Difference between revisions of "Experiments on Visual Information Extraction with the Faces of Wikipedia"
(+ embed code) |
Bernadette (talk | contribs) (Category) |
||
| Line 31: | Line 31: | ||
</nowiki> | </nowiki> | ||
</code> | </code> | ||
| + | |||
| + | |||
| + | |||
| + | [[Category:Scientific works]] | ||
Latest revision as of 06:01, 31 March 2021
Authors | Md. Kamrul Hasan Chris Pal |
|---|---|
Publication date | 2014 |
Links | Original |
Experiments on Visual Information Extraction with the Faces of Wikipedia - scientific work related to Wikipedia quality published in 2014, written by Md. Kamrul Hasan and Chris Pal.
Overview
Authors present a series of visual information extraction experiments using the Faces of Wikipedia database - a new resource that authors release into the public domain for both recognition and extraction research containing over 50,000 identities and 60,000 disambiguated images of faces. Authors compare different techniques for automatically extracting the faces corresponding to the subject of a Wikipedia biography within the images appearing on the page. Authors top performing approach is based on probabilistic graphical models and uses the text of Wikipedia pages, similarities of faces as well as various other features of the document, meta-data and image files. Authors method resolves the problem jointly for all detected faces on a page. While experiments focus on extracting faces from Wikipedia biographies, approach is easily adapted to other types of documents and multiple documents. Authors focus on Wikipedia because the content is a Creative Commons resource and authors provide database to the community including registered faces, hand labeled and automated disambiguations, processed captions, meta data and evaluation protocols. Authors best probabilistic extraction pipeline yields an expected average accuracy of 77% compared to image only and text only baselines which yield 63% and 66% respectively.
Embed
Wikipedia Quality
Hasan, Md. Kamrul; Pal, Chris. (2014). "[[Experiments on Visual Information Extraction with the Faces of Wikipedia]]". AAAI Press.
English Wikipedia
{{cite journal |last1=Hasan |first1=Md. Kamrul |last2=Pal |first2=Chris |title=Experiments on Visual Information Extraction with the Faces of Wikipedia |date=2014 |url=https://wikipediaquality.com/wiki/Experiments_on_Visual_Information_Extraction_with_the_Faces_of_Wikipedia |journal=AAAI Press}}
HTML
Hasan, Md. Kamrul; Pal, Chris. (2014). "<a href="https://wikipediaquality.com/wiki/Experiments_on_Visual_Information_Extraction_with_the_Faces_of_Wikipedia">Experiments on Visual Information Extraction with the Faces of Wikipedia</a>". AAAI Press.
