You are in : Home » Results & submissions » Select UOA » 11 - Computer Science and Informatics » View submission: University of Edinburgh » Outputs » Detail

Output details

11 - Computer Science and Informatics

University of Edinburgh

Return to search Previous output Next output

Output 313 of 401 in the submission

Output title

Segmentation Propagation in ImageNet

Type

E - Conference contribution

DOI

10.1007/978-3-642-33786-4_34

Name of conference/published proceedings

Computer Vision - ECCV 2012 : 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part VII

Volume number

7578

Issue number

First page of article

459

ISSN of proceedings

0302-9743

Year of publication

2012

URL

http://link.springer.com/chapter/10.1007%2F978-3-642-33786-4_34

Number of additional authors

Additional information

<23> Originality: Novel procedure to recursively segment large image databases; able to segment images of object classes for which no segmented training data is available thanks to knowledge transfer from other classes.

Significance: Best paper award at ECCV 2012, selected out of 1500 submissions. ECCV is one of the top 3 international conferences in the field.

Rigour: Evaluated on 500,000 images, probably the largest image segmentation experiment to date.

Interdisciplinary

Cross-referral requested

Research group

E - Institute of Perception, Action & Behaviour

Citation count

Proposed double-weighted

Double-weighted statement

Reserve for a double-weighted output

Non-English

English abstract