@inproceedings{989d9815cece4a5daba1c9fe8f1b0564,
title = "Video Captioning with Semantic Information from the Knowledge Base",
abstract = "Generating video description is a very challenging task due to the complex spatiotemporal information. Recently, many methods have been proposed by utilizing LSTM to generate sentence for video. Inspired by recent work in machine translation and object detection, we propose a new approach for video captioning which aims to incorporate Knowledge Base information with frame features of the video. We compare and analyze our approach with prior work and show that the large volumes information is available to generate video description. We experiment with our ideas on the S2VT model, and we demonstrate that our method outperforms the state-of-the-art on video captioning benchmarks.",
keywords = "Video description, knowledge base, object detection",
author = "Dan Wang and Dandan Song",
note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 8th IEEE International Conference on Big Knowledge, ICBK 2017 ; Conference date: 09-08-2017 Through 10-08-2017",
year = "2017",
month = aug,
day = "30",
doi = "10.1109/ICBK.2017.26",
language = "English",
series = "Proceedings - 2017 IEEE International Conference on Big Knowledge, ICBK 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "224--229",
editor = "Xindong Wu and Xindong Wu and Tamer Ozsu and Jim Hendler and Ruqian Lu",
booktitle = "Proceedings - 2017 IEEE International Conference on Big Knowledge, ICBK 2017",
address = "United States",
}