@inproceedings{a2a573ec6f45485ca189f4033b883f0c,
title = "News Image Captioning Based on Text Summarization Using Image as Query",
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.",
keywords = "Deep learning, Image captioning, Multi-modal summarization, Text summarization",
author = "Jingqiang Chen and Hai Zhuge",
year = "2020",
month = mar,
day = "23",
doi = "10.1109/SKG49510.2019.00029",
language = "English",
isbn = "978-1-7281-5824-2",
series = "Proceedings - 15th International Conference on Semantics, Knowledge and Grids: On Big Data, AI and Future Interconnection Environment, SKG 2019",
publisher = "IEEE",
pages = "123--126",
editor = "Hai Zhuge and Xiaoping Sun",
booktitle = "Proceedings - 15th International Conference on Semantics, Knowledge and Grids",
address = "United States",
note = "2019 15th International Conference on Semantics, Knowledge and Grids (SKG) ; Conference date: 17-09-2019 Through 18-09-2019",
}