Boosting end-to-end multi-object tracking and person search via knowledge distillation | |
Zhang, Wei![]() ![]() ![]() ![]() ![]() | |
2021-10 | |
会议名称 | ACM International Conference on Multimedia |
会议日期 | 2021-10 |
会议地点 | China |
摘要 | Multi-Object Tracking (MOT) and Person Search both demand to localize and identify specific targets from raw image frames. Existing methods can be classified into two categories, namely two-step strategy and end-to-end strategy. Two-step approaches have high accuracy but suffer from costly computations, while end-to-end methods show greater efficiency with limited performance. In this paper, we dissect the gap between two-step and end-to-end strategy and propose a simple yet effective end-to-end framework with knowledge distillation. Our proposed framework is simple in concept and easy to benefit from external datasets. Experimental results demonstrate that our model performs competitively with other sophisticated two-step and end-to-end methods in multi-object tracking and person search. |
是否为代表性论文 | 否 |
七大方向——子方向分类 | 生物特征识别 |
国重实验室规划方向分类 | 视觉信息处理 |
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/173211/55262 |
专题 | 模式识别实验室 |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.JD AI Research |
推荐引用方式 GB/T 7714 | Zhang, Wei,He, Lingxiao,Chen, Peng,et al. Boosting end-to-end multi-object tracking and person search via knowledge distillation[C],2021. |
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 | ||
3474085.3481546.pdf(3267KB) | 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