Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Sakazawa, Shigeyuki"'
Although deep neural networks have made tremendous progress in the area of multimedia representation, training neural models requires a large amount of data and time. It is well-known that utilizing trained models as initial weights often achieves lo
Externí odkaz:
http://arxiv.org/abs/1802.02601
Publikováno v:
ICMR '17 Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pages 269-277
Deep neural networks have recently achieved significant progress. Sharing trained models of these deep neural networks is very important in the rapid progress of researching or developing deep neural network systems. At the same time, it is necessary
Externí odkaz:
http://arxiv.org/abs/1701.04082
In this paper, we propose a stand-alone mobile visual search system based on binary features and the bag-of-visual words framework. The contribution of this study is three-fold: (1) We propose an adaptive substring extraction method that adaptively e
Externí odkaz:
http://arxiv.org/abs/1610.06266
Recently, the Fisher vector representation of local features has attracted much attention because of its effectiveness in both image classification and image retrieval. Another trend in the area of image retrieval is the use of binary features such a
Externí odkaz:
http://arxiv.org/abs/1609.08291
Autor:
Nakajima, Masayuki, Lau, Phooi Yee, Kim, Jae-Gon, Kubo, Hiroyuki, Chang, Chuan-Yu, Kemao, Qian, Furukawa, Ryu, Sakazawa, Shigeyuki
Publikováno v:
Proceedings of SPIE; May 2024, Vol. 13164 Issue: 1 p131640Z-131640Z-6, 1184767p
Publikováno v:
In Journal of Visual Communication and Image Representation 2010 21(5):377-391
Autor:
Nakajima, Masayuki, Muramatsu, Shogo, Kim, Jae-Gon, Guo, Jing-Ming, Kemao, Qian, Yamaji, Yudai, Sakazawa, Shigeyuki
Publikováno v:
Proceedings of SPIE; April 2022, Vol. 12177 Issue: 1 p121771R-121771R-6, 1095946p
Autor:
Nakajima, Masayuki, Muramatsu, Shogo, Kim, Jae-Gon, Guo, Jing-Ming, Kemao, Qian, Matsumoto, Kota, Sakazawa, Shigeyuki
Publikováno v:
Proceedings of SPIE; April 2022, Vol. 12177 Issue: 1 p121770N-121770N-6, 1095937p
Publikováno v:
IEEE Proc. of Multimedia Signal Processing MMSP 2008. :855-860
Publikováno v:
Transactions on Computational Collective Intelligence XX; 2015, p1-22, 22p