2016 IEEE International Conference on Image Processing (ICIP) 2016
DOI: 10.1109/icip.2016.7532794
|View full text |Cite
|
Sign up to set email alerts
|

What's on TV: A large scale quantitative characterisation of modern broadcast video content

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
10
0

Year Published

2016
2016
2023
2023

Publication Types

Select...
2
2

Relationship

3
1

Authors

Journals

citations
Cited by 4 publications
(10 citation statements)
references
References 11 publications
0
10
0
Order By: Relevance
“…An extensive analysis of recent broadcast content has shown that the distribution of five uncorrelated factors (generated using PCA) can be used to quantify the representativeness of a small-scale video database compared to the vast population of modern broadcast content (in this case BBC Redux data) [43].…”
Section: Characterisation Of Video Contentmentioning
confidence: 99%
See 2 more Smart Citations
“…An extensive analysis of recent broadcast content has shown that the distribution of five uncorrelated factors (generated using PCA) can be used to quantify the representativeness of a small-scale video database compared to the vast population of modern broadcast content (in this case BBC Redux data) [43].…”
Section: Characterisation Of Video Contentmentioning
confidence: 99%
“…Therefore to ensure that methods benchmarked on a video database are applicable to real-world applications, and that lasting conclusions are relevant to a wider audience, it is crucial that a video database contains content which is archetypical of broadcast content. Using the method outlined by Moss et al [43], we can ascertain whether there are any similarities between BVI-HFR and BBC broadcast content (14075 sequences from BBC Redux [49]). In order to acheive this we need to calculate two further descriptors: DTP (Dynamic Texture Parameter) [50] and TP (Texture Parameter) [50] to estimate complex and irregular motion, and static textures respectively.…”
Section: B Content Descriptionmentioning
confidence: 99%
See 1 more Smart Citation
“…Further characterisation of the HomTex dataset was performed using the methodology of [14], which offers a way of measuring how well a given dataset reflects the characteristics of broadcast consumer video. The dataset was parameterised using low level features, which were then transformed into orthogonal factors.…”
Section: A Homogeneous Texture Datasetmentioning
confidence: 99%
“…An important feature of this dataset is that it is representative of broadcasting video content, as suggested by the methodology proposed by [14] (Section II). The second contribution of this paper is to offer a better understanding of the performance of HEVC on different texture classes.…”
Section: Introductionmentioning
confidence: 99%