2011
DOI: 10.1117/12.872257
|View full text |Cite
|
Sign up to set email alerts
|

A 2D histogram representation of images for pooling

Abstract: Designing a suitable image representation is one of the most fundamental issues of computer vision. There are three steps in the popular Bag of Words based image representation: feature extraction, coding and pooling. In the final step, current methods make an M × K encoded feature matrix degraded to a K-dimensional vector (histogram), where M is the number of features, and K is the size of the codebook: information is lost dramatically here. In this paper, a novel pooling method, based on 2-D histogram repres… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2017
2017
2017
2017

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(2 citation statements)
references
References 22 publications
0
2
0
Order By: Relevance
“…Unlike the joint occurrence after pooling in equation (30), the joint occurrence of visual words computed in equation (32) before pooling can be interpreted as a new auxiliary element in the visual vocabulary. Intuitive illustration.…”
Section: Beyond Average Pooling Of Higher-order Occurrencesmentioning
confidence: 99%
See 1 more Smart Citation
“…Unlike the joint occurrence after pooling in equation (30), the joint occurrence of visual words computed in equation (32) before pooling can be interpreted as a new auxiliary element in the visual vocabulary. Intuitive illustration.…”
Section: Beyond Average Pooling Of Higher-order Occurrencesmentioning
confidence: 99%
“…In addition, we propose and evaluate Higher-order Occurrence Pooling. Moreover, unlike 2D histogram representation [32], which is another take on building rich statistics from the mid-level features, our approach results from the analytical solution to the kernel linearisation problems.…”
Section: Introductionmentioning
confidence: 99%