帮助 关于我们

返回检索结果

A novel cross-modal hashing algorithm based on multimodal deep learning

查看参考文献36篇

Qu Wen 1   Wang Daling 2   Feng Shi 2   Zhang Yifei 2   Yu Ge 2 *  
文摘 With the growing popularity of multimodal data on the Web, cross-modal retrieval on large-scale multimedia databases has become an important research topic. Cross-modal retrieval methods based on hashing assume that there is a latent space shared by multimodal features. To model the relationship among heterogeneous data, most existing methods embed the data into a joint abstraction space by linear projections. However, these approaches are sensitive to noise in the data and are unable to make use of unlabeled data and multimodal data with missing values in real-world applications. To address these challenges, we proposed a novel multimodal deep-learning-based hash (MDLH) algorithm. In particular, MDLH uses a deep neural network to encode heterogeneous features into a compact common representation and learns the hash functions based on the common representation. The parameters of the whole model are fine-tuned in a supervised training stage. Experiments on two standard datasets show that the method achieves more effective results than other methods in cross-modal retrieval.
来源 Science China. Information Science ,2017,60(9):092104-1-092104-14 【核心库】
DOI 10.1007/s11432-015-0902-2
关键词 hashing ; cross-modal retrieval ; cross-modal hashing ; multimodal data analysis ; deep learning
地址

1. School of Information Science and Engineering, Northeastern University, Shenyang, 110819  

2. School of Information Science and Engineering, Northeastern University, Key Laboratory of Medical Image Computing, MOE, Shenyang, 110819

语种 英文
文献类型 研究性论文
ISSN 1674-733X
学科 自动化技术、计算机技术
基金 国家自然科学基金 ;  Fundamental Research Funds for the Central Universities of China
文献收藏号 CSCD:6087845

参考文献 共 36 共2页

1.  Chen C. Web media semantic concept retrieval via tag removal and model fusion. ACM Trans Intel Syst Technol,2013,4:478-488 CSCD被引 1 次    
2.  Leung C H C. Intelligent social media indexing and sharing using an adaptive indexing search engine. ACM Trans Intel Syst Technol,2012,3:338-343 CSCD被引 1 次    
3.  Zhang R M. Bit-scalable deep hashing with regularized similarity learning for image retrieval and person re-identification. IEEE Trans Imag Process,2015,24:4766-4779 CSCD被引 25 次    
4.  Nie X S. Robust video hashing based on representative-dispersive frames. Sci China Inf Sci,2013,56:068104 CSCD被引 3 次    
5.  Xiang S J. Perceptual video hashing robust against geometric distortions. Sci China Inf Sci,2012,55:1520-1527 CSCD被引 4 次    
6.  Datar M. Locality-sensitive hashing scheme based on p-stable distributions. Proceedings of ACM Symposium on Computational Geometry,2004:253-262 CSCD被引 2 次    
7.  Weiss Y. Spectral hashing. Proceedings of 22nd Annual Conference on Neural Information Processing Systems,2008:1753-1760 CSCD被引 1 次    
8.  Zhen Y. A probabilistic model for multimodal hash function learning. Proceedings of the 18th ACM SIGKDD Conference on Knowledge Discovery and Data Mining,2012:940-948 CSCD被引 1 次    
9.  Zhu X F. Linear cross-modal hashing for efficient multimedia search. Proceedings of the 21st ACM International Conference on Multimedia,2013:143-152 CSCD被引 8 次    
10.  Yu Z. Discriminative coupled dictionary hashing for fast cross-media retrieval. Proceedings of the 37th Annual ACM SIGIR Conference,2014:395-404 CSCD被引 1 次    
11.  Bronstein M. Data fusion through cross-modality metric learning using similarity-sensitive hashing. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2010:3594-3601 CSCD被引 1 次    
12.  Kumar S. Learning hash functions for cross-view similarity search. Proceedings of the 25th International Joint Conference on Artificial Intelligence,2011:1360-1365 CSCD被引 1 次    
13.  Hu Y. Iterative multi-view hashing for cross media indexing. Proceedings of the 22nd ACM International Conference on Multimedia,2014:527-536 CSCD被引 1 次    
14.  Song J K. Inter-media hashing for large-scale retrieval from heterogeneous data sources. Proceedings of the ACM SIGMOD International Conference on Management of Data,2013:785-796 CSCD被引 4 次    
15.  Wu B T. Quantized correlation hashing for fast cross-modal search. Proceedings of International Joint Conference on Artificial Intelligence,2015:3946-3952 CSCD被引 1 次    
16.  Kang Y. Deep learning to hash with multiple representations. Proceedings of IEEE International Conference on Data Mining,2012:930-935 CSCD被引 1 次    
17.  Wang D X. Deep multimodal hashing with orthogonal regularization. Proceedings of International Joint Conference on Artificial Intelligence,2015:2291-2297 CSCD被引 1 次    
18.  Wang Q F. Learning to hash on partial multimodal data. Proceedings of International Joint Conference on Artificial Intelligence,2015:3904-3910 CSCD被引 1 次    
19.  Dahl G E. Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans Audio Speech,2012,20:30-42 CSCD被引 140 次    
20.  Krizhevsky A. Imagenet classification with deep convolutional neural networks. Proceedings of Annual Conference on Neural Information Processing Systems,2012:1106-1114 CSCD被引 1 次    
引证文献 7 篇

1 Jin Junwei Discriminative graph regularized broad learning system for image recognition Science China. Information Science,2018,61(11):112209-1-112209-14
CSCD被引 8 次

2 郭田德 逐层数据再表达的前后端融合学习的理论及其模型和算法 中国科学. 信息科学,2019,49(6):739-759
CSCD被引 1 次

显示所有7篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号