• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of visual communication & image representation >Collaborative sparse representation leaning model for RGBD action recognition
【24h】

Collaborative sparse representation leaning model for RGBD action recognition

机译：用于RGBD动作识别的协作稀疏表示学习模型

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

Multi-modalities action recognition becomes a hot research topic, and this paper proposes a collaborative sparse representation leaning model for RGB-D action recognition where RGB and depth information are adaptive fused. Specifically, dense trajectory feature is firstly extracted and Bag-of-Word (BoW) weight scheme is employed for RGB modality, and then for depth modality, the human pose representation model (HPM) and temporal modeling (TM) representation are utilized. Meanwhile, the collaborative reconstruction structure and corresponding objective functions for the multiple modalities are designed, and then the proposed model is collaboratively optimized which is used to discover the latent complementary information between RGB and depth data. Finally, the collaborative reconstruction error is employed as our classification scheme. Large scale experimental results on challenging and public DHA, (MI)-I-2 and Northwestern-UCLA action datasets show that the performances of our model on two modalities are much better than traditional sole modality, which can boost the performance of human action recognition by taking advance of complementary characteristics from both RGB and depth modalities. (C) 2017 Elsevier Inc. All rights reserved.
机译：多模式动作识别成为研究的热点，本文提出了一种基于RGB和深度信息自适应融合的协作稀疏表示学习模型。具体来说，首先提取密集的轨迹特征，然后将词袋（BoW）权重方案用于RGB模态，然后对于深度模态，利用人体姿势表示模型（HPM）和时间建模（TM）表示。同时，设计了多种形式的协同重构结构和相应的目标函数，然后对提出的模型进行了协同优化，以发现RGB和深度数据之间的潜在互补信息。最后，将协同重建误差作为我们的分类方案。在具有挑战性和公共性的DHA，（MI）-I-2和Northwestern-UCLA行动数据集上进行的大规模实验结果表明，我们的模型在两种模式下的性能要比传统的唯一模式好得多，这可以提高人类行动识别的性能通过充分利用RGB和深度模态的互补特性。 （C）2017 Elsevier Inc.保留所有权利。

著录项

  • 来源
  • 作者

    Gao Z.; Li S. H.; Zhu Y. J.; Wang C.; Zhang H.;

  • 作者单位

    Tianjin Univ Technol, Key Lab Comp Vis & Syst, Minist Educ, Tianjin 300384, Peoples R China|Tianjin Univ Technol, Tianjin Key Lab Intelligence Comp & Novel Softwar, Tianjin 300384, Peoples R China;

    Tianjin Univ Technol, Key Lab Comp Vis & Syst, Minist Educ, Tianjin 300384, Peoples R China|Tianjin Univ Technol, Tianjin Key Lab Intelligence Comp & Novel Softwar, Tianjin 300384, Peoples R China;

    Chinese Acad Sci, Inst Informat Engn, Natl Engn Lab Informat Secur Technol, Beijing 100093, Peoples R China;

    Home Depot, Atlanta, GA USA;

    Tianjin Univ Technol, Key Lab Comp Vis & Syst, Minist Educ, Tianjin 300384, Peoples R China|Tianjin Univ Technol, Tianjin Key Lab Intelligence Comp & Novel Softwar, Tianjin 300384, Peoples R China;

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

    RGBD action recognition; Collaborative sparse representation leaning model; Dense trajectory; Multi-modality; Depth feature;

    机译：RGBD动作识别;协作稀疏表示学习模型;密集轨迹;多模态;深度特征;

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