Online discriminative dictionary learning via label information for multi task object tracking
文献类型：会议论文
| 作者 | Fan BJ(范保杰); Du YK(杜英魁); Gao, Hao; Wang, Baoyun |
| 出版日期 | 2014 |
| 会议名称 | 2014 IEEE International Conference on Multimedia and Expo, ICME 2014 |
| 会议日期 | July 14-18, 2014 |
| 会议地点 | Chengdu, China |
| 关键词 | label information discriminative dictionary learning multi task learning object tracking |
| 页码 | 1-6 |
| 中文摘要 | In this paper, a supervised approach to online learn a structured sparse and discriminative representation for object tracking is presented. Label information from training data is incorporated into the dictionary learning process to construct a compact and discriminative dictionary. This is accomplished by adding an ideal-code regularization term and classification error term to the total objective function. By minimizing the total objective function, we learn the high quality dictionary and optimal linear multi-classifier simultaneously. Combined with multi task sparse learning, the learned classifier is employed directly to separate the object from background. As the tracking continues, the proposed algorithm alternates between multi task sparse coding and dictionary updating. Experimental evaluations on the challenging sequences show that the proposed algorithm performs favorably against state-of-the-art methods in terms of effectiveness, accuracy and robustness. |
| 收录类别 | EI ; CPCI（ISTP） |
| 产权排序 | 2 |
| 会议主办者 | Baidu; BOCOM; et al.; NSF; NSFC; QIY |
| 会议录 | Proceedings - IEEE International Conference on Multimedia and Expo
 |
| 会议录出版者 | IEEE Computer Society |
| 会议录出版地 | Washington, DC |
| 语种 | 英语 |
| ISSN号 | 1945-7871 |
| ISBN号 | 978-1-4799-4761-4 |
| WOS记录号 | WOS:000360831800126 |
| 源URL | [http://ir.sia.cn/handle/173321/16816]  |
| 专题 | 沈阳自动化研究所_机器人学研究室 |
| 推荐引用方式 GB/T 7714 | Fan BJ,Du YK,Gao, Hao,et al. Online discriminative dictionary learning via label information for multi task object tracking[C]. 见:2014 IEEE International Conference on Multimedia and Expo, ICME 2014. Chengdu, China. July 14-18, 2014. |
入库方式： OAI收割
来源：沈阳自动化研究所
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。