News Image Captioning Based on Text Summarization Using Image as Query

Jingqiang Chen, Hai Zhuge

    Research output: Chapter in Book/Published conference outputConference publication

    Abstract

    News image captioning aims to generate captions or descriptions for news images automatically, serving as draft captions for creating news image captions manually. News image captions contain more detailed information such as entity names and events than generic image captions do. Detailed information is usually contained in news text but not in news images. Generic image captioning does not make full use of the accompanying news text to generate image captions. This paper proposes a news image captioning method based on the attentional encoder-decoder model through summarizing the news text according to query image. The multi-modal attentional mechanism is proposed to compute the context vector. The proposed model is trained on the DailyMail news image captioning corpora which are created by collecting images, caption, news texts through parsing the html-formatted documents. Experiments on the DailyMail test dataset show that the proposed method outperforms the generic image captioning and the text summarization method.
    Original languageEnglish
    Title of host publicationProceedings - 15th International Conference on Semantics, Knowledge and Grids
    Subtitle of host publicationOn Big Data, AI and Future Interconnection Environment, SKG 2019
    EditorsHai Zhuge, Xiaoping Sun
    PublisherIEEE
    Pages123-126
    Number of pages4
    ISBN (Electronic)978-1-7281-5823-5
    ISBN (Print)978-1-7281-5824-2
    DOIs
    Publication statusPublished - 23 Mar 2020
    Event2019 15th International Conference on Semantics, Knowledge and Grids (SKG) - Guangzhou, China
    Duration: 17 Sept 201918 Sept 2019

    Publication series

    NameProceedings - 15th International Conference on Semantics, Knowledge and Grids: On Big Data, AI and Future Interconnection Environment, SKG 2019

    Conference

    Conference2019 15th International Conference on Semantics, Knowledge and Grids (SKG)
    Period17/09/1918/09/19

    Keywords

    • Deep learning
    • Image captioning
    • Multi-modal summarization
    • Text summarization

    Fingerprint

    Dive into the research topics of 'News Image Captioning Based on Text Summarization Using Image as Query'. Together they form a unique fingerprint.

    Cite this