Blog Article Summarization with Image-Text Alignment Techniques

Wei Ta Chu, Ming Chih Kao

研究成果: Conference contribution

1 引文 斯高帕斯(Scopus)

摘要

We propose an image-text alignment framework to match images with text, and take blog article summarization as the main application. Objects in an image are first detected, from them deep features are extracted and transformed into a space commonly shared with the text. On the other hand, sentences of a blog article are represented as vectors, and are also embedded into the common space. With these processes, cross-modal matching can be achieved. A blog article is then summarized in the representation of images and their matched sentences. In evaluation, we demonstrate the effectiveness of the proposed method, and show that the generated summary makes more sense.

原文English
主出版物標題Proceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017
發行者Institute of Electrical and Electronics Engineers Inc.
頁面244-247
頁數4
ISBN(電子)9781538629369
DOIs
出版狀態Published - 2017 十二月 28
事件19th IEEE International Symposium on Multimedia, ISM 2017 - Taichung, Taiwan
持續時間: 2017 十二月 112017 十二月 13

出版系列

名字Proceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017
2017-January

Conference

Conference19th IEEE International Symposium on Multimedia, ISM 2017
國家Taiwan
城市Taichung
期間17-12-1117-12-13

All Science Journal Classification (ASJC) codes

  • Media Technology
  • Sensory Systems

指紋 深入研究「Blog Article Summarization with Image-Text Alignment Techniques」主題。共同形成了獨特的指紋。

引用此