Large-scale Video Classification with Convolutional Neural Networks(泛读)
2014-10-08 20:50
435 查看
一.文献名字和作者
Large-scale Video Classification with Convolutional Neural Networks, CVPR2014二.阅读时间
2014年10月8日三.文献的贡献点
文章的贡献点主要有三个:1.将CNN拓展,用于视频分类;2.使用两种不同的分辨率的帧分别作为输入,输入到两个CNN中,在最后的两个全连接层将两个CNN统一起来;两个流分别是低分辨率的内容流和采用每一个帧中间部分的高分辨率流(如图1);
3.将从自建数据库学习到的CNN结构迁移到UCF-101数据集上面。
在考虑时间关联性方面,作者提出了四种方案(如图2),并且进行了相关实验,实验的结果表示这四种方面都能取得很好的结果。
作者也做了关于迁移学习的实验,证明了使用自建数据库学习到的神经网络能够用于UCF-101数据集,而且效果比单独使用UCF-101训练得到的效果还要好。
这篇文献提出的使用不同分辨率作为输入的方法,可以考虑在图像分类方面使用一下。
图1. 网络结构
图2. 不同关于时间信息的融合方案
版权所有,欢迎转载,转载请注明出处,谢谢
相关文章推荐
- Notes on Large-scale Video Classification with Convolutional Neural Networks
- 【论文学习】Large-scale Video Classification with Convolutional Neural Networks
- [深度学习论文笔记][Video Classification] Large-scale Video Classification with Convolutional Neural Networks
- Large-scale Video Classification with Convolutional Neural Networks
- CV论文笔记(二) Large-scale Video Classification with Convolutional Neural Networks
- Large-scale Video Classification with Convolution Neural Networks
- ImageNet Classification with Deep Convolutional Neural Networks泛读总结
- 《On Classification of Distorted Images with Deep Convolutional Neural Networks》翻译
- 经典计算机视觉论文笔记——《ImageNet Classification with Deep Convolutional Neural Networks》
- ImageNet Classification with Deep Convolutional Neural Networks(译文)转载
- ImageNet Classification with Deep Convolutional Neural Networks简介
- 论文:ImageNet Classification with Deep Convolutional Neural Networks
- 《ImageNet Classification with Deep Convolutional Neural Networks》
- 论文阅读(1)——ImageNet Classification with Deep Convolutional Neural Networks
- AlexNet-ImageNet Classification with Deep Convolutional Neural Networks
- AlexNet--ImageNet Classification with Deep Convolutional Neural Networks
- ImageNet Classification with Deep Convolutional Neural Networks阅读笔记
- AlexNet学习笔记1-ImageNet Classification with Deep Convolutional Neural Networks
- AlexNet : ImageNet Classification with Deep Convolutional Neural Networks
- 《ImageNet Classification with Deep Convolutional Neural Networks》论文阅读