Exploiting Aesthetic Features in Visual Contents for Movie Recommendation

doi:10.1109/ACCESS.2019.2910722

	Exploiting Aesthetic Features in Visual Contents for Movie Recommendation
	Chen, Xiaojie 1; Zhao, Pengpeng 1,2; Liu, Yanchi 3; Zhao, Lei 1; Fang, Junhua 1; Sheng, Victor S.4; Cui, Zhiming 5
	2019
发表期刊	IEEE ACCESS
ISSN	2169-3536
卷号	7 页码:49813-49821
摘要	As one of the most widely used recommender systems, movie recommendation plays an important role in our life. However, the data sparsity problem severely hinders the effectiveness of personalized movie recommendation, which requires more rich content information to be utilized. Posters and still frames, which directly display the visual contents of movies, have significant influences on movie recommendation. They not only reveal rich knowledge for understanding movies but also useful for understanding user preferences. However, existing recommendation methods rarely consider aesthetic features, which tell how the movie looks and feels, extracted from these pictures for the movie recommendation. To this end, in this paper, we propose an aesthetic-aware unified visual content matrix factorization (called UVMF-AES) to integrate visual feature learning and recommendation into a unified framework. Specifically, we first integrate the convolutional neural network (CNN) features and aesthetic features into probabilistic matrix factorization. Then we establish a unified optimization framework with these features for the movie recommendation. The experimental results on two real-world datasets show that our proposed method UVMF-AES is significantly superior to the state-of-the-art methods on movie recommendation.
关键词	Movie recommendation aesthetic features probabilistic matrix factorization
DOI	10.1109/ACCESS.2019.2910722
收录类别	SCI
语种	英语
资助项目	NSFC[61876217] ; NSFC[61872258] ; NSFC[61728205] ; Suzhou Science and Technology Development Program[SYG201803] ; Postdoctoral Research Foundation of China[2017M621813] ; Natural Science Fund for Colleges and Universities in Jiangsu Province[18KJB520044] ; Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences[IIP2019-1]
WOS研究方向	Computer Science ; Engineering ; Telecommunications
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:000466916200001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/4258
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhao, Pengpeng
作者单位	1.Soochow Univ, Sch Comp Sci & Technol, Inst Artificial Intelligence, Suzhou 215006, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 3.Rutgers State Univ, Management Sci & Informat Syst, New Brunswick, NJ 08901 USA 4.Univ Cent Arkansas, Comp Sci Dept, Conway, AR 72035 USA 5.Suzhou Univ Sci & Technol, Sch Elect & Informat Engn, Suzhou 215009, Peoples R China
推荐引用方式 GB/T 7714	Chen, Xiaojie,Zhao, Pengpeng,Liu, Yanchi,et al. Exploiting Aesthetic Features in Visual Contents for Movie Recommendation[J]. IEEE ACCESS,2019,7:49813-49821.
APA	Chen, Xiaojie.,Zhao, Pengpeng.,Liu, Yanchi.,Zhao, Lei.,Fang, Junhua.,...&Cui, Zhiming.(2019).Exploiting Aesthetic Features in Visual Contents for Movie Recommendation.IEEE ACCESS,7,49813-49821.
MLA	Chen, Xiaojie,et al."Exploiting Aesthetic Features in Visual Contents for Movie Recommendation".IEEE ACCESS 7(2019):49813-49821.