Recognizing cultural events in images: A study of image categorization models

Heeyoung Kwon; Kiwon Yun; Minh Hoai; Dimitris Samaras

doi:10.1109/CVPRW.2015.7301336

Recognizing cultural events in images: A study of image categorization models

Heeyoung Kwon
, Kiwon Yun
, Minh Hoai
, Dimitris Samaras

Computer Science

Stony Brook University

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

6 Scopus citations

Abstract

The goal of this work is to study recognition of cultural events represented in still images. We pose cultural event recognition as an image categorization problem, and we study the performance of several state-of-the-art image categorization approaches, including Spatial Pyramid Matching and Regularized Max Pooling. We consider SIFT and color features as well as the recently proposed CNN features. Experiments on the ChaLearn dataset of 50 cultural events, we find that Regularized Max Pooling with CNN, SIFT, and Color features achieves the best performance.

Original language	English
Title of host publication	2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015
Publisher	IEEE Computer Society
Pages	51-57
Number of pages	7
ISBN (Electronic)	9781467367592
DOIs	https://doi.org/10.1109/CVPRW.2015.7301336
State	Published - Oct 19 2015
Event	IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015 - Boston, United States Duration: Jun 7 2015 → Jun 12 2015

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume	2015-October
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Conference

Conference	IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015
Country/Territory	United States
City	Boston
Period	06/7/15 → 06/12/15

Keywords

Cultural differences
Feature extraction
Image color analysis
Image recognition
Support vector machines
Training
Visualization

Access to Document

10.1109/CVPRW.2015.7301336

Cite this

Kwon, H., Yun, K., Hoai, M., & Samaras, D. (2015). Recognizing cultural events in images: A study of image categorization models. In 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015 (pp. 51-57). Article 7301336 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2015-October). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2015.7301336

@inproceedings{97f0c127344c4b8eb4d6a4644ecc657e,

title = "Recognizing cultural events in images: A study of image categorization models",

abstract = "The goal of this work is to study recognition of cultural events represented in still images. We pose cultural event recognition as an image categorization problem, and we study the performance of several state-of-the-art image categorization approaches, including Spatial Pyramid Matching and Regularized Max Pooling. We consider SIFT and color features as well as the recently proposed CNN features. Experiments on the ChaLearn dataset of 50 cultural events, we find that Regularized Max Pooling with CNN, SIFT, and Color features achieves the best performance.",

keywords = "Cultural differences, Feature extraction, Image color analysis, Image recognition, Support vector machines, Training, Visualization",

author = "Heeyoung Kwon and Kiwon Yun and Minh Hoai and Dimitris Samaras",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015 ; Conference date: 07-06-2015 Through 12-06-2015",

year = "2015",

month = oct,

day = "19",

doi = "10.1109/CVPRW.2015.7301336",

language = "English",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

publisher = "IEEE Computer Society",

pages = "51--57",

booktitle = "2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015",

}

Kwon, H, Yun, K, Hoai, M & Samaras, D 2015, Recognizing cultural events in images: A study of image categorization models. in 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015., 7301336, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2015-October, IEEE Computer Society, pp. 51-57, IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015, Boston, United States, 06/7/15. https://doi.org/10.1109/CVPRW.2015.7301336

Recognizing cultural events in images: A study of image categorization models. / Kwon, Heeyoung; Yun, Kiwon; Hoai, Minh et al.
2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015. IEEE Computer Society, 2015. p. 51-57 7301336 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2015-October).

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

TY - GEN

T1 - Recognizing cultural events in images

T2 - IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015

AU - Kwon, Heeyoung

AU - Yun, Kiwon

AU - Hoai, Minh

AU - Samaras, Dimitris

PY - 2015/10/19

Y1 - 2015/10/19

N2 - The goal of this work is to study recognition of cultural events represented in still images. We pose cultural event recognition as an image categorization problem, and we study the performance of several state-of-the-art image categorization approaches, including Spatial Pyramid Matching and Regularized Max Pooling. We consider SIFT and color features as well as the recently proposed CNN features. Experiments on the ChaLearn dataset of 50 cultural events, we find that Regularized Max Pooling with CNN, SIFT, and Color features achieves the best performance.

AB - The goal of this work is to study recognition of cultural events represented in still images. We pose cultural event recognition as an image categorization problem, and we study the performance of several state-of-the-art image categorization approaches, including Spatial Pyramid Matching and Regularized Max Pooling. We consider SIFT and color features as well as the recently proposed CNN features. Experiments on the ChaLearn dataset of 50 cultural events, we find that Regularized Max Pooling with CNN, SIFT, and Color features achieves the best performance.

KW - Cultural differences

KW - Feature extraction

KW - Image color analysis

KW - Image recognition

KW - Support vector machines

KW - Training

KW - Visualization

UR - https://www.scopus.com/pages/publications/84951994432

U2 - 10.1109/CVPRW.2015.7301336

DO - 10.1109/CVPRW.2015.7301336

M3 - Conference contribution

AN - SCOPUS:84951994432

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 51

EP - 57

BT - 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015

PB - IEEE Computer Society

Y2 - 7 June 2015 through 12 June 2015

ER -

Kwon H, Yun K, Hoai M, Samaras D. Recognizing cultural events in images: A study of image categorization models. In 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2015. IEEE Computer Society. 2015. p. 51-57. 7301336. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW.2015.7301336

Recognizing cultural events in images: A study of image categorization models

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this