中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 多媒体计算与图形学团队
Text2Video: An End-to-end Learning Framework for Expressing Text With Videos

文献类型：期刊论文

作者Yang, Xiaoshan1,2; Zhang, Tianzhu1,2; Xu, Changsheng1,2
刊名IEEE TRANSACTIONS ON MULTIMEDIA
出版日期2018-09-01
卷号20期号:9页码:2360-2370
关键词Multimedia Storytelling Video Analysis Deep Learning
DOI10.1109/TMM.2018.2807588
文献子类Article
英文摘要Video creation is a challenging and highly professional task that generally involves substantial manual efforts. To ease this burden, a better approach is to automatically produce new videos based on clips from the massive amount of existing videos according to arbitrary text. In this paper, we formulate video creation as a problem of retrieving a sequence of videos for a sentence stream. To achieve this goal, we propose a novel multimodal recurrent architecture for automatic video production. Compared with existing methods, the proposed model has three major advantages. First, it is the first completely integrated end-to-end deep learning system for real-world production to the best of our knowledge. We are among the first to address the problem of retrieving a sequence of videos for a sentence stream. Second, it can effectively exploit the correspondence between sentences and video clips through semantic consistency modeling. Third, it can model the visual coherence well by requiring that the produced videos should be organized coherently in terms of visual appearance. We have conducted extensive experiments on two applications, including video retrieval and video composition. The qualitative and quantitative results obtained on two public datasets used in the Large Scale Movie Description Challenge 2016 both demonstrate the effectiveness of the proposed model compared with other state-of-the-art algorithms.
WOS关键词ANNOTATION ; REPRESENTATION ; NARRATIVES ; MOVIE ; WEB ; TV
WOS研究方向Computer Science ; Telecommunications
语种英语
WOS记录号WOS:000442358200010
资助机构National Natural Science Foundation of China(61432019 ; Beijing Natural Science Foundation(4172062) ; Key Research Program of Frontier Sciences, CAS(QYZDJ-SSW-JSC039) ; 61572498 ; 61532009 ; 61702511 ; 61720106006 ; 61711530243)
源URL[http://ir.ia.ac.cn/handle/173211/20467]  
专题自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
作者单位1.National Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
推荐引用方式
GB/T 7714		 Yang, Xiaoshan,Zhang, Tianzhu,Xu, Changsheng. Text2Video: An End-to-end Learning Framework for Expressing Text With Videos[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2018,20(9):2360-2370.
APA Yang, Xiaoshan,Zhang, Tianzhu,&Xu, Changsheng.(2018).Text2Video: An End-to-end Learning Framework for Expressing Text With Videos.IEEE TRANSACTIONS ON MULTIMEDIA,20(9),2360-2370.
MLA Yang, Xiaoshan,et al."Text2Video: An End-to-end Learning Framework for Expressing Text With Videos".IEEE TRANSACTIONS ON MULTIMEDIA 20.9(2018):2360-2370.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。