DocumentCode :
254361
Title :
Relative Parts: Distinctive Parts for Learning Relative Attributes
Author :
Sandeep, Ramachandruni N. ; Verma, Yashaswi ; Jawahar, C.V.
Author_Institution :
Center for Visual Inf. Technol., IIIT Hyderabad, Hyderabad, India
fYear :
2014
fDate :
23-28 June 2014
Firstpage :
3614
Lastpage :
3621
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.
Keywords :
image matching; image representation; interactive systems; learning (artificial intelligence); search problems; support vector machines; adaptive significance oefficient; annotated images; baseline method; face images; max-margin ranking model; outdoor images; part-based representation; ranking SVM based formulation; relative attribute prediction accuracy; relative feedback based interactive image search; visual properties; Face; Joints; Optimization; Support vector machines; Training; Vectors; Visualization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on
Conference_Location :
Columbus, OH
Type :
conf
DOI :
10.1109/CVPR.2014.462
Filename :
6909857
Link To Document :
بازگشت