arXiv is an e-print service in the fields of physics, mathematics, computer science, quantitative biology, quantitative finance and statistics. There'll be lots of papers in advance. Here's some recent papers which is important or interesting.

1. Object Detection

even faster than fast rcnn, more end to end for detection, more accurate

You Only Look Once: Unified, Real-Time Object Detection

Faster R-CNN: Towards Real-Time Object Detection with RegionProposal Network

watermark/2/text/aHR0cDovL2Jsb2cuY3Nkbi5uZXQvc3VuYmFpZ3Vp/font/5a6L5L2T/fontsize/400/fill/I0JBQkFCMA==/dissolve/70/gravity/Center" alt="">

2. cnn itself

more faster over cnn

Fast ConvNets Using Group-wise Brain Damage

more fine-grained visual recognition

Bilinear CNN Models for Fine-grained Visual Recognition

watermark/2/text/aHR0cDovL2Jsb2cuY3Nkbi5uZXQvc3VuYmFpZ3Vp/font/5a6L5L2T/fontsize/400/fill/I0JBQkFCMA==/dissolve/70/gravity/Center" alt="">

new post process for classify

Classify Images with Conceptor Network

SVM and ELM: Who Wins? Object Recognitionwith Deep Convolutional Features from ImageNet

watermark/2/text/aHR0cDovL2Jsb2cuY3Nkbi5uZXQvc3VuYmFpZ3Vp/font/5a6L5L2T/fontsize/400/fill/I0JBQkFCMA==/dissolve/70/gravity/Center" alt="">

how to combine multiple cnn?

Learning to Select Pre-Trained Deep Representations withBayesian Evidence Framework

3. image captioning

attributes/word layer

Image Captioning with an Intermediate Attributes Layer

4. OCR

Boosting Optical Character Recognition: ASuper-Resolution Approach

5. interesting work

Visual Learning of Arithmetic Operations

EventNet: A Large Scale Structured ConceptLibrary forComplex Event Detection in Video

[3 Jun 2015 ~ 9 Jun 2015] Deep Learning in arxiv的更多相关文章

  1. [Fri 26 Jun 2015 ~ Thu 2 Jul 2015] Deep Learning in arxiv

    Natural Neural Networks Google DeepMind又一神作 Projected Natural Gradient Descent algorithm (PRONG) bet ...

  2. [Tue, 11 Aug 2015 ~ Mon, 17 Aug 2015] Deep Learning in arxiv

    Image Representations and New Domains inNeural Image Captioning we find that a state-of-theart neura ...

  3. [Thu, 9 Jul 2015 ~ Tue, 14 Jul 2015] Deep Learning in arxiv

    这一期的神作论文有蛮多的,都很有意思. Feature Representation In ConvolutionalNeural Networks 该论文中论述了在某种CNN结构下,是否有准确率较高 ...

  4. [Fri, 3 Jul 2015 ~ Tue, 7 Jul 2015] Deep Learning in arxiv

    Convolutional Color Constancy can this be used for training cnn to narrow the gap between different ...

  5. 【深度学习Deep Learning】资料大全

    最近在学深度学习相关的东西,在网上搜集到了一些不错的资料,现在汇总一下: Free Online Books  by Yoshua Bengio, Ian Goodfellow and Aaron C ...

  6. (转) Awesome Deep Learning

    Awesome Deep Learning  Table of Contents Free Online Books Courses Videos and Lectures Papers Tutori ...

  7. What are some good books/papers for learning deep learning?

    What's the most effective way to get started with deep learning?       29 Answers     Yoshua Bengio, ...

  8. (zhuan) Where can I start with Deep Learning?

    Where can I start with Deep Learning? By Rotek Song, Deep Reinforcement Learning/Robotics/Computer V ...

  9. 0.读书笔记之The major advancements in Deep Learning in 2016

    The major advancements in Deep Learning in 2016 地址:https://tryolabs.com/blog/2016/12/06/major-advanc ...

随机推荐

  1. PHP协程是通过生成器实现的，这里测试了PHP生成器的一些特性

    学习PHP的生成器,测试了一些特性.代码如下: function gen() { $name = (yield 'hello'); $nickname = (yield 'world'); yield ...

  2. DS博客作业05—树

    1.本周学习总结 1.1思维导图 1.2学习体会 本周学习了树的相关知识,了解了树结构体的应用和基本操作 学习了二叉树的遍历,创建以及哈夫曼树的相关操作 通过树的构建等操作熟练了递归的使用 2.PTA ...

  3. JSON之解析

    JSON之解析通过TouchJSON\SBJSON\JSONKit\NSJSONSerialization JSON(JavaScript Object Notation) 是一种轻量级的数据交换格式 ...

  4. 扩展kmp--模板解析

    扩展kmp: 用于求串的各个后缀与原串的最长公共前缀的长度: 上图的是字符串自匹配的过程: 图一: 假设现在匹配到i-1了,开始求next [ i ] 的值,此时,k记录的是到目前为止匹配到的最远的位 ...

  5. HDU——1982Kaitou Kid - The Phantom Thief (1)（坑爹string题）

    Kaitou Kid - The Phantom Thief (1) Time Limit: 3000/1000 MS (Java/Others)    Memory Limit: 32768/327 ...

  6. 详解keepalived配置和使用

    标签:keepalived 原创作品,允许转载,转载时请务必以超链接形式标明文章 原始出处 .作者信息和本声明.否则将追究法律责任.http://lanlian.blog.51cto.com/6790 ...

  7. bzoj 4311 向量 时间线建线段树+凸包+三分

    题目大意 你要维护一个向量集合,支持以下操作: 1.插入一个向量(x,y) 2.删除插入的第i个向量 3.查询当前集合与(x,y)点积的最大值是多少.如果当前是空集输出0 分析 按时间线建线段树 大致 ...

  8. hdu 3613 KMP算法扩展

    Best Reward Time Limit: 2000/1000 MS (Java/Others)    Memory Limit: 65536/65536 K (Java/Others)Total ...

  9. APUE 学习笔记(六) 进程控制

    1. fork 创建新进程 fork创建的新进程称为子进程,fork函数调用一次,返回两次. 两次返回的唯一区别就是子进程的返回值是0,而父进程的返回值是新子进程的进程ID 在fork之后是父进程先执 ...

  10. 转 PHP中exec、system等函数调用linux命令问题

    PHP中exec.system等函数调用linux命令问题 先小说两句:今天研究了下PHP调用LINUX命令的功能,一开始怎么做都调用不成功,试了好久才终于成功了,所以发出来分享一下.下面我将详细介绍 ...