Knowledge Commons of Institute of Automation,CAS
Context-Aware Video Retargeting via Graph Model | |
Qu, Zhan1; Wang, Jinqiao1![]() ![]() ![]() | |
发表期刊 | IEEE TRANSACTIONS ON MULTIMEDIA
![]() |
2013-11-01 | |
卷号 | 15期号:7页码:1677-1687 |
文章类型 | Article |
摘要 | Video retargeting is a crowded but challenging research area. In order to maximally comfort the viewers' watching experience, the most challenging issue is how to retain the spatial shape of important objects while ensure temporal smoothness and coherence. Existing retargeting techniques deal with these spatial-temporal requirements individually, which preserve the spatial geometry and temporal coherence for each region. However, the spatial-temporal property of the video content should be context-relevant, i.e., the regions belonging to the same object are supposed to undergo uniform spatial-temporal transformation. Regardless of the contextual information, the divide-and-rule strategy of existing techniques usually incurs various spatial-temporal artifacts. In order to achieve satisfactory spatial-temporal coherent video retargeting, in this paper, a novel context-aware solution is proposed via graph model. First, we employ a grid-based warping framework to preserve the spatial structure and temporal motion trend at the unit of grid cell. Second, we propose a graph-based motion layer partition algorithm to estimate motions of different regions, which simultaneously provides the evaluation of contextual relationship between grid cells while estimating the motions of regions. Third, complementing the salience-based spatial-temporal information preservation, two novel context constraints are encoded for encouraging the grid cells of the same object to undergo uniform spatial and temporal transformation, respectively. Finally, we formulate the objective function as a quadratic programming problem. Our method achieves a satisfactory spatial-temporal coherence while maximally avoiding the influence of artifacts. In addition, the grid-cell-wise motion estimation could be calculated every few frames, which obviously improves the speed. Experimental results and comparisons with state-of-the-art methods demonstrate the effectiveness and efficiency of our approach. |
关键词 | Context-aware Grid Graph Model Spatial-temporal Correlation Video Retargeting |
WOS标题词 | Science & Technology ; Technology |
DOI | 10.1109/TMM.2013.2267727 |
关键词[WOS] | ENERGY MINIMIZATION |
收录类别 | SCI |
语种 | 英语 |
WOS研究方向 | Computer Science ; Telecommunications |
WOS类目 | Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications |
WOS记录号 | WOS:000325811800018 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/3348 |
专题 | 紫东太初大模型研究中心_图像与视频分析 |
通讯作者 | Wang, Jinqiao |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Technol Sydney, Sch Comp & Commun, INEXT, Sydney, NSW 2007, Australia |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Qu, Zhan,Wang, Jinqiao,Xu, Min,et al. Context-Aware Video Retargeting via Graph Model[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2013,15(7):1677-1687. |
APA | Qu, Zhan,Wang, Jinqiao,Xu, Min,&Lu, Hanqing.(2013).Context-Aware Video Retargeting via Graph Model.IEEE TRANSACTIONS ON MULTIMEDIA,15(7),1677-1687. |
MLA | Qu, Zhan,et al."Context-Aware Video Retargeting via Graph Model".IEEE TRANSACTIONS ON MULTIMEDIA 15.7(2013):1677-1687. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Context-Aware Video (1846KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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