Visually interpreting names as demographic attributes by exploiting click-through data
Journal
National Conference on Artificial Intelligence
Journal Volume
1
Pages
44-50
ISBN
9781577356998
Date Issued
2015
Author(s)
Abstract
Name of an identity is strongly influenced by his/her cultural background such as gender and ethnicity, both vital attributes for user profiling, attribute-based retrieval, etc. Typically, the associations between names and attributes (e.g., people named "Amy" are mostly females) are annotated manually or provided by the census data of governments. We propose to associate a name and its likely demographic attributes by exploiting click-throughs between name queries and images with automatically detected facial attributes. This is the first work attempting to translate an abstract name to demographic attributes in visual-data-driven manner, and it is adaptive to incremental data, more countries and even unseen names (the names out of click-through data) without additional manual labels. In the experiments, the automatic name-attribute associations can help gender inference with competitive accuracy by using manual labeling. It also benefits profiling social media users and keyword-based face image retrieval, especially for contributing 12% relative improvement of accuracy in adapting to unseen names. Copyright ? 2015, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Type
conference paper