咨询与建议

限定检索结果

文献类型

  • 1 篇 期刊文献
  • 1 篇 会议

馆藏范围

  • 2 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

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

主题

  • 2 篇 parallel asymmet...
  • 1 篇 semantic informa...
  • 1 篇 blstm
  • 1 篇 text classificat...
  • 1 篇 electronic mail
  • 1 篇 text detection
  • 1 篇 global max pooli...
  • 1 篇 annotations
  • 1 篇 semantics
  • 1 篇 feature extracti...
  • 1 篇 kernel
  • 1 篇 detectors
  • 1 篇 accuracy
  • 1 篇 shape
  • 1 篇 multiscale featu...
  • 1 篇 discrete cosine ...

机构

  • 1 篇 natl univ def te...
  • 1 篇 hunan normal uni...
  • 1 篇 univ sci & techn...
  • 1 篇 huazhong univ sc...
  • 1 篇 hunan normal uni...

作者

  • 1 篇 jin zhong
  • 1 篇 jiang wei
  • 1 篇 chen hua
  • 1 篇 zhu zhenlin
  • 1 篇 sang nong
  • 1 篇 qian shengyou
  • 1 篇 liu li
  • 1 篇 zhu yanbin
  • 1 篇 wang runmin
  • 1 篇 cao xiaofei
  • 1 篇 gao changxin
  • 1 篇 xu juan

语言

  • 2 篇 英文
检索条件"主题词=parallel asymmetric convolution"
2 条 记 录,以下是1-10 订阅
排序:
S3INet: Semantic-Information Space Sharing Interaction Network for Arbitrary Shape Text Detection
收藏 引用
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2025年 PP卷 PP页
作者: Wang, Runmin Chen, Hua Zhu, Yanbin Xu, Juan Cao, Xiaofei Zhu, Zhenlin Qian, Shengyou Gao, Changxin Liu, Li Sang, Nong Hunan Normal Univ Sch Informat Sci & Engn Changsha 410081 Peoples R China Hunan Normal Univ Sch Phys & Elect Sci Changsha 410081 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Natl Univ Def Technol Coll Elect Sci & Technol Changsha 410000 Peoples R China
The detecting arbitrary shape text is a challenging task due to the significant variation in text shape, size, and aspect ratio, as well as the complexity of scene backgrounds. The enhancing feature extraction capabil... 详细信息
来源: 评论
Integrating Bidirectional LSTM with Inception for Text Classification  4
Integrating Bidirectional LSTM with Inception for Text Class...
收藏 引用
4th IAPR Asian Conference on Pattern Recognition (ACPR)
作者: Jiang, Wei Jin, Zhong Univ Sci & Technol Sch Comp Sci & Engn Nanjing Jiangsu Peoples R China
A novel neural network architecture, BLSTM-Inception v1, is proposed for text classification. It mainly consists of the BLSTM-Inception module, which has two parts, and a global max pooling layer. In the first part, f... 详细信息
来源: 评论