Zobrazeno 1 - 10
of 20
pro vyhledávání: '"David Minnen"'
Autor:
Fabian Mentzer, Eirikur Agustsson, Johannes Ballé, David Minnen, Nick Johnston, George Toderici
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198083
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::df9334220aa7708d0a71500730016771
https://doi.org/10.1007/978-3-031-19809-0_32
https://doi.org/10.1007/978-3-031-19809-0_32
Autor:
David Minnen, Michał Januszewski, Tim Blakely, Alexander Shapson-Coe, Richard L. Schalek, Johannes Ballé, Jeff W. Lichtman, Viren Jain
Connectomic reconstruction of neural circuits relies on nanometer resolution microscopy which produces on the order of a petabyte of imagery for each cubic millimeter of brain tissue. The cost of storing such data is a significant barrier to broadeni
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::18c5e2a7b4e26c45e3374d350f77874c
https://doi.org/10.1101/2021.05.29.445828
https://doi.org/10.1101/2021.05.29.445828
Autor:
Johannes Ballé, Eirikur Agustsson, Philip A. Chou, George Toderici, David Minnen, Sung Jin Hwang, Saurabh Singh, Nick Johnston
We review a class of methods that can be collected under the name nonlinear transform coding (NTC), which over the past few years have become competitive with the best linear transform codecs for images, and have superseded them in terms of rate--dis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9815f12bc297e8cf59a32383059b96e0
http://arxiv.org/abs/2007.03034
http://arxiv.org/abs/2007.03034
Autor:
Nick Johnston, George Toderici, David Minnen, Johannes Ballé, Eirikur Agustsson, Sung Jin Hwang
Publikováno v:
CVPR
Despite considerable progress on end-to-end optimized deep networks for image compression, video coding remains a challenging task. Recently proposed methods for learned video compression use optical flow and bilinear warping for motion compensation
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aa5e595331ac8607b8bd7dca0329e737
https://doi.org/10.1109/cvpr42600.2020.00853
https://doi.org/10.1109/cvpr42600.2020.00853
Autor:
David Minnen, Saurabh Singh
Publikováno v:
ICIP
In learning-based approaches to image compression, codecs are developed by optimizing a computational model to minimize a rate-distortion objective. Currently, the most effective learned image codecs take the form of an entropy-constrained autoencode
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::880cd259df0bfc908b5a6e96b302e546
Autor:
Damien Vincent, Nick Johnston, Michele Covell, Sung Jin Hwang, David Minnen, George Toderici, Saurabh Singh, Troy Chinen, Joel Shor
Publikováno v:
CVPR
We propose a method for lossy image compression based on recurrent, convolutional neural networks that outperforms BPG (4:2:0), WebP, JPEG2000, and JPEG as measured by MS-SSIM. We introduce three improvements over previous research that lead to this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::49f012e8e5aa4cf330e909407b02e1da
https://doi.org/10.1109/cvpr.2018.00461
https://doi.org/10.1109/cvpr.2018.00461
Publikováno v:
ICIP
The leading approach for image compression with artificial neural networks (ANNs) is to learn a nonlinear transform and a fixed entropy model that are optimized for rate-distortion performance. We show that this approach can be significantly improved
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::46b2268003120ef19086b999fcdae3fa
Autor:
Michele Covell, George Toderici, David Minnen, Nick Johnston, Damien Vincent, Sung Jin Hwang, Joel Shor
Publikováno v:
CVPR
This paper presents a set of full-resolution lossy image compression methods based on neural networks. Each of the architectures we describe can provide variable compression rates during deployment without requiring retraining of the network: each ne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::257279c594be3f9c0a605e461707e50e
Publikováno v:
Pattern Recognition. 39:1918-1931
By analyzing the similarities between bit streams coming from a network of motion detectors, we can recover the network geometry and discover structure in the human behavior being observed. This means that a low-cost network of sensors can provide po
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7e1be3f057841a5fdcc486a25f194a5e
https://doi.org/10.1016/j.patcog.2006.04.009
https://doi.org/10.1016/j.patcog.2006.04.009
Publikováno v:
Machine Vision and Applications. 14:59-71
The Perceptive Workbench endeavors to create a spontaneous and unimpeded interface between the physical and virtual worlds. Its vision-based methods for interaction constitute an alternative to wired input devices and tethered tracking. Objects are r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::18df898d01eaf48d1c44be883ec2cbf8
https://doi.org/10.1007/s00138-002-0096-8
https://doi.org/10.1007/s00138-002-0096-8