2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
DOI: 10.1109/cvpr.2005.339
|View full text |Cite
|
Sign up to set email alerts
|

Tangent-Corrected Embedding

Abstract: Abstract

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3

Citation Types

0
3
0

Publication Types

Select...
4
1

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(3 citation statements)
references
References 12 publications
(10 reference statements)
0
3
0
Order By: Relevance
“…5. structure, on which the neighboring samples are small transformations of one another [31]. At the same time, as shown in Fig.…”
Section: Image Recognitionmentioning
confidence: 76%
“…5. structure, on which the neighboring samples are small transformations of one another [31]. At the same time, as shown in Fig.…”
Section: Image Recognitionmentioning
confidence: 76%
“…That is, the image data often have an underlying invariant and associated transformations, like shifts, rotation, changes of expression, etc, that naturally imply a manifold on which those neighboring points are small transformations of one another [51]. Therefore, in this subsection, we apply our proposed method to image recognition.…”
Section: Image Recognitionmentioning
confidence: 99%
“…Many researchers have suggested that the image data can often be characterized by a low-dimensional intrinsic manifold [27,31,50,51]. That is, the image data often have an underlying invariant and associated transformations, like shifts, rotation, changes of expression, etc, that naturally imply a manifold on which those neighboring points are small transformations of one another [51].…”
Section: Image Recognitionmentioning
confidence: 99%