Multiclass recognition and part localization with humans in the loop

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt

Standard

Multiclass recognition and part localization with humans in the loop. / Wah, Catherine; Branson, Steve; Perona, Pietro; Belongie, Serge.

I: Proceedings of the IEEE International Conference on Computer Vision, 2011, s. 2524-2531.

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt

Harvard

Wah, C, Branson, S, Perona, P & Belongie, S 2011, 'Multiclass recognition and part localization with humans in the loop', Proceedings of the IEEE International Conference on Computer Vision, s. 2524-2531. https://doi.org/10.1109/ICCV.2011.6126539

APA

Wah, C., Branson, S., Perona, P., & Belongie, S. (2011). Multiclass recognition and part localization with humans in the loop. Proceedings of the IEEE International Conference on Computer Vision, 2524-2531. https://doi.org/10.1109/ICCV.2011.6126539

Vancouver

Wah C, Branson S, Perona P, Belongie S. Multiclass recognition and part localization with humans in the loop. Proceedings of the IEEE International Conference on Computer Vision. 2011;2524-2531. https://doi.org/10.1109/ICCV.2011.6126539

Author

Wah, Catherine ; Branson, Steve ; Perona, Pietro ; Belongie, Serge. / Multiclass recognition and part localization with humans in the loop. I: Proceedings of the IEEE International Conference on Computer Vision. 2011 ; s. 2524-2531.

Bibtex

@inproceedings{ec8f25e8532b439abb20184a8a8034c8,
title = "Multiclass recognition and part localization with humans in the loop",
abstract = "We propose a visual recognition system that is designed for fine-grained visual categorization. The system is composed of a machine and a human user. The user, who is unable to carry out the recognition task by himself, is interactively asked to provide two heterogeneous forms of information: clicking on object parts and answering binary questions. The machine intelligently selects the most informative question to pose to the user in order to identify the object's class as quickly as possible. By leveraging computer vision and analyzing the user responses, the overall amount of human effort required, measured in seconds, is minimized. We demonstrate promising results on a challenging dataset of uncropped images, achieving a significant average reduction in human effort over previous methods.",
author = "Catherine Wah and Steve Branson and Pietro Perona and Serge Belongie",
year = "2011",
doi = "10.1109/ICCV.2011.6126539",
language = "English",
pages = "2524--2531",
journal = "Proceedings of the IEEE International Conference on Computer Vision",
note = "2011 IEEE International Conference on Computer Vision, ICCV 2011 ; Conference date: 06-11-2011 Through 13-11-2011",

}

RIS

TY - GEN

T1 - Multiclass recognition and part localization with humans in the loop

AU - Wah, Catherine

AU - Branson, Steve

AU - Perona, Pietro

AU - Belongie, Serge

PY - 2011

Y1 - 2011

N2 - We propose a visual recognition system that is designed for fine-grained visual categorization. The system is composed of a machine and a human user. The user, who is unable to carry out the recognition task by himself, is interactively asked to provide two heterogeneous forms of information: clicking on object parts and answering binary questions. The machine intelligently selects the most informative question to pose to the user in order to identify the object's class as quickly as possible. By leveraging computer vision and analyzing the user responses, the overall amount of human effort required, measured in seconds, is minimized. We demonstrate promising results on a challenging dataset of uncropped images, achieving a significant average reduction in human effort over previous methods.

AB - We propose a visual recognition system that is designed for fine-grained visual categorization. The system is composed of a machine and a human user. The user, who is unable to carry out the recognition task by himself, is interactively asked to provide two heterogeneous forms of information: clicking on object parts and answering binary questions. The machine intelligently selects the most informative question to pose to the user in order to identify the object's class as quickly as possible. By leveraging computer vision and analyzing the user responses, the overall amount of human effort required, measured in seconds, is minimized. We demonstrate promising results on a challenging dataset of uncropped images, achieving a significant average reduction in human effort over previous methods.

UR - http://www.scopus.com/inward/record.url?scp=84856635994&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2011.6126539

DO - 10.1109/ICCV.2011.6126539

M3 - Conference article

AN - SCOPUS:84856635994

SP - 2524

EP - 2531

JO - Proceedings of the IEEE International Conference on Computer Vision

JF - Proceedings of the IEEE International Conference on Computer Vision

T2 - 2011 IEEE International Conference on Computer Vision, ICCV 2011

Y2 - 6 November 2011 through 13 November 2011

ER -

ID: 301830771