Paper reading:Multiple People Tracking by Lifted Multicut and Person Re-identification
论文地址：http://openaccess.thecvf.com/content_cvpr_2017/papers/Tang_Multiple_People_Tracking_CVPR_2017_paper.pdf 摘要 通过行人重识别策略我们能重新找到他的位置即使在局部位置失去跟踪目标。在长距离跟踪上，相似度高的行人有可能不是同一目标。本文提出一种新颖的基于图的构想：通过求解最小代价的提升mu
相关文章
- 1. CVPR 2017 Multiple People Tracking by Lifted Multicut and Person Re-identification 阅读笔记
- 2. 论文阅读Multiple People Tracking by Lifted Multicut and Person Re-identification
- 3. Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-identificat...
- 4. User and People
- 5. [paper] Look Into Person
- 6. 《Extending IOU Based Multi-Object Tracking by Visual Information》
- 7. Improving Person Re-identification by Attribute and Identity Learning
- 8. CVPR2017 all paper list
- 9. Tracking-by-detecion/learning(1): My beginning
- 10. 【Person Re-ID】Person Re-identification: Past, Present and Future
- 更多相关文章...
- • SQLite Indexed By - SQLite教程
- • SQLite Group By - SQLite教程
- • RxJava操作符（七）Conditional and Boolean
- • Java 8 Stream 教程
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
最新文章
欢迎关注本站公众号,获取更多信息
相关文章
- 1. CVPR 2017 Multiple People Tracking by Lifted Multicut and Person Re-identification 阅读笔记
- 2. 论文阅读Multiple People Tracking by Lifted Multicut and Person Re-identification
- 3. Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-identificat...
- 4. User and People
- 5. [paper] Look Into Person
- 6. 《Extending IOU Based Multi-Object Tracking by Visual Information》
- 7. Improving Person Re-identification by Attribute and Identity Learning
- 8. CVPR2017 all paper list
- 9. Tracking-by-detecion/learning(1): My beginning
- 10. 【Person Re-ID】Person Re-identification: Past, Present and Future