跳到主要导航 跳到搜索 跳到主要内容

Human action recognition based on sub-data learning

  • Yang Chen
  • , Tian Wang*
  • , Jiakun Li
  • , Xiaowei Lv
  • , Hichem Snoussi
  • *此作品的通讯作者
  • Beihang University
  • China Electronics Technology Group Corporation
  • Université de technologie de Troyes

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Human action recognizing nowadays plays a key role in varieties of computer vision applications while at the same time it’s quite challenging for the requirement of accuracy and robustness. Most current computer vision methods focus on algorithms designing classifiers with handcrafted features which are complex and inflexible. To automatically extract both spatial and temporal features, in this paper we propose a method of human action recognition based on sub-data learning which combines the proposed 3D convolutional neural network (3DCNN) with the One-versus-One (OvO) algorithm. We also employ effective data augmentation to reduce overfitting. We evaluate our method on the KTH and UCF Sports dataset and achieve promising results.

源语言英语
主期刊名Computer Vision - 2nd CCF Chinese Conference, CCCV 2017, Proceedings
编辑Jinfeng Yang, Qingshan Liu, Liang Wang, Xiang Bai, Qinghua Hu, Ming-Ming Cheng, Deyu Meng
出版商Springer Verlag
617-626
页数10
ISBN(印刷版)9789811073045
DOI
出版状态已出版 - 2017
活动2nd Chinese Conference on Computer Vision, CCCV 2017 - Tianjin, 中国
期限: 11 10月 201714 10月 2017

丛书

姓名Communications in Computer and Information Science
773
ISSN(印刷版)1865-0929

会议

会议2nd Chinese Conference on Computer Vision, CCCV 2017
国家/地区中国
Tianjin
时期11/10/1714/10/17

学术指纹

探究 'Human action recognition based on sub-data learning' 的科研主题。它们共同构成独一无二的学术指纹。

引用此