Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Tetsu Matsukawa"'
Publikováno v:
Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5581c4707cb77644d06b83dccac3f91c
https://doi.org/10.5220/0011699300003417
https://doi.org/10.5220/0011699300003417
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031208614
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4a71a686775e4de6299859003de2bd3c
https://doi.org/10.1007/978-3-031-20862-1_15
https://doi.org/10.1007/978-3-031-20862-1_15
Publikováno v:
Knowledge and Information Systems. 62:1781-1818
In this paper, we propose an outlier detection method from an unlabeled target dataset by exploiting an unlabeled source dataset. Detecting outliers has attracted attention of data miners for over two decades, since such outliers can be crucial in de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4d3ed10bde38cbad5ccd339035cd1337
https://doi.org/10.1007/s10115-019-01407-5
https://doi.org/10.1007/s10115-019-01407-5
Publikováno v:
ICPR
Affinity measure in object tracking outputs a similarity or distance score for given detections. As an affinity measure is typically imperfect, it generally has an uncertain region in which regarding two groups of detections as the same object or dif
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::922acb232066fb2b725b888eb3179f96
https://doi.org/10.1109/icpr48806.2021.9413215
https://doi.org/10.1109/icpr48806.2021.9413215
Autor:
Tetsu Matsukawa, Einoshin Suzuki
Publikováno v:
ICPR
Modern Convolutional Neural Networks (CNNs) have been improving the accuracy of person re-identification (re-id) using a large number of training samples. Such a re-id system suffers from a lack of training samples for deployment to practical securit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::071de7e62b2df5a6c3fa1200066113e4
https://doi.org/10.1109/icpr48806.2021.9412420
https://doi.org/10.1109/icpr48806.2021.9412420
Publikováno v:
VISIGRAPP (5: VISAPP)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::119ede4440e113e878c5c63e0f455f73
https://doi.org/10.5220/0010313509430953
https://doi.org/10.5220/0010313509430953
Publikováno v:
Advances in Knowledge Discovery and Data Mining ISBN: 9783030474256
PAKDD (1)
PAKDD (1)
We propose a new generative model for topic segmentation based on Latent Dirichlet Allocation. The task is to divide a document into a sequence of topically coherent segments, while preserving long topic change-points (coherency) and keeping short to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::718773e2627c7a30a2ae144ae1ff8aeb
https://doi.org/10.1007/978-3-030-47426-3_37
https://doi.org/10.1007/978-3-030-47426-3_37
Autor:
Qingpu Yang, Tetsu Matsukawa, Yuanyuan Li, Einoshin Suzuki, Muhammad Fikko Fadjrimiratno, Yusuke Hatae
Publikováno v:
VISIGRAPP (5: VISAPP)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::29264c3e1b795480bd324cf245aa9d19
https://doi.org/10.5220/0008949603260335
https://doi.org/10.5220/0008949603260335
Publikováno v:
Journal of Intelligent Information Systems. 52:367-392
N-ary error correcting output codes (ECOC) decompose a multi-class problem into simpler multi-class problems by splitting the classes into N subsets (meta-classes) to form an ensemble of N-class classifiers and combine them to make predictions. It is
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f10640e1966cbe0a9d2f08fe77a30738
https://doi.org/10.1007/s10844-018-0516-5
https://doi.org/10.1007/s10844-018-0516-5
Publikováno v:
ICTAI
We propose a GAN-based one-shot generation method on a fine-grained category, which represents a subclass of a category, typically with diverse examples. One-shot generation refers to a task of taking an image which belongs to a class not used in the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e53dd28da32d3fce8fa86483d99b86c2
https://doi.org/10.1109/ictai.2019.00130
https://doi.org/10.1109/ictai.2019.00130