...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE transactions on multimedia >Learning Multi-View Representation With LSTM for 3-D Shape Recognition and Retrieval
【24h】

Learning Multi-View Representation With LSTM for 3-D Shape Recognition and Retrieval

机译：使用LSTM学习多视图表示，用于3-D形识别和检索

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Shape representation for 3-D models is an important topic in computer vision, multimedia analysis, and computer graphics. Recent multiview-based methods demonstrate promising performance for 3-D shape recognition and retrieval. However, most multiview-based methods ignore the correlations of multiple views or suffer from high computional cost. In this paper, we propose a novel multiview-based network architecture for 3-D shape recognition and retrieval. Our network combines convolutional neural networks (CNNs) with long short-term memory (LSTM) to exploit the correlative information from multiple views. Well-pretrained CNNs with residual connections are first used to extract a low-level feature of each view image rendered from a 3-D shape. Then, a LSTM and a sequence voting layer are employed to aggregate these features into a shape descriptor. The highway network and a three-step training strategy are also adopted to boost the optimization of the deep network. Experimental results on two public datasets demonstrate that the proposed method achieves promising performance for 3-D shape recognition and the state-of-the-art performance for the 3-D shape retrieval.
机译：3-D模型的形状表示是计算机视觉，多媒体分析和计算机图形中的一个重要主题。最近基于多视图的方法表明了3-D形状和检索的有希望的性能。然而，基于大多数的基于多视图的方法忽略了多个视图的相关性或遭受高卷积成本。在本文中，我们提出了一种基于多维视图的网络架构，用于3-D形状和检索。我们的网络将卷积神经网络（CNNS）与长短短期内存（LSTM）结合起来，以利用多视图来利用相关信息。具有剩余连接的良好预制的CNN，首先用于提取从3-D形状呈现的每个视图图像的低级特征。然后，采用LSTM和序列投票层将这些特征聚合到形状描述符中。还采用了公路网络和三步培训策略来提高深网络优化。两种公共数据集上的实验结果表明，该方法实现了3-D形状识别的有希望的性能和3-D形检索的最先进的性能。

著录项

  • 来源
    《IEEE transactions on multimedia》 |2019年第5期|1169-1182|共14页
  • 作者

    Ma Chao; Guo Yulan; Yang Jungang; An Wei;

  • 作者单位

    Natl Univ Def Technol Coll Elect Sci Changsha 410073 Hunan Peoples R China;

    Natl Univ Def Technol Coll Elect Sci Changsha 410073 Hunan Peoples R China|Sun Yat Sen Univ Sch Elect & Commun Engn Guangzhou 510275 Guangdong Peoples R China;

    Natl Univ Def Technol Coll Elect Sci Changsha 410073 Hunan Peoples R China;

    Natl Univ Def Technol Coll Elect Sci Changsha 410073 Hunan Peoples R China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    3-D shape; multi-view; object recognition; object retrieval; CNN; LSTM;

    机译：3-D形;多视图;对象识别;对象检索;CNN;LSTM;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号