咨询与建议

限定检索结果

文献类型

  • 1 篇 期刊文献

馆藏范围

  • 1 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 1 篇 工学
    • 1 篇 电气工程
    • 1 篇 计算机科学与技术...

主题

  • 1 篇 vector of locall...
  • 1 篇 spatial pyramid ...
  • 1 篇 intelligent info...
  • 1 篇 computer archite...
  • 1 篇 feedforward neur...
  • 1 篇 cn ns
  • 1 篇 convolution feat...
  • 1 篇 graphics
  • 1 篇 locally aggregat...
  • 1 篇 learning artific...
  • 1 篇 image coding
  • 1 篇 spatial informat...
  • 1 篇 multiple vlad en...
  • 1 篇 visualization
  • 1 篇 cnn
  • 1 篇 feature extracti...
  • 1 篇 image representa...
  • 1 篇 encoding algorit...
  • 1 篇 image classifica...
  • 1 篇 images salient o...

机构

  • 1 篇 southwest jiaoto...
  • 1 篇 southwest jiaoto...

作者

  • 1 篇 li qing
  • 1 篇 yan chuan
  • 1 篇 peng qiang

语言

  • 1 篇 英文
检索条件"主题词=VLAD Coding Methods Performance"
1 条 记 录,以下是1-10 订阅
排序:
Multiple vlad Encoding of CNNs for Image Classification
收藏 引用
COMPUTING IN SCIENCE & ENGINEERING 2018年 第2期20卷 52-63页
作者: Li, Qing Peng, Qiang Yan, Chuan Southwest Jiaotong Univ Comp Applicat Technol Chengdu Sichuan Peoples R China Southwest Jiaotong Univ Sch Informat Sci & Technol Chengdu Sichuan Peoples R China
Despite the effectiveness of convolutional neural networks (CNNs), especially for image classification tasks, the effect of convolution features on learned representations is still limited, mainly focusing on an image... 详细信息
来源: 评论