Access Restriction

Author Sandeep, R.N. ♦ Verma, Y. ♦ Jawahar, C.V.
Source IEEE Xplore Digital Library
Content type Text
Publisher Institute of Electrical and Electronics Engineers, Inc. (IEEE)
File Format PDF
Copyright Year ©2014
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Joints ♦ Support vector machines ♦ Face ♦ Visualization ♦ Vectors ♦ Training ♦ Optimization
Abstract The notion of relative attributes as introduced by Parikh and Grauman (ICCV, 2011) provides an appealing way of comparing two images based on their visual properties (or attributes) such as "smiling" for face images, "naturalness" for outdoor images, etc. For learning such attributes, a Ranking SVM based formulation was proposed that uses globally represented pairs of annotated images. In this paper, we extend this idea towards learning relative attributes using local parts that are shared across categories. First, instead of using a global representation, we introduce a part-based representation combining a pair of images that specifically compares corresponding parts. Then, with each part we associate a locally adaptive "significance-coefficient" that represents its discriminative ability with respect to a particular attribute. For each attribute, the significance-coefficients are learned simultaneously with a max-margin ranking model in an iterative manner. Compared to the baseline method, the new method is shown to achieve significant improvement in relative attribute prediction accuracy. Additionally, it is also shown to improve relative feedback based interactive image search.
Description Author affiliation: Center for Visual Inf. Technol., IIIT Hyderabad, Hyderabad, India (Sandeep, R.N.; Verma, Y.; Jawahar, C.V.)
ISBN 9781479951185
ISSN 10636919
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research ♦ Reading
Education Level UG and PG
Learning Resource Type Article
Publisher Date 2014-06-23
Publisher Place USA
Rights Holder Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Size (in Bytes) 1.47 MB
Page Count 8
Starting Page 3614
Ending Page 3621

Source: IEEE Xplore Digital Library