跳到主要导航 跳到搜索 跳到主要内容

Deep multi-context Network for fine-grained visual recognition

  • Xinyu Ou
  • , Zhen Wei
  • , Ling Hefei*
  • , Liu Si
  • , Cao Xiaochun
  • *此作品的通讯作者
  • Huazhong University of Science and Technology
  • CAS - Institute of Information Engineering
  • 3Yunnan Open University
  • University of Electronic Science and Technology of China

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

In this paper, we tackle the FINE-GRAINED VISUAL RECOGNITION problem by proposing a deep multi-context framework. We employ deep Convolutional Neural Networks to model features of objects in images. Global context and local context are both taken into consideration, and are jointly modeled in a unified multi-context deep learning framework. To cleanse the relatively dirty data for training, a regional proposal method is designed to make the multi-context modeling suited for fine-grained visual recognition in the real world. Furthermore, recently proposed contemporary deep models are used, and their combination is investigated. Our approaches are evaluated on MSR-IRC 2016 and further assessed on the more complex validation set. The results show significant and consistent improvements over the baseline.

源语言英语
主期刊名2016 IEEE International Conference on Multimedia and Expo Workshop, ICMEW 2016
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(电子版)9781509015528
DOI
出版状态已出版 - 22 9月 2016
已对外发布
活动2016 IEEE International Conference on Multimedia and Expo Workshop, ICMEW 2016 - Seattle, 美国
期限: 11 7月 201615 7月 2016

出版系列

姓名2016 IEEE International Conference on Multimedia and Expo Workshop, ICMEW 2016

会议

会议2016 IEEE International Conference on Multimedia and Expo Workshop, ICMEW 2016
国家/地区美国
Seattle
时期11/07/1615/07/16

学术指纹

探究 'Deep multi-context Network for fine-grained visual recognition' 的科研主题。它们共同构成独一无二的学术指纹。

引用此