A data driven method for feature transformation

Mert Dikmen; Derek W Hoiem; Thomas S Huang

doi:10.1109/CVPR.2012.6248069

A data driven method for feature transformation

Mert Dikmen, Derek W Hoiem, Thomas S Huang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Most image understanding algorithms begin with the extraction of information thought to be relevant to the particular task. This is commonly known as feature extraction and has, up to this date, been a largely manual process, where a reasonable method is chosen through validation on the experimented dataset. In this work we propose a data driven, local histogram based feature extraction method that reduces the manual intervention during the feature computation process and improves on the performance of widely used gradient histogram based features (e.g., HOG). We demonstrate favorable object detection results against HOG on the Inria Pedestrian[7], Pascal 2007[10] data.

Original language	English (US)
Title of host publication	2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
Pages	3314-3321
Number of pages	8
DOIs	https://doi.org/10.1109/CVPR.2012.6248069
State	Published - Oct 1 2012
Event	2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012 - Providence, RI, United States Duration: Jun 16 2012 → Jun 21 2012

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)	1063-6919

Other

Other	2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
Country	United States
City	Providence, RI
Period	6/16/12 → 6/21/12

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.2012.6248069

Fingerprint Dive into the research topics of 'A data driven method for feature transformation'. Together they form a unique fingerprint.

Cite this

A data driven method for feature transformation. / Dikmen, Mert; Hoiem, Derek W; Huang, Thomas S.

2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012. 2012. p. 3314-3321 6248069 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Dikmen, M, Hoiem, DW & Huang, TS 2012, A data driven method for feature transformation. in 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012., 6248069, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3314-3321, 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012, Providence, RI, United States, 6/16/12. https://doi.org/10.1109/CVPR.2012.6248069

@inproceedings{246701a0d35c488384f09d855973f6ab,

title = "A data driven method for feature transformation",

abstract = "Most image understanding algorithms begin with the extraction of information thought to be relevant to the particular task. This is commonly known as feature extraction and has, up to this date, been a largely manual process, where a reasonable method is chosen through validation on the experimented dataset. In this work we propose a data driven, local histogram based feature extraction method that reduces the manual intervention during the feature computation process and improves on the performance of widely used gradient histogram based features (e.g., HOG). We demonstrate favorable object detection results against HOG on the Inria Pedestrian[7], Pascal 2007[10] data.",

author = "Mert Dikmen and Hoiem, {Derek W} and Huang, {Thomas S}",

year = "2012",

month = oct,

day = "1",

doi = "10.1109/CVPR.2012.6248069",

language = "English (US)",

isbn = "9781467312264",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

pages = "3314--3321",

booktitle = "2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012",

note = "2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012 ; Conference date: 16-06-2012 Through 21-06-2012",

}

TY - GEN

T1 - A data driven method for feature transformation

AU - Dikmen, Mert

AU - Hoiem, Derek W

AU - Huang, Thomas S

PY - 2012/10/1

Y1 - 2012/10/1

N2 - Most image understanding algorithms begin with the extraction of information thought to be relevant to the particular task. This is commonly known as feature extraction and has, up to this date, been a largely manual process, where a reasonable method is chosen through validation on the experimented dataset. In this work we propose a data driven, local histogram based feature extraction method that reduces the manual intervention during the feature computation process and improves on the performance of widely used gradient histogram based features (e.g., HOG). We demonstrate favorable object detection results against HOG on the Inria Pedestrian[7], Pascal 2007[10] data.

AB - Most image understanding algorithms begin with the extraction of information thought to be relevant to the particular task. This is commonly known as feature extraction and has, up to this date, been a largely manual process, where a reasonable method is chosen through validation on the experimented dataset. In this work we propose a data driven, local histogram based feature extraction method that reduces the manual intervention during the feature computation process and improves on the performance of widely used gradient histogram based features (e.g., HOG). We demonstrate favorable object detection results against HOG on the Inria Pedestrian[7], Pascal 2007[10] data.

UR - http://www.scopus.com/inward/record.url?scp=84866694001&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866694001&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2012.6248069

DO - 10.1109/CVPR.2012.6248069

M3 - Conference contribution

AN - SCOPUS:84866694001

SN - 9781467312264

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 3314

EP - 3321

BT - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012

T2 - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012

Y2 - 16 June 2012 through 21 June 2012

ER -