MISC

2016年8月

Large Scale Retrieval and Generation of Image Descriptions

INTERNATIONAL JOURNAL OF COMPUTER VISION
  • Vicente Ordonez
  • ,
  • Xufeng Han
  • ,
  • Polina Kuznetsova
  • ,
  • Girish Kulkarni
  • ,
  • Margaret Mitchell
  • ,
  • Kota Yamaguchi
  • ,
  • Karl Stratos
  • ,
  • Amit Goyal
  • ,
  • Jesse Dodge
  • ,
  • Alyssa Mensch
  • ,
  • Hal Daume
  • ,
  • Alexander C. Berg
  • ,
  • Yejin Choi
  • ,
  • Tamara L. Berg

119
1
開始ページ
46
終了ページ
59
記述言語
英語
掲載種別
DOI
10.1007/s11263-015-0840-y
出版者・発行元
SPRINGER

What is the story of an image? What is the relationship between pictures, language, and information we can extract using state of the art computational recognition systems? In an attempt to address both of these questions, we explore methods for retrieving and generating natural language descriptions for images. Ideally, we would like our generated textual descriptions (captions) to both sound like a person wrote them, and also remain true to the image content. To do this we develop data-driven approaches for image description generation, using retrieval-based techniques to gather either: (a) whole captions associated with a visually similar image, or (b) relevant bits of text (phrases) from a large collection of image + description pairs. In the case of (b), we develop optimization algorithms to merge the retrieved phrases into valid natural language sentences. The end result is two simple, but effective, methods for harnessing the power of big data to produce image captions that are altogether more general, relevant, and human-like than previous attempts.

Web of Science ® 被引用回数 : 35

リンク情報
DOI
https://doi.org/10.1007/s11263-015-0840-y
Web of Science
https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=JSTA_CEL&SrcApp=J_Gate_JST&DestLinkType=FullRecord&KeyUT=WOS:000378789400004&DestApp=WOS_CPL
URL
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84936796885&origin=inward
ID情報
  • DOI : 10.1007/s11263-015-0840-y
  • ISSN : 0920-5691
  • eISSN : 1573-1405
  • SCOPUS ID : 84936796885
  • Web of Science ID : WOS:000378789400004

エクスポート
BibTeX RIS