FAME: Face association through model evolution
Author
Gölge, Eren
Duygulu, Pınar
Date
2015-06Source Title
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Publisher
IEEE
Pages
43 - 49
Language
English
Type
Conference PaperItem Usage Stats
133
views
views
97
downloads
downloads
Abstract
We attack the problem of building classifiers for public faces from web images collected through querying a name. The search results are very noisy even after face detection, with several irrelevant faces corresponding to other people. Moreover, the photographs are taken in the wild with large variety in poses and expressions. We propose a novel method, Face Association through Model Evolution (FAME), that is able to prune the data in an iterative way, for the models associated to a name to evolve. The idea is based on capturing discriminative and representative properties of each instance and eliminating the outliers. The final models are used to classify faces on novel datasets with different characteristics. On benchmark datasets, our results are comparable to or better than the state-of-the-art studies for the task of face identification. © 2015 IEEE.
Keywords
AccuracyBuildings
Computational modeling
Data models
Face
Noise measurement
Training
Buildings
Classification (of information)
Data structures
Face recognition
Iterative methods
Pattern recognition
Personnel training
Accuracy
Benchmark datasets
Computational model
Face
Face identification
Model evolution
Noise measurements
State of the art
Computer vision
Permalink
http://hdl.handle.net/11693/28185Published Version (Please cite this version)
http://dx.doi.org/10.1109/CVPRW.2015.7301353Collections
Related items
Showing items related by title, author, creator and subject.
-
Interaction-based feature-driven model-transformations for generating E-forms
Tekinerdoǧan, Bedir; Aktekin, N. (ACM, 2009-10)One of the basic pillars in Model-Driven Software Development (MDSD) is defined by model transformations and likewise several useful approaches have been proposed in this context. In parallel, domain modeling plays an ... -
Influence of phase function on modeled optical response of nanoparticle-labeled epithelial tissues
Cihan, C.; Arifler, D. (2011)Metal nanoparticles can be functionalized with biomolecules to selectively localize in precancerous tissues and can act as optical contrast enhancers for reflectance-based diagnosis of epithelial precancer. We carry out ... -
Architecture framework for mapping parallel algorithms to parallel computing platforms
Tekinerdogan, Bedir; Arkin, E. (CEUR-WS, 2013)Mapping parallel algorithms to parallel computing platforms requires several activities such as the analysis of the parallel algorithm, the definition of the logical configuration of the platform, and the mapping of the ...