Spectral Feature Transformation for Person Re-Identification | |
Luo CC(罗传琛)1,3![]() ![]() ![]() | |
2019-10 | |
会议名称 | IEEE International Conference on Computer Vision (ICCV) |
会议日期 | 2019-10-27 |
会议地点 | 韩国首尔 |
摘要 | With the surge of deep learning techniques, the field of person re-identification has witnessed rapid progress in recent years. Deep learning based methods focus on learning a discriminative feature space where data points are clustered compactly according to their corresponding identities. Most existing methods process data points individually or only involves a fraction of samples while building a similarity structure. They ignore dense informative connections among samples more or less. The lack of holistic observation eventually leads to inferior performance. To relieve the issue, we propose to formulate the whole data batch as a similarity graph. Inspired by spectral clustering, a novel module termed Spectral Feature Transformation is developed to facilitate the optimization of group-wise similarities. It adds no burden to the inference and can be applied to various scenarios. As a natural extension, we further derive a lightweight re-ranking method named Local Blurring Re-ranking which makes the underlying clustering structure around the probe set more compact. Empirical studies on four public benchmarks show the superiority of the proposed method. |
收录类别 | EI |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
国重实验室规划方向分类 | 多模态协同认知 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51899 |
专题 | 模式识别实验室 |
通讯作者 | Wang NY(王乃岩) |
作者单位 | 1.University of Chinese Academy of Sciences 2.TuSimple 3.Center for Research on Intelligent Perception and Computing, CASIA 4.Center for Excellence in Brain Science and Intelligence Technology, CAS |
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 | Luo CC,Chen YT,Wang NY,et al. Spectral Feature Transformation for Person Re-Identification[C],2019. |
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 | ||
Luo_Spectral_Feature(912KB) | 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