Knowledge Commons of Institute of Automation,CAS
Cascade Attention Network For Person Re-Identification | |
Guo Haiyun1; Wu Huiyao2; Zhao Chaoyang1; Zhang Huichen3; Wang Jinqiao1; Lu Hanqing1 | |
2019-09 | |
会议名称 | IEEE International Conference on Image Processing |
页码 | 2264-2268 |
会议日期 | 2019-9 |
会议地点 | Taipei, TAIWAN |
出版地 | 345 E 47TH ST, NEW YORK, NY 10017 USA |
出版者 | IEEE |
摘要 | Person re-identification is a challenging task due to the view-point, illumination and pose variations. Recent works focus on extracting part-level features to offer beneficial fine-grained information. However, the part misalignment as well as the multi-stage training process limits their performance. Inspired by the human visual attention mechanism, this paper builds a cascade attention network(CAN) to learn the discriminative person features in a coarse-to-fine manner. Firstly, we employ the human semantic parsing module to generate coarse-grained part-level attention, which corresponds to the division of human body parts and can effectively filter the background noise. Then, to extract the local detailed features within each part, we introduce spatial-channel attention module to generate fine-grained pixel-level attention, which can further highlight the distinctive characteristics and repress the irrelevant ones. Finally, we can obtain an efficient person feature descriptor by combining both the global and local features. The whole learning process is conducted end-to-end. Experimental results show that the proposed method not only considerably outperforms its counter part but also achieves competitive performance on Market-1501 and DukeMTMC. |
关键词 | cascade attention network human parsing spatial-channel attention module person re-identification |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 图像视频处理与分析 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/40570 |
专题 | 紫东太初大模型研究中心_图像与视频分析 |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences 2.Beijing Institute of Technology 3.Key Laboratory of Ministry of Public Security for Road Traffic Safety |
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 | Guo Haiyun,Wu Huiyao,Zhao Chaoyang,et al. Cascade Attention Network For Person Re-Identification[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2019:2264-2268. |
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 | ||
cascade attention ne(487KB) | 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