Sequence multi-labeling: a unified video annotation scheme with spatial and temporal context
文献类型：期刊论文
| 作者 | Li, Yuanning1,2; Tian, Yonghong3; Duan, Ling-Yu3; Yang, Jingjing1,2; Huang, Tiejun3; Gao, Wen3 |
| 刊名 | Ieee transactions on multimedia
 |
| 出版日期 | 2010-12-01 |
| 卷号 | 12期号:8页码:814-828 |
| 关键词 | Sequence multi-labeling Spatial correlation Temporal correlation Video annotation |
| ISSN号 | 1520-9210 |
| DOI | 10.1109/tmm.2010.2066960 |
| 通讯作者 | Li, yuanning(ynli@jdl.ac.cn) |
| 英文摘要 | Automatic video annotation is a challenging yet important problem for content-based video indexing and retrieval. in most existing works, annotation is formulated as a multi-labeling problem over individual shots. however, video is by nature informative in spatial and temporal context of semantic concepts. in this paper, we formulate video annotation as a sequence multi-labeling (sml) problem over a shot sequence. different from many video annotation paradigms working on individual shots, sml aims to predict a multi-label sequence for consecutive shots in a global optimization manner by incorporating spatial and temporal context into a unified learning framework. a novel discriminative method, called sequence multi-label support vector machine (svmsml), is accordingly proposed to infer the multi-label sequence for a given shot sequence. in (svmsml), a joint kernel is employed to model the feature-level and concept-level context relationships (i.e., the dependencies of concepts on the low-level features, spatial and temporal correlations of concepts). a multiple-kernel learning (mkl) algorithm is developed to optimize the kernel weights of the joint kernel as well as the sml score function. to efficiently search the desirable multi-label sequence over the large output space in both training and test phases, we adopt an approximate method to maximize the energy of a binary markov random field (bmrf). extensive experiments on trecvid'05 and trecvid'07 datasets have shown that our proposed (svmsml) gains superior performance over the state-of-the-art. |
| WOS关键词 | CONCEPT FUSION ; FRAMEWORK ; RETRIEVAL |
| WOS研究方向 | Computer Science ; Telecommunications |
| WOS类目 | Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications |
| 语种 | 英语 |
| WOS记录号 | WOS:000284365100004 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| URI标识 | http://www.irgrid.ac.cn/handle/1471x/2414020 |
| 专题 | 中国科学院大学 |
| 通讯作者 | Li, Yuanning |
| 作者单位 | 1.Chinese Acad Sci, Inst Comp Technol, Beijing 100080, Peoples R China 2.Chinese Acad Sci, Grad Sch, Beijing 100080, Peoples R China 3.Peking Univ, Natl Engn Lab Video Technol, Sch Elect Engn & Comp Sci, Beijing 100871, Peoples R China |
| 推荐引用方式 GB/T 7714 | Li, Yuanning,Tian, Yonghong,Duan, Ling-Yu,et al. Sequence multi-labeling: a unified video annotation scheme with spatial and temporal context[J]. Ieee transactions on multimedia,2010,12(8):814-828. |
| APA | Li, Yuanning,Tian, Yonghong,Duan, Ling-Yu,Yang, Jingjing,Huang, Tiejun,&Gao, Wen.(2010).Sequence multi-labeling: a unified video annotation scheme with spatial and temporal context.Ieee transactions on multimedia,12(8),814-828. |
| MLA | Li, Yuanning,et al."Sequence multi-labeling: a unified video annotation scheme with spatial and temporal context".Ieee transactions on multimedia 12.8(2010):814-828. |
入库方式： iSwitch采集
来源：中国科学院大学
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。