CASIA OpenIR  > 模式识别实验室
Boosting end-to-end multi-object tracking and person search via knowledge distillation
Zhang, Wei; He, Lingxiao; Chen, Peng; Liao, Xingyu; Liu, Wu; Li, Qi; Sun, Zhenan
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
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
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
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhang, Wei]的文章
[He, Lingxiao]的文章
[Chen, Peng]的文章
百度学术
百度学术中相似的文章
[Zhang, Wei]的文章
[He, Lingxiao]的文章
[Chen, Peng]的文章
必应学术
必应学术中相似的文章
[Zhang, Wei]的文章
[He, Lingxiao]的文章
[Chen, Peng]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 3474085.3481546.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。