Link of the Paper: https://arxiv.org/pdf/1504.06692.pdf

Innovations:

  • The authors propose the Novel Visual Concept learning from Sentences ( NVCS ) task. In this task, methods need to learn novel concepts from sentence descriptions of a few images.
  • The authors propose a transposed weight sharing scheme, which not only improves performance on image captioning, but also makes the model more suitable for the novel concept learning task.
  • Three novel concept datasets are constructed for NVCS task.

Improvements:

  • The method proposed is based on m-RNN and the authors provide several inprovements.

General Points:

Paper Reading - Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images ( ICCV 2015 )的更多相关文章

  1. Paper Reading: Stereo DSO

    开篇第一篇就写一个paper reading吧,用markdown+vim写东西切换中英文挺麻烦的,有些就偷懒都用英文写了. Stereo DSO: Large-Scale Direct Sparse ...

  2. Paper Reading - Deep Captioning with Multimodal Recurrent Neural Networks ( m-RNN ) ( ICLR 2015 ) ★

    Link of the Paper: https://arxiv.org/pdf/1412.6632.pdf Main Points: The authors propose a multimodal ...

  3. Targeted Learning R Packages for Causal Inference and Machine Learning（转）

    Targeted learning methods build machine-learning-based estimators of parameters defined as features ...

  4. 【转载】 《Human-level concept learning through probabilistic program induction》阅读笔记

    原文地址: https://blog.csdn.net/ln1996/article/details/78459060 --------------------- 作者:lnn_csdn 来源:CSD ...

  5. Learning Conditioned Graph Structures for Interpretable Visual Question Answering

    Learning Conditioned Graph Structures for Interpretable Visual Question Answering 2019-05-29 00:29:4 ...

  6. 论文笔记之：Learning Multi-Domain Convolutional Neural Networks for Visual Tracking

    Learning Multi-Domain Convolutional Neural Networks for Visual Tracking CVPR 2016 本文提出了一种新的CNN 框架来处理 ...

  7. Deep Learning论文笔记之（八）Deep Learning最新综述

    Deep Learning论文笔记之(八)Deep Learning最新综述 zouxy09@qq.com http://blog.csdn.net/zouxy09 自己平时看了一些论文,但老感觉看完 ...

  8. [DEEP LEARNING An MIT Press book in preparation]Deep Learning for AI

    动人的DL我们有六个月的时间,积累了一定的经验,实验,也DL有了一些自己的想法和理解.曾经想扩大和加深DL相关方面的一些知识. 然后看到了一个MIT按有关的对出版物DL图书http://www.iro ...

  9. 【CV】ICCV2015_Unsupervised Visual Representation Learning by Context Prediction

    Unsupervised Visual Representation Learning by Context Prediction Note here: it's a learning note on ...

随机推荐

  1. Unity3D Errors And Fix

    Author Error: Shader warning in 'Custom/ShowAnimation': Not enough temporary registers, needs 9 (com ...

  2. git获取步骤

    $ git init $ git config --global user.name "[name]" $ git config --global user.email [emai ...

  3. layui form表单 input输入框获取焦点后 阻止Enter回车自动提交

    最简单的解决办法,不影响其他操作,给提交按钮增加 type="button" 属性 完美解决 <button type="button" class=&q ...

  4. Laravel 开发支付宝支付与提现转账问题小结

    由于项目需要,所以需要开发支付宝支付与微信支付,支付部分采用了 yansongda/pay    https://packagist.org/packages/yansongda/pay  https ...

  5. sublime text 3安装 package control 插件的方法

    自动安装的方法 - 快捷键ctrl+` 或者View->Show Console,输入如下代码 import  urllib.request,os;pf='Package Control.sub ...

  6. Python(1-8天总结）

    day1:变量:把程序运行过程中产生的中间值.暂时存储起来.方便后面的程序调用.变量命名规范:常量:所有字母大写注释:数据类型: 1. int 整数 2. str 字符串. 不会用字符串保存大量的数据 ...

  7. ruby语言里的self理解

    关键的一句话:关键看谁调用self,self就属于谁 有3种情况: 1.在class或module的定义中,self代表这个class或者这个module对象,代码如下: class S puts ' ...

  8. PWA-缓存

    PWA-缓存 基础 PWA强大的离线能力就在于Service Worker拦截请求及提供缓存的能力,Service Worker的缓存能力比较强大,它能够赋予你更加精确控制缓存的能力.示例页面 < ...

  9. 高斯消元c++（非常暴力）

    暴力方法(已更新): #include<iostream> using namespace std; const int maxn = 1000; int n; double a[maxn ...

  10. 2018南京网络赛L题：Magical Girl Haze（最短路分层图）

    题目链接:https://nanti.jisuanke.com/t/31001 解题心得: 一个BZOJ的原题,之前就写过博客了. 原题地址:https://www.lydsy.com/JudgeOn ...