Unsupervised Object-Level Video Summarization with Online Motion Auto-Encoder | |
Yujia Zhang1,2![]() ![]() | |
刊名 | Pattern Recognition Letters
![]() |
2018-07 | |
期号 | 无页码:无 |
关键词 | Object-level Video Summarization Online Motion Auto-encoder Stacked Sparse Lstm Auto-encoder |
英文摘要 | Unsupervised video summarization plays an important role on digesting, browsing, and searching the ever-growing videos every day, and the underlying fine-grained semantic and motion information (i.e., objects of interest and their key motions) in online videos has been barely touched. In this paper, we investigate a pioneer research direction towards the fine-grained unsupervised object-level video summarization. It can be distinguished from existing pipelines in two aspects: extracting key motions of articipated objects, and learning to summarize in an unsupervised and online manner. To achieve this goal, we propose a novel online motion Auto-Encoder (online motion-AE) framework that functions on the super-segmented object motion clips. Comprehensive experiments on a newly-collected surveillance dataset and public datasets have demonstrated the effectiveness of our proposed method. |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/23648] ![]() |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进机器人控制团队 |
通讯作者 | Yujia Zhang |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.Carnegie Mellon University 4.Xidian University |
推荐引用方式 GB/T 7714 | Yujia Zhang,Xiaodan Liang,Dingwen Zhang,et al. Unsupervised Object-Level Video Summarization with Online Motion Auto-Encoder[J]. Pattern Recognition Letters,2018(无):无. |
APA | Yujia Zhang,Xiaodan Liang,Dingwen Zhang,Min Tan,&Eric P. Xing.(2018).Unsupervised Object-Level Video Summarization with Online Motion Auto-Encoder.Pattern Recognition Letters(无),无. |
MLA | Yujia Zhang,et al."Unsupervised Object-Level Video Summarization with Online Motion Auto-Encoder".Pattern Recognition Letters .无(2018):无. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论