<link rel="stylesheet" href="styles.f3b1fba60ec7970c.css">

Publication:
Identifying visual attributes for object recognition from text and taxonomy

Loading...
Thumbnail Image

Departments

Item type:Organizational Unit,

School / College / Institute

Item type:Organizational Unit,

Program

Organization Authors

Co-Authors

Tırkaz, Çağlar

Eisenstein, Jacob

Yanıkoğlu, Berrin

Date

Language

Embargo Status

N/A

Journal Title

Journal ISSN

Volume Title

Alternative Title

Abstract

Attributes of objects such as "square", "metallic", and "red" allow a way for humans to explain or discriminate object categories. These attributes also provide a useful intermediate representation for object recognition, including support for zero-shot learning from textual descriptions of object appearance. However, manual selection of relevant attributes among thousands of potential candidates is labor intensive. Hence, there is increasing interest in mining attributes for object recognition. In this paper, we introduce two novel techniques for nominating attributes and a method for assessing the suitability of candidate attributes for object recognition. The first technique for attribute nomination estimates attribute qualities based on their ability to discriminate objects at multiple levels of the taxonomy. The second technique leverages the linguistic concept of distributional similarity to further refine the estimated qualities. Attribute nomination is followed by our attribute assessment procedure, which assesses the quality of the candidate attributes based on their performance in object recognition. Our evaluations demonstrate that both taxonomy and distributional similarity serve as useful sources of information for attribute nomination, and our methods can effectively exploit them. We use the mined attributes in supervised and zero-shot learning settings to show the utility of the selected attributes in object recognition. Our experimental results show that in the supervised case we can improve on a state of the art classifier while in the zero-shot scenario we make accurate predictions outperforming previous automated techniques.

Source

Publisher

Academic Press

Citation

item.page.haspartof

Source

Computer Vision and Image Understanding

item.page.ispartofseries

item.page.edition

DOI

10.1016/j.cviu.2015.02.006

item.page.datauri

item.page.link

Rights

N/A

Copyrights Note

Rights and licensing

N/A

Endorsement

Review

Supplemented By

Referenced By

Related Patent

Related Goal

Item type:Goal, Access status: Open Access ,
16 - Peace, Justice and Strong Institutions
Compassion and a strong moral compass is essential to every democratic society.Yet, persecution, injustice and abuse still runs rampant and is tearing at the very fabric of civilization. We must ensure that we have strong institutions, global standards of justice, and a commitment to peace everywhere.
Google Scholar
Scholar'da Ara ↗
Altmetric
Dimensions
PlumX Metrikleri
BIP! Indicators