摘要
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.
源语言 | 英语 |
---|---|
主期刊名 | Proceedings - 2017 IEEE International Conference on Big Knowledge, ICBK 2017 |
编辑 | Ruqian Lu, Xindong Wu, Tamer Ozsu, Xindong Wu, Jim Hendler |
出版商 | Institute of Electrical and Electronics Engineers Inc. |
页 | 224-229 |
页数 | 6 |
ISBN(电子版) | 9781538631195 |
DOI | |
出版状态 | 已出版 - 30 8月 2017 |
活动 | 2017 IEEE International Conference on Big Knowledge, ICBK 2017 - Hefei, 中国 期限: 9 8月 2017 → 10 8月 2017 |
出版系列
姓名 | Proceedings - 2017 IEEE International Conference on Big Knowledge, ICBK 2017 |
---|
会议
会议 | 2017 IEEE International Conference on Big Knowledge, ICBK 2017 |
---|---|
国家/地区 | 中国 |
市 | Hefei |
时期 | 9/08/17 → 10/08/17 |
指纹
探究 'Video Captioning with Semantic Information from the Knowledge Base' 的科研主题。它们共同构成独一无二的指纹。引用此
Wang, D., & Song, D. (2017). Video Captioning with Semantic Information from the Knowledge Base. 在 R. Lu, X. Wu, T. Ozsu, X. Wu, & J. Hendler (编辑), Proceedings - 2017 IEEE International Conference on Big Knowledge, ICBK 2017 (页码 224-229). 文章 8023421 (Proceedings - 2017 IEEE International Conference on Big Knowledge, ICBK 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICBK.2017.26