Finding Images of Rare and Ambiguous Entities
Year: 2011
Type: article
Abstract: Despite much progress on entity-oriented Web search and automatically constructed knowledge bases with millions of entities, it is still difficult to find images of named entities like people or places. While images of famous entities are abundant on the Internet, they are much harder to retrieve for less popular entities such as notable computer scientists or regionally interesting churches. Querying the entity names in image search engines yields large candidate lists, but they often have low precision and unsatisfactory recall. In this paper, we propose a principled model for finding images of rare or ambiguous named entities. We propose a set of efficient, light-weight algorithms for identifying entity-specific keyphrases from a given textual description of the entity, which we then use to score candidate images based on the matches of keyphrases in the underlying Web pages. Our experiments with a variety of entity categories show the high precision-recall quality of
Authors: Bilyana Taneva, Mouna Kacimi, Gerhard Weikum, Mouna Kacimi
Institutions: Max Planck Society, Max Planck Institute for Informatics
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2115060050