论文
关注
分享
扫一扫
阅进康庄大道
六半
学无止境，认识时间，认识自己
展开
专栏收录文章
- 默认排序
- 最新发布
- 最早发布
- 最多阅读
- 最少阅读
-
[paper] 00041-A Flexible New Technique for Camera Calibration
Today Let's read a classics and old paper which is the foundation for calibration.Author: Zhengyou Zhang0. AbstractCalibrate a camera. The technique only requires the camera to observe a pla...原创 2019-11-02 20:43:23 · 578 阅读 · 0 评论 -
[paper] 00039- AI Benchmark: Running Deep Neural Networks on Android Smartphones
AI Benchmark: Running Deep Neural Networks on Android SmartphonesAuthor:0. AbstractIn this paper, we present a study of the current state of deep learning in the Android ecosystem and descr...原创 2019-10-29 08:35:46 · 405 阅读 · 0 评论 -
[paper] 00040-Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional ArchitecturePaper:Author:David Eigen: Dept. of Computer Science, Courant Institute, New York Unive...原创 2019-10-29 08:31:25 · 439 阅读 · 0 评论 -
[paper] 00034-Convoulution Pose Machines
Author: Shih-En Wei---The Robotics Institute Carnegie Mellon UniversityAbstract:Pose Machines provide a sequential prediction framework for learning rich implicit spatial models.The contribu...原创 2019-10-25 08:04:25 · 241 阅读 · 0 评论 -
[paper] 00037-Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Author: Liang-CHieh Chen et. al--- Google Inc.Keywords:DeepLabv3+ : extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along obj...原创 2019-10-24 08:27:18 · 329 阅读 · 0 评论 -
[paper] 00036-Xception:Deep Learning with Depthwise Separable Convolutions
Author: Francois Chollet ----Google---Keras作者、谷歌大脑Key Words:Depthwise Separable Convolutions-------1. Introduction1.1 The Inception HypothesisA single convolution kernel is task...原创 2019-10-24 08:23:06 · 313 阅读 · 0 评论 -
[paper] 00033 Distance Metric Learning：A Comprehensive Survey
看的很费劲，也只看了个囫囵吞枣。不过，Get到不少的知识点，总体来说值。原创 2019-10-22 00:42:32 · 571 阅读 · 0 评论 -
[paper] 00035 Synthetic Depth-of-Field with a Single-Camera Mobile Phone
Google ResearchPaper name aimed two point: 1. Synthetic Depth-of-Field 2. Single-Camera Mobile PhoneKey Words:Shallow depth-of-field: W...原创 2019-10-22 00:34:36 · 1080 阅读 · 1 评论 -
[paper] 00020 Faster R-CNN_ Towards Real-Time ObjectDetection with Region Proposal Net
abstract:干啥的：物体检测。研究这篇论文的好处：1. 开源的代码2. 2给版本：python和matlab3. 用的公开数据，具有可信度数据+算法+代码 = 方便作者Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun源码：PYTHON:https://github.com/...原创 2019-10-14 00:42:24 · 142 阅读 · 0 评论 -
[paper] 00032 Distance Metric Learning for Large Margin Nearest Neighbor Classification
原创 2019-09-20 00:32:19 · 419 阅读 · 0 评论 -
[paper] 00031 Target Ultinate accuracy: Face Recognition via deep embedding
百度的人脸识别方法。虽然仅有4页，思路和方法都非常明确。原创 2019-09-18 00:11:14 · 314 阅读 · 0 评论 -
[paper] 00030 FaceNet: A Unified Embedding for Face Recognition and Clastering
原创 2019-09-10 00:11:51 · 116 阅读 · 0 评论 -
[paper] 00029 Deep Face Recognition: A Survey (下)
V. Face DataBases And Evaluation ProtocolsA. Large-scale training data sets and their label noise原创 2019-09-08 00:01:48 · 348 阅读 · 0 评论 -
[paper] 00029 Deep Face Recognition: A Survey (上)
这周开始搞人脸识别，找啊找啊找论文，这篇论文对于刚开始搞人脸识别的，并且有其它深度学习经验的工作者来说，是个福音。Deep Face Recognition: A Survey1. INFORMATIONAttributes:a. Mainstream network architecture: Deepface [195], DeepID series [191],[2...原创 2019-09-05 23:57:44 · 404 阅读 · 0 评论 -
[paper] 00028 Deep Face Recognition
这篇论文，主要讲了2点：1. 如何建立一个大的数据集 2. 如何搭建深度学习网络来做人脸识别。原创 2019-09-05 00:55:15 · 155 阅读 · 0 评论 -
[paper] 00027 Iterated extended Kalman filter based visual-inertial odometry using direct （下）
废话少说，直接笔记伺候原创 2019-09-03 01:01:41 · 532 阅读 · 1 评论 -
[paper] 00027 Iterated extended Kalman filter based visual-inertial odometry using direct （上）
Iterated extended Kalman filter based visual-inertial odometry using direct photometric feedbackROVIO的论文，一个有想法的SLAM开源方案，也是可以在某些应用下适合的方案。论文在百度上搜索的都有某些限制，我放到资源里，有资源的同学可以自用，或者留言邮箱。...原创 2019-09-01 01:01:33 · 647 阅读 · 2 评论 -
[paper] 00026 ORB-SLAM_ a Versatile and AccurateMonocular SLAM System
论文地址：https://arxiv.org/abs/1502.00956?context=cs.CV一个很系统的对单目视觉SLAM讲解的论文。原创 2019-08-31 00:35:21 · 245 阅读 · 0 评论 -
[paper] 00025 MEC-assisted End-to-End Latency Evaluations for C-V2X Communications
老板给出命令，要搞个以后的自驾的解决方向，找到相关知识点，就是基于5G的V2X论文地址：https://arxiv.org/pdf/1802.08027.pdf稍微做了下笔记，内容有些虚，只能get到一些基本知识点，没有很深的东西。...原创 2019-08-29 00:50:24 · 233 阅读 · 0 评论