Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Asako Kanezaki"'
Publikováno v:
IEEE Access, Vol 11, Pp 82665-82673 (2023)
Cross-domain few-shot classification (CD-FSC) aims to develop few-shot classification models trained on seen domains but tested on unseen domains. However, the cross-domain setup poses a challenge in the form of domain shift between the training and
Externí odkaz:
https://doaj.org/article/ac25d389a03943fdad5ea96385f59365
Autor:
Kei Ota, Asako Kanezaki
Publikováno v:
Journal of the Robotics Society of Japan. 39:581-586
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bfb344220c9495ee55b3d17ef4390cd9
https://doi.org/10.7210/jrsj.39.581
https://doi.org/10.7210/jrsj.39.581
Publikováno v:
IEEE Robotics and Automation Letters (RA-L). 5(2):1279-1286
We present a visual navigation approach that uses context information to navigate an agent to find and reach a target object. To learn context from the objects present in the scene, we transform visual information into an intermediate representation
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b23eb870eb79d2ea221ae52864377783
http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100823507
http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100823507
Publikováno v:
IEEE Transactions on Image Processing. 29:8055-8068
The usage of convolutional neural networks (CNNs) for unsupervised image segmentation was investigated in this study. In the proposed approach, label prediction and network parameter learning are alternately iterated to meet the following criteria: (
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bc372157f81bc40901f607887fa56d9f
https://doi.org/10.1109/tip.2020.3011269
https://doi.org/10.1109/tip.2020.3011269
This paper presents a reinforcement learning method for object goal navigation (ObjNav) where an agent navigates in 3D indoor environments to reach a target object based on long-term observations of objects and scenes. To this end, we propose Object
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0e5cdadd3b740d6b25776eccae2cff53
Publikováno v:
Proceedings of the 2nd ACM International Conference on Multimedia in Asia.
Object detection in a single image is a challenging problem due to clutters, occlusions, and a large variety of viewing locations. This task can benefit from integrating multi-frame information captured by a moving camera. In this paper, we propose a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c6174a1aead9688c6aaf8a9943a5748f
https://doi.org/10.1145/3444685.3446257
https://doi.org/10.1145/3444685.3446257
Publikováno v:
SMC
The paper proposes a motion planning method using a deep reinforcement learning algorithm, Asynchronous Advantage Actor-Critic (A3C). For mobile robot navigation tasks in crowds, existing path planning based approaches are limited because the surroun
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::081150220b24b327b1c0fc4c7802c772
https://doi.org/10.1109/smc.2019.8914201
https://doi.org/10.1109/smc.2019.8914201
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 43(1)
We propose a Convolutional Neural Network (CNN)-based model “RotationNet,” which takes multi-view images of an object as input and jointly estimates its pose and object category. Unlike previous approaches that use known viewpoint labels for trai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::04d10e0b26a351487cebf6eb8e64e4e0
https://pubmed.ncbi.nlm.nih.gov/31217093
https://pubmed.ncbi.nlm.nih.gov/31217093
Recent advance in deep learning has enabled realistic image-to-image translation of multimodal data. Along with the development, auto-encoders and generative adversarial networks (GAN) have been extended to deal with multimodal input and output. At t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::535a69559293f8981ff7d618e1ad553b
https://doi.org/10.1016/b978-0-12-817358-9.00008-1
https://doi.org/10.1016/b978-0-12-817358-9.00008-1
Publikováno v:
IEEE Robotics and Automation Letters. 3(2)
Robot navigation using deep neural networks has been drawing a great deal of attention. Although reactive neural networks easily learn expert behaviors and are computationally efficient, they suffer from generalization of policies learned in specific
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::de536f821686c6f533c424a1effde94c
http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100823509
http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100823509