Xiaoguang Tu's Home Page
Xiaoguang Tu (涂晓光):

CV: Ph.D. Candidate of School of Communication and Information Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, P.R. China.
Research field: Face Recognition; Medical Image Processing; Computer vision; Deep Learning.
Publications:
1. Tu X, Gao J, Zhu C, et al. MR image segmentation and bias field estimation based on coherent local intensity clustering with total variation regularization.[J]. Medical & Biological Engineering & Computing,
2016, 54(12):1807-1818. (pdf, code).
2. Tu X, Gao J, Xie M, et al. Illumination Normalization based on Correction of Large-scale Components for Face Recognition[J]. Neurocomputing, 2017.
3. Tu X, Xie M, Gao J, et al. Automatic Categorization and Scoring of Solid, Part-Solid and Non-Solid Pulmonary Nodules in CT Images with Convolutional Neural Network[J]. Scientific Reports, 2017, 7.
4. Ge H, Yang F, Tu X, et al. Pre-Processing for Fine-Grained Image Classification[J]. IEICE TRANSACTIONS on Information and Systems, 2017, 100(8): 1938-1942.
5. Gao J, Dai X, Zhu C, et al. Supervoxel Segmentation and Bias Correction of MR Image with Intensity Inhomogeneity[J]. Neural Processing Letters, 2017: 1-14.
6. TU X, YANG F, XIE M. Illumination Normalization for Face Recognition Using Energy Minimization Framework[J]. IEICE TRANSACTIONS on Information and Systems, 2017, 100(6): 1376-1379.
7. X Tu, J Zhao, M Xie, G Du, H Zhang, J Li, Z Ma, J Feng - arXiv preprint arXiv:1901.05602, 2019. Learning Generalizable and Identity-Discriminative Representations for Face Anti-Spoofing.
8. X Tu, H Zhang, M Xie, Y Luo, Y Zhang, Z Ma - arXiv preprint arXiv:1901.05635, 2019. Enhance the Motion Cues for Face Anti-Spoofing using CNN-LSTM Architecture
9. X Tu, H Zhang, M Xie, Y Luo, Y Zhang, Z Ma - arXiv preprint arXiv:1901.05633, 2019. Deep Transfer Across Domains for Face Anti-spoofing
10. J Zhao, J Li, X Tu, F Zhao, Y Xin, J Xing, H Liu, S Yan… - arXiv preprint arXiv:1902.04755, 2019. Multi-Prototype Networks for Unconstrained Set-based Face Recognition
11. X Tu, Jian Zhao, et al. Joint 3D Face Reconstruction and Dense Face Alignment from A Single Image with 2D-Assisted Self-Supervised Learning. Arxiv: https://arxiv.org/abs/1903.09359
Xiaoguang Tu's Home Page的更多相关文章
- Operating System Memory Management、Page Fault Exception、Cache Replacement Strategy Learning、LRU Algorithm
目录 . 引言 . 页表 . 结构化内存管理 . 物理内存的管理 . SLAB分配器 . 处理器高速缓存和TLB控制 . 内存管理的概念 . 内存覆盖与内存交换 . 内存连续分配管理方式 . 内存非连 ...
- How to manipulate pixels on a bitmap by scanline property(Ma Xiaoguang and Ma Xiaoming)
We have been developing image processing software for above 14 years with old versions of Delphi, su ...
- 我这么玩Web Api(一):帮助页面或用户手册(Microsoft and Swashbuckle Help Page)
前言 你需要为客户编写Api调用手册?你需要测试你的Api接口?你需要和前端进行接口对接?那么这篇文章应该可以帮到你.本文将介绍创建Web Api 帮助文档页面的两种方式,Microsoft Help ...
- HTML5 Page Visibility
什么是 Page Visibility ? Page Visibility 即页面可见性,通过 visibilityState 的值检测页面当前是否可见.当一个网站是可见或点击选中的状态时 Page ...
- angularjs 1 开发简单案例(包含common.js,service.js,controller.js,page)
common.js var app = angular.module('app', ['ngFileUpload']) .factory('SV_Common', function ($http) { ...
- Selenium的PO模式(Page Object Model)[python版]
Page Object Model 简称POM 普通的测试用例代码: .... #测试用例 def test_login_mail(self): driver = self.driver driv ...
- SharePoint2013 Set a custom application page as site welcome page
本文主要介绍如何添加一个custom application page as site welcome page 1.首先创建一个sharepoint 2013 empty solution, add ...
- 使用page object模式抓取几个主要城市的pm2.5并从小到大排序后写入txt文档
#coding=utf-8from time import sleepimport unittestfrom selenium import webdriverfrom selenium.webdri ...
- github page+jekyll搭博客初体验
div.oembedall-githubrepos { border: 1px solid #DDD; list-style-type: none; margin: 0 0 10px; padding ...
随机推荐
- [USACO5.3]量取牛奶Milk Measuring
https://daniu.luogu.org/problemnew/show/P2744 滚动数组压去第一维:前i种木桶 f[j] 量取体积j最少需要几种木桶 g[j] 体积j的最优解是否使用了第 ...
- Linux 常见文件及目录
文件/etc//etc/passwd用户基本信息/etc/group用户组基本信息/etc/shadow/etc/passwd 文件的补充/etc/gshadow阴影口令套组中的组配置文件/etc/l ...
- windows 下 react-native(v0.56) Android 环境搭建踩坑记录
debugservicereact-native 安装官网 https://reactnative.cn/docs/getting-started.html 根据官网步骤一步步执行下去.还能碰到一些问 ...
- HDU 3790 最短路径问题 (最短路)
题目链接 Problem Description 给你n个点,m条无向边,每条边都有长度d和花费p,给你起点s终点t,要求输出起点到终点的最短距离及其花费,如果最短距离有多条路线,则输出花费最少的. ...
- linux源码安装nginx
任务目标:源码安装nginx,作为web服务修改配置文件,让配置生效,验证配置 首先要去官网nginx.org下载一个tar包: tar xvf 解包 进入到解包出来的目录,对configure进行配 ...
- 转载-SVN常用命令
SVN(Subversion)是一个自由.开源的项目源代码版本控制工具.目前,绝大多数开源软件和企业代码管理,都使用SVN作为代码版本管理软件. Subversion将文件存放在中心版本库里,这个版本 ...
- Git 创建仓库【转】
转自:http://www.runoob.com/git/git-create-repository.html Git 创建仓库 本章节我们将为大家介绍如何创建一个 Git 仓库. 你可以使用一个已经 ...
- linux创建新用户
服务器只用root账号会有风险,最好是每个人使用一个账号. 1. 添加用户名 adduser linuxidc 2. 给这个用户名设置新密码 passwd linuxidc 3.授权 个人用户的权限只 ...
- hash算法原理详解
转载出处http://blog.csdn.net/tanggao1314/article/details/51457585 一.概念 哈希表就是一种以 键-值(key-indexed) 存储数据的结构 ...
- 解决insert语句插入时,需要写列值的问题
今天发现解决这个问题其实很简单,闲话不多谈,我直接附上语句 ) select @s = isnull(@s+',', '') + [name] from syscolumns where id = o ...