Learning localized perceptual similarity metrics for interactive categorization

Research output: Contribution to journal › Conference article › Research › peer-review

Standard

Learning localized perceptual similarity metrics for interactive categorization. / Wah, Catherine; Maji, Subhransu; Belongie, Serge.

In: Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015, 19.02.2015, p. 502-509.

Research output: Contribution to journal › Conference article › Research › peer-review

Harvard

Wah, C, Maji, S & Belongie, S 2015, 'Learning localized perceptual similarity metrics for interactive categorization', Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015, pp. 502-509. https://doi.org/10.1109/WACV.2015.73

APA

Wah, C., Maji, S., & Belongie, S. (2015). Learning localized perceptual similarity metrics for interactive categorization. Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015, 502-509. https://doi.org/10.1109/WACV.2015.73

Vancouver

Wah C, Maji S, Belongie S. Learning localized perceptual similarity metrics for interactive categorization. Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015. 2015 Feb 19;502-509. https://doi.org/10.1109/WACV.2015.73

Author

Wah, Catherine ; Maji, Subhransu ; Belongie, Serge. / Learning localized perceptual similarity metrics for interactive categorization. In: Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015. 2015 ; pp. 502-509.

Bibtex

@inproceedings{fb2838347f2e46d7a47dc9539135ed28,

title = "Learning localized perceptual similarity metrics for interactive categorization",

abstract = "Current similarity-based approaches to interactive fine grained categorization rely on learning metrics from holistic perceptual measurements of similarity between objects or images. However, making a single judgment of similarity at the object level can be a difficult or overwhelming task for the human user to perform. Secondly, a single general metric of similarity may not be able to adequately capture the minute differences that discriminate fine-grained categories. In this work, we propose a novel approach to interactive categorization that leverages multiple perceptual similarity metrics learned from localized and roughly aligned regions across images, reporting state-of-the-art results and outperforming methods that use a single nonlocalized similarity metric.",

author = "Catherine Wah and Subhransu Maji and Serge Belongie",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015 ; Conference date: 05-01-2015 Through 09-01-2015",

year = "2015",

month = feb,

day = "19",

doi = "10.1109/WACV.2015.73",

language = "English",

pages = "502--509",

journal = "Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015",

}

RIS

TY - GEN

T1 - Learning localized perceptual similarity metrics for interactive categorization

AU - Wah, Catherine

AU - Maji, Subhransu

AU - Belongie, Serge

PY - 2015/2/19

Y1 - 2015/2/19

N2 - Current similarity-based approaches to interactive fine grained categorization rely on learning metrics from holistic perceptual measurements of similarity between objects or images. However, making a single judgment of similarity at the object level can be a difficult or overwhelming task for the human user to perform. Secondly, a single general metric of similarity may not be able to adequately capture the minute differences that discriminate fine-grained categories. In this work, we propose a novel approach to interactive categorization that leverages multiple perceptual similarity metrics learned from localized and roughly aligned regions across images, reporting state-of-the-art results and outperforming methods that use a single nonlocalized similarity metric.

AB - Current similarity-based approaches to interactive fine grained categorization rely on learning metrics from holistic perceptual measurements of similarity between objects or images. However, making a single judgment of similarity at the object level can be a difficult or overwhelming task for the human user to perform. Secondly, a single general metric of similarity may not be able to adequately capture the minute differences that discriminate fine-grained categories. In this work, we propose a novel approach to interactive categorization that leverages multiple perceptual similarity metrics learned from localized and roughly aligned regions across images, reporting state-of-the-art results and outperforming methods that use a single nonlocalized similarity metric.

UR - http://www.scopus.com/inward/record.url?scp=84925438496&partnerID=8YFLogxK

U2 - 10.1109/WACV.2015.73

DO - 10.1109/WACV.2015.73

M3 - Conference article

AN - SCOPUS:84925438496

SP - 502

EP - 509

JO - Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015

JF - Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015

T2 - 2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015

Y2 - 5 January 2015 through 9 January 2015

ER -

ID: 301829777

Forskning