CASIA OpenIR
High-dimensional multimedia classification using deep CNN and extended residual units
Shamsolmoali, Pourya1; Jain, Deepak Kumar2; Zareapoor, Masoumeh1; Yang, Jie1; Alam, M. Afshar3
Source PublicationMULTIMEDIA TOOLS AND APPLICATIONS
ISSN1380-7501
2019-09-01
Volume78Issue:17Pages:23867-23882
Corresponding AuthorShamsolmoali, Pourya(pshams55@gmail.com)
AbstractProcessing multimedia data has emerged as a key area for the application of machine learning methods Building a robust classification model to use in high dimensional space requires the combination of a deep feature extractor and a powerful classifier. We present a new classification pipeline to facilitate multimedia data analysis based on convolutional neural network and the modified residual network which can integrate with the other feedforward network style in an endwise training fashion. The proposed residual network is producing attention-aware features. We proposed a unified deep CNN model to achieve promising performance in classifying high dimensional multimedia data by getting the advantages of the residual network. In every residual module, up-down and vice-versa feedforward structure is implemented to unfold the feedforward and backward process into a unique process. The hybrid proposed model evaluated on four datasets and have been shown promising results which outperform the previous best results. Last but not the least, the proposed model achieves detection speeds that are much faster than other approaches.
KeywordHigh dimensional Multimedia data classification Deep learning Feature extraction Residual network
DOI10.1007/s11042-018-6146-7
WOS KeywordFEATURE-SELECTION ; REPRESENTATION
Indexed BySCI
Language英语
Funding ProjectNSFC, China[61572315] ; Committee of Science and Technology, Shanghai, China[17JC1403000] ; NSFC, China[61572315] ; Committee of Science and Technology, Shanghai, China[17JC1403000]
Funding OrganizationNSFC, China ; Committee of Science and Technology, Shanghai, China
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000482419900005
PublisherSPRINGER
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/27221
Collection中国科学院自动化研究所
Corresponding AuthorShamsolmoali, Pourya
Affiliation1.Shanghai Jiao Tong Univ, Inst Image Proc & Pattern Recognit, Shanghai, Peoples R China
2.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China
3.Jamia Hamdard, Dept Comp Sci & Engn, New Delhi, India
Recommended Citation
GB/T 7714
Shamsolmoali, Pourya,Jain, Deepak Kumar,Zareapoor, Masoumeh,et al. High-dimensional multimedia classification using deep CNN and extended residual units[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2019,78(17):23867-23882.
APA Shamsolmoali, Pourya,Jain, Deepak Kumar,Zareapoor, Masoumeh,Yang, Jie,&Alam, M. Afshar.(2019).High-dimensional multimedia classification using deep CNN and extended residual units.MULTIMEDIA TOOLS AND APPLICATIONS,78(17),23867-23882.
MLA Shamsolmoali, Pourya,et al."High-dimensional multimedia classification using deep CNN and extended residual units".MULTIMEDIA TOOLS AND APPLICATIONS 78.17(2019):23867-23882.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Shamsolmoali, Pourya]'s Articles
[Jain, Deepak Kumar]'s Articles
[Zareapoor, Masoumeh]'s Articles
Baidu academic
Similar articles in Baidu academic
[Shamsolmoali, Pourya]'s Articles
[Jain, Deepak Kumar]'s Articles
[Zareapoor, Masoumeh]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Shamsolmoali, Pourya]'s Articles
[Jain, Deepak Kumar]'s Articles
[Zareapoor, Masoumeh]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.