Learning Temporally Correlated Representations Using Lstms for Visual Tracking
文献类型：会议论文
| 作者 | Qiaozhe Li ; Xin Zhao; Kaiqi Huang
|
| 出版日期 | 2016 |
| 会议日期 | 2016-09-01 |
| 会议地点 | Phoenix, USA |
| 关键词 | Long Short Term Memory Structured Svm Temporally Correlated Feature Learning visual Tracking |
| 页码 | 2381-8549 |
| 英文摘要 | In this paper, we propose to learn object representations with inference from temporal correlation in videos to achieve effective visual tracking. Unlike traditional methods which perform feature learning either at image level or based on intuitive temporal constraint, we employ the recurrent network with Long Short Term Memory (LSTM) units to directly learn temporally correlated representations of the objects in long sequences. The recurrent network is pre-trained offline with auxiliary data and then online optimized to adapt to the target-specific object. A structured SVM is employed to account for the temporally correlated object appearance as well as distinguish the object from background distraction. Experiment results not only show that the appearance and dynamic patterns of the objects can be characterized via temporally correlated feature learning, but also demonstrate that the proposed tracking algorithm performs favorably against the state-of-the-art methods. |
| 会议录 | Image Processing (ICIP), 2016 IEEE International Conference on
 |
| 语种 | 英语 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/12676]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | Kaiqi Huang |
| 作者单位 | 中国科学院自动化研究所 |
| 推荐引用方式 GB/T 7714 | Qiaozhe Li,Xin Zhao,Kaiqi Huang. Learning Temporally Correlated Representations Using Lstms for Visual Tracking[C]. 见:. Phoenix, USA. 2016-09-01. |
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。