Zobrazeno 1 - 10
of 17
pro vyhledávání: '"68U10, 68T45"'
Autor:
Barcelos, I. B., Belém, F. de C., João, L. de M., Patrocínio Jr., Z. K. G. do, Falcão, A. X., Guimarães, S. J. F.
Publikováno v:
ACM Comput. Surv. 56, 8, Article 200 (August 2024), 39 pages
Superpixel segmentation consists of partitioning images into regions composed of similar and connected pixels. Its methods have been widely used in many computer vision applications since it allows for reducing the workload, removing redundant inform
Externí odkaz:
http://arxiv.org/abs/2409.19179
Recently, we have witnessed the success of total variation (TV) for many imaging applications. However, traditional TV is defined on the original pixel domain, which limits its potential. In this work, we suggest a new TV regularization defined on th
Externí odkaz:
http://arxiv.org/abs/2405.17241
Semi-supervised action recognition aims to improve spatio-temporal reasoning ability with a few labeled data in conjunction with a large amount of unlabeled data. Albeit recent advancements, existing powerful methods are still prone to making ambiguo
Externí odkaz:
http://arxiv.org/abs/2404.16416
Autor:
Gong, Le, Li, Shiying, Pathan, Naqib Sad, Shifat-E-Rabbi, Mohammad, Rohde, Gustavo K., Rubaiyat, Abu Hasnat Mohammad, Thareja, Sumati
Here we describe a new image representation technique based on the mathematics of transport and optimal transport. The method relies on the combination of the well-known Radon transform for images and a recent signal representation method called the
Externí odkaz:
http://arxiv.org/abs/2307.15339
Publikováno v:
Computer Aided Geometric Design, Volume 85, 2021
We propose a novel approach to image segmentation based on combining implicit spline representations with deep convolutional neural networks. This is done by predicting the control points of a bivariate spline function whose zero-set represents the s
Externí odkaz:
http://arxiv.org/abs/2102.12759
Autor:
Geiping, Jonas, Moeller, Michael
Energy minimization methods are a classical tool in a multitude of computer vision applications. While they are interpretable and well-studied, their regularity assumptions are difficult to design by hand. Deep learning techniques on the other hand a
Externí odkaz:
http://arxiv.org/abs/1908.06209
Autor:
Micheli, Mario
A simple and effective method for imaging through ground-level atmospheric turbulence.
Comment: 7 pages, 2 figures, preliminary report
Comment: 7 pages, 2 figures, preliminary report
Externí odkaz:
http://arxiv.org/abs/1206.3925
Publikováno v:
Computer Aided Geometric Design
We propose a novel approach to image segmentation based on combining implicit spline representations with deep convolutional neural networks. This is done by predicting the control points of a bivariate spline function whose zero-set represents the s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::65f1f375457c558640f85948de314a90
http://arxiv.org/abs/2102.12759
http://arxiv.org/abs/2102.12759
Autor:
Michael Moeller, Jonas Geiping
Publikováno v:
ICCV
Energy minimization methods are a classical tool in a multitude of computer vision applications. While they are interpretable and well-studied, their regularity assumptions are difficult to design by hand. Deep learning techniques on the other hand a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7405899d9dcad585bcbed2bf45213c19
https://doi.org/10.1109/iccv.2019.01036
https://doi.org/10.1109/iccv.2019.01036
Autor:
Yongfeng Qi, Jiashu Zhang
Publikováno v:
COMPUTING AND INFORMATICS; Vol 31, No 6+ (2012): Computing and Informatics; 1465-1479
In this paper, a novel algorithm for feature extraction, named supervised kernel locally principle component analysis (SKLPCA), is proposed. The SKLPCA is a non-linear and supervised subspace learning method, which maps the data into a potentially mu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=issn13359150::30e1a823e82ca3129c63dfaed54d2750
http://www.cai.sk/ojs/index.php/cai/article/view/1327
http://www.cai.sk/ojs/index.php/cai/article/view/1327