- 博客(6)
- 收藏
- 关注
原创 Re-ID: Learning Deep Feature Representation with Domain Guided Dropout for Person Re-identifiation
刚刚看完这篇论文,整理了一下思路。这篇论文基于神经元在学习不同特征时活跃程度不同而提出DGD的方法,也是666的论文:https://arxiv.org/abs/1604.07528 代码:https://github.com/Cysu/dgd_person_reid论文解析文章一开始,作者解释了为什么要使用多个数据集进行训练: Learning generic and robust feat
2017-11-19 12:12:49 603
原创 Leetcode: 43.Multiply Strings(Week11, Medium)
注:本题使用的是高精度乘法的思路 Leetcode 43 Given two non-negative integers num1 and num2 represented as strings, return the product of num1 and num2. Note: (1)The length of both num1 and num2 is < 110.
2017-11-19 09:08:46 295
原创 Re-ID: Person Re-identification by Local Maximal Occurrence Representation and Metric Learning 论文解析
注: 刚刚看完了这篇论文,顺便整理了一下这篇论文的思路,对论文的方法表示666项目主页:http://www.cbsr.ia.ac.cn/users/scliao/projects/lomo_xqda/论文解析行人重识别有两个特别重要的问题: Feature representationMetric learning在这篇论文中,作者采用的是LOMO的特征表示方法,以及XQDA的度量学习方法
2017-11-17 00:11:06 4387 4
原创 Re-ID: Reidentification by Relative Distance Comparison 论文解析
注:刚刚看完了这篇论文,顺便整理了一下这篇论文的思路,还是得膜一下伟诗大佬,666论文地址:Person Re-identification论文解析Matching people across nonoverlapping camera views at different locations and different time.RE-ID的一个经典的简化设定是一个pro...
2017-11-14 12:31:25 1432
原创 Leetcode: 515.Find Largest Value in Each Tree Row(Week10, Medium)
注:本题采用的是BFS算法 Leetcode 515 You need to find the largest value in each row of a binary tree. Example: Input: 1 / \ 3 2 / \ \ 5 3 9 Output: [1, 3, 9]题意:找到二
2017-11-09 16:15:35 284
原创 Leetcode: 34. Search for range(Week9, Medium)
注:本题采用二分法的思想 Leetcode 34 Given an array of integers sorted in ascending order, find the starting and ending position of a given target value. Your algorithm’s runtime complexity must be in th
2017-11-05 17:04:49 292
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人