper proposes a method to design objects by interactive evolutionary computation (IEC) using generative adversarial network (GAN) with the contour image of the object which the user wants to design. Here, a conditional GAN is adopted in order t
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::cda9ed9a9421d3e1aa4a0409bef74684
https://doi.org/10.1007/978-981-16-3264-8_7
Zobrazit plný text záznamu
10
Kernel Correlation Filter Tracker via Adaptive Model
Autor: Kaoru Arakawa, Zhao-Qian Tang
Publikováno v: ISPACS
In this paper, we propose a robust object tracking algorithm using an adaptive model and robust state recognition in kernel correlation filter tracker. In the first stage of the proposed algorithm, we apply a scale pool technique to deal with scale v
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::e8fbd601449b1ffec12a6b545c6e6aa0
https://doi.org/10.1109/ispacs.2018.8923187
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje