2016
DOI: 10.1109/tip.2016.2573581
|View full text |Cite
|
Sign up to set email alerts
|

Dual Diversified Dynamical Gaussian Process Latent Variable Model for Video Repairing

Abstract: In this paper, we propose a dual diversified dynamical Gaussian process latent variable model ( [Formula: see text]GPLVM) to tackle the video repairing issue. For preservation purposes, videos have to be conserved on media. However, storing on media, such as films and hard disks, can suffer from unexpected data loss, for instance, physical damage. So repairing of missing or damaged pixels is essential for better video maintenance. Most methods seek to fill in missing holes by synthesizing similar textures from… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
4
0

Year Published

2016
2016
2019
2019

Publication Types

Select...
4
3

Relationship

0
7

Authors

Journals

citations
Cited by 7 publications
(4 citation statements)
references
References 49 publications
0
4
0
Order By: Relevance
“…Based on the above analyses, h 1 (Z) is redefined as (see (4) and 5) Thus, the partial derivative over Z k of h 1 (Z) is (see (5) and (6)) then (see (6)) Let…”
Section: ∂ ∂Zmentioning
confidence: 99%
See 1 more Smart Citation
“…Based on the above analyses, h 1 (Z) is redefined as (see (4) and 5) Thus, the partial derivative over Z k of h 1 (Z) is (see (5) and (6)) then (see (6)) Let…”
Section: ∂ ∂Zmentioning
confidence: 99%
“…Image classification [1,2], as a computer vision technology [3][4][5][6][7], has been developing rapidly. Meanwhile, it has also attracted considerable attention in recent years [8].…”
Section: Introductionmentioning
confidence: 99%
“…The anomalous asymmetry in the two sign models is no longer observed in non-convex algorithms. Next, we highlight the speed of our algorithm for large-scale matrices, typical of video sequences Xiong et al [2016]. 1500×1500 to 2500×2500 random observation matrices are generated, where the rank is chosen to be 20% of the column number and random sign error corrupts 11% of the entries, with features X, Y having a dimension of 50% of the column number.…”
Section: Phase Transitionmentioning
confidence: 99%
“…by periodic kernels. VGPDSs were also applied in many fields, such as phoneme classification [19], video repairing [20] and multi-task motion modeling [21]. The VDM-GPDS considers the dependence of multiple outputs and introduces convolution processes to explicitly depict multi-output dependence.…”
Section: Introductionmentioning
confidence: 99%