Zobrazeno 1 - 10
of 136
pro vyhledávání: '"Storer, James A."'
A well-trained Convolutional Neural Network can easily be pruned without significant loss of performance. This is because of unnecessary overlap in the features captured by the network's filters. Innovations in network architecture such as skip/dense
Externí odkaz:
http://arxiv.org/abs/1811.07275
As deep neural networks (DNNs) have been integrated into critical systems, several methods to attack these systems have been developed. These adversarial attacks make imperceptible modifications to an image that fool DNN classifiers. We present an ad
Externí odkaz:
http://arxiv.org/abs/1803.00940
CNNs are poised to become integral parts of many critical systems. Despite their robustness to natural variations, image pixel values can be manipulated, via small, carefully crafted, imperceptible perturbations, to cause a model to misclassify image
Externí odkaz:
http://arxiv.org/abs/1801.08926
It has long been considered a significant problem to improve the visual quality of lossy image and video compression. Recent advances in computing power together with the availability of large training data sets has increased interest in the applicat
Externí odkaz:
http://arxiv.org/abs/1612.08712
Publikováno v:
Proceedings of the National Academy of Sciences of the United States of America, 2016 Jul . 113(30), 8496-8501.
Externí odkaz:
https://www.jstor.org/stable/26470962
Autor:
Foxman, Ellen F., Storer, James A., Fitzgerald, Megan E., Wasik, Bethany R., Hou, Lin, Zhao, Hongyu, Turner, Paul E., Pyle, Anna Marie, Iwasaki, Akiko
Publikováno v:
Proceedings of the National Academy of Sciences of the United States of America, 2015 Jan . 112(3), 827-832.
Externí odkaz:
https://www.jstor.org/stable/26459402
Autor:
Storer, James A.
Publikováno v:
Far Eastern Survey, 1953 Jul 01. 22(8), 89-95.
Externí odkaz:
https://www.jstor.org/stable/3024483
Autor:
Xu, Jiacheng, Fang, Zhijun, Gao, Yongbin, Ma, Siwei, Jin, Yaochu, Zhou, Heng, Wang, Anjie, Bilgin, Ali, Marcellin, Michael W., Serra-Sagrista, Joan, Storer, James A.
Publikováno v:
DCC
3D point cloud has been widely applied in virtual reality and augmented reality. A complex 3D scene always needs a large number of the point cloud to represent and demands a lot of space to store. Thus, point cloud compression becomes a crucial issue
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b0f3c8fcbe787420b144003f96395fa3
https://doi.org/10.1109/dcc50243.2021.00085
https://doi.org/10.1109/dcc50243.2021.00085