Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/107959
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Less is more: zero-shot learning from online textual documents with noise suppression |
Author: | Qiao, R. Liu, L. Shen, C. van den Hengel, A. |
Citation: | Proceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016, vol.2016-December, pp.2249-2257 |
Publisher: | IEEE |
Issue Date: | 2016 |
Series/Report no.: | IEEE Conference on Computer Vision and Pattern Recognition |
ISBN: | 9781467388511 |
ISSN: | 1063-6919 |
Conference Name: | 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2016) (26 Jun 2016 - 1 Jul 2016 : Las Vegas, NV) |
Statement of Responsibility: | Ruizhi Qiao, Lingqiao Liu, Chunhua Shen, Anton van den Hengel |
Abstract: | Classifying a visual concept merely from its associated online textual source, such as a Wikipedia article, is an attractive research topic in zero-shot learning because it alleviates the burden of manually collecting semantic attributes. Recent work has pursued this approach by exploring various ways of connecting the visual and text domains. In this paper, we revisit this idea by going further to consider one important factor: the textual representation is usually too noisy for the zero-shot learning application. This observation motivates us to design a simple yet effective zero-shot learning method that is capable of suppressing noise in the text. Specifically, we propose an l2,1-norm based objective function which can simultaneously suppress the noisy signal in the text and learn a function to match the text document and visual features. We also develop an optimization algorithm to efficiently solve the resulting problem. By conducting experiments on two large datasets, we demonstrate that the proposed method significantly outperforms those competing methods which rely on online information sources but with no explicit noise suppression. Furthermore, we make an in-depth analysis of the proposed method and provide insight as to what kind of information in documents is useful for zero-shot learning. |
Keywords: | Semantics, noise measurement, visualization, internet, linear programming, encyclopedias |
Rights: | © 2016 IEEE |
DOI: | 10.1109/CVPR.2016.247 |
Published version: | http://dx.doi.org/10.1109/cvpr.2016.247 |
Appears in Collections: | Aurora harvest 8 Computer Science publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
RA_hdl_107959.pdf Restricted Access | Restricted Access | 1.06 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.