Knowledge Commons of Institute of Automation,CAS
Do not Lose the Details: Reinforced Representation Learning for High Performance Visual Tracking | |
Wang, Qiang1,2; Zhang, Mengdan2; Xing, Junliang2; Gao, Jin2; Hu, Weiming2; Steve Maybank3 | |
2018-07 | |
会议名称 | International Joint Conference on Artificial Intelligence |
会议日期 | 2018-7 |
会议地点 | Stockholm, Sweden |
摘要 | This work presents a novel end-to-end trainable CNN model for high performance visual object tracking. It learns both low-level fine-grained representations and a high-level semantic embedding space in a mutual reinforced way, and a multi-task learning strategy is proposed to perform the correlation analysis on representations from both levels. In particular, a fully convolutional encoderdecoder network is designed to reconstruct the original visual features from the semantic projections to preserve all the geometric information. Moreover, the correlation filter layer working on the finegrained representations leverages a global context constraint for accurate object appearance modeling. The correlation filter in this layer is updated online efficiently without network fine-tuning. Therefore, the proposed tracker benefits from two complementary effects: the adaptability of the fine-grained correlation analysis and the generalization capability of the semantic embedding. Extensive experimental evaluations on four popular benchmarks demonstrate its state-of-the-art performance. |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39071 |
专题 | 多模态人工智能系统全国重点实验室_视频内容安全 中国科学院自动化研究所 |
作者单位 | 1.University of Chinese Academy of Sciences 2.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 3.Department of Computer Science and Information Systems, Birkbeck College, University of London |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Wang, Qiang,Zhang, Mengdan,Xing, Junliang,et al. Do not Lose the Details: Reinforced Representation Learning for High Performance Visual Tracking[C],2018. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
王强_IJCAI2018.pdf(860KB) | 会议论文 | 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