Optical Flow Estimation via Neural Singular Value Decomposition Learning

机译：通过神经奇异值分解学习进行光流估计

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

In the recent contribution, it was given a unified view of four neural-network-learning-based singular-value-decomposition algorithms, along with some analytical results that characterize their behavior. In the mentioned paper, no attention was paid to the specific integration of the learning equations which appear under the form of first-order matrix-type ordinary differential equations on the orthogonal group or on the Stiefel manifold. The aim of the present paper is to consider a suitable integration method, based on mathematical geometric integration theory. The obtained algorithm is applied to optical flow computation for motion estimation in image sequences.

机译：在最近的贡献中，它给出了四种基于神经网络学习的奇异值分解算法的统一视图，以及表征其行为的一些分析结果。在提到的论文中，没有注意学习方程的特定积分，这些积分以一阶矩阵型常微分方程的形式出现在正交群或Stiefel流形上。本文的目的是基于数学几何积分理论，考虑一种合适的积分方法。所获得的算法被应用于光流计算以用于图像序列中的运动估计。

著录项

来源
《International Conference on Computational Science and Its Applications(ICCSA 2004) pt.2; 20040514-20040517; Assisi; IT》|2004年|P.961-970|共10页
会议地点 Assisi(IT);Assisi(IT)
作者
Simone Fiori; Nicoletta Del Buono; Tiziano Politi;
展开▼
作者单位

Facolta di Ingegneria, Universita di Perugia, Polo Didattico e Scientifico del Ternano, Loc. Pentima bassa, 21, I-05100 Terni, Italy;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类理论、方法;
关键词

相似文献

外文文献
中文文献
专利

1. Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion Perception [J] . Paredes-Valles Federico, Scheper Kirk Y. W., de Croon Guido C. H. E. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2020,第8期

机译：对光学流量估计的分层尖峰神经网络的无监督学习：从事件到全球运动感知
2. A FAST NEURAL NETWORK LEARNING ALGORITHM WITH APPROXIMATE SINGULAR VALUE DECOMPOSITION [J] . NORBERT JANKOWSKI, RAFAL LINOWIECKI International Journal of Applied Mathematics and Computer Science . 2019,第3期

机译：近似奇异值分解的快速神经网络学习算法
3. A Fast Neural Network Learning Algorithm with Approximate Singular Value Decomposition [J] . Norbert Jankowski, Rafa? Linowiecki International journal of applied mathematics and computer science . 2019,第3期

机译：具有近似奇异值分解的快速神经网络学习算法
4. Optical Flow Estimation via Neural Singular Value Decomposition Learning [C] . Simone Fiori, Nicoletta Del Buono, Tiziano Politi International Conference on Computational Science and its Applications . 2004

机译：通过神经奇异值分解学习的光学流量估计
5. Power system state estimation using contraction mapping and singular value decomposition [D] . Aboonabi, Arina 2011

机译：使用收缩映射和奇异值分解的电力系统状态估计
6. Bayesian Estimation of CBF Measured by DSC-MRI in Patients with Moyamoya Disease: Comparison with 15O-Gas PET and Singular Value Decomposition [O] . S. Hara, Y. Tanaka, S. Hayashi, 2019

机译：Moyamoya病患者DSC-MRI测量CBF的贝叶斯估计：与15o气体PET和奇异值分解的比较
7. A Fast Neural Network Learning Algorithm with Approximate Singular Value Decomposition [O] . Norbert Jankowski, Rafał Linowiecki 2019

机译：具有近似奇异值分解的快速神经网络学习算法

Optical Flow Estimation via Neural Singular Value Decomposition Learning

摘要

著录项

相似文献

相关主题

期刊订阅