Modified Densely Connected Convolutional Network for Content Generation in Automatic Image Description Generation System

被引:0
作者
Sreela, S. R. [1 ]
Idicula, Sumam Mary [1 ]
机构
[1] Cochin Univ Sci & Technol, Dept Comp Sci, Kochi, Kerala, India
来源
2017 IEEE REGION 10 INTERNATIONAL SYMPOSIUM ON TECHNOLOGIES FOR SMART CITIES (IEEE TENSYMP 2017) | 2017年
关键词
Social media; Object classification; Densenet; Image forgery;
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Automatic image description generation is a challenging task in computer vision and computational linguistics. It helps people to get access to social media images easily. Content generation and surface realization are two important phases of this task. Deep learning techniques have a major role in content generation phase. The important scenario in content generation is object recognition. Deep learning algorithms produce better results compared to classical machine learning techniques. In this paper, we will explain a modified densely connected convolution network(Densenet) for object classification.
引用
收藏
页数:5
相关论文
共 20 条
  • [1] Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265
  • [2] [Anonymous], STUDY RESIDUAL NETWO
  • [3] [Anonymous], 2011, P 24 CVPR
  • [4] [Anonymous], 2005, PROC CVPR IEEE
  • [5] [Anonymous], 2013, arXiv
  • [6] [Anonymous], 2012, P 13 C EUR CHAPT ASS
  • [7] Deep Machine Learning-A New Frontier in Artificial Intelligence Research
    Arel, Itamar
    Rose, Derek C.
    Karnowski, Thomas P.
    [J]. IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE, 2010, 5 (04) : 13 - 18
  • [8] Davis J., 2006, ICML 06, DOI 10.1145/1143844.1143874
  • [9] He K., 2016, PROC CVPR IEEE, P630, DOI [10.1007/978-3-319-46493-0_38, DOI 10.1007/978-3-319-46493-0_38, DOI 10.1109/CVPR.2016.90]
  • [10] He K., 2016, P IEEE COMPUTER SOC, P770