Multimedia Annotation Refinement Based on Contextual Information Diffusion

doi:10.16182/j.issn1004731x.joss.201611029

Abstract

Abstract: A data driven multimedia annotation refinement method based on dataset contextual information diffusion was proposed. The label contextual graph was constructed, and the label correlation can be diffused on textual label space; Multimedia object content relevant graph was constructed. Label contextual graph and multimedia object content relevant graph were mutually reinforced and formulated into a regularized framework. The proposed method incorporated both multimedia content correlation and label contextual information, and the optimization process was solved by approximate solution algorithm. The experimental results on real world dataset show that the proposed method can obviously improve the annotation performance.

Key words: multimedia annotation, semantic annotation, annotation refinement, contextual diffusion

CLC Number:

TP391

Tian Feng, Shang Fuhua. Multimedia Annotation Refinement Based on Contextual Information Diffusion[J]. Journal of System Simulation, 2016, 28(11): 2860-2867.

References 15

[1]	Jin Y H, Khan L, Wang L.Image annotations by combining multiple evidence & Wordnet[C]// Proceedings of the 13th annual ACM international conference on Multimedia. New York, USA: ACM, 2005: 706-715.
[2]	Jin YH, Khan L, Prabhakaran B.Knowledge Based Image Annotation Refinement[J]. Journal of Signal Processing Systems, 2010, 58(3): 387-406.
[3]	Wang CH, Feng J, Zhang L, et al.Image annotation refinement using random walk with restarts[C]// Proceedings of the ACM International Conference on Multimedia. New York, USA: ACM, 2006: 647-650.
[4]	Wang CH, Feng J, Zhang L, et al.Content-Based Image Annotation Refinement[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE Computer Society, 2007: 1-8.
[5]	Li XR, Snoek C.G.M, Worring M. Learning social tag relevance by neighbor voting[C]// IEEE Transactions on Multimedia. USA: IEEE, 2009: 1310-1322
[6]	Chen L, Xu D, Tsang IW.Tag-based Web Photo Retrieval Improved by Batch Mode Re-Tagging[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE Computer Society, 2010: 3440-3446.
[7]	Liu D, Hua XC, Yang LJ, et al.Tag ranking[C]// Proceedings of the Intenational World Wide Web Conference. New York, USA: ACM, 2009: 351-360.
[8]	Xu H, Wang JD, Hua XS.Tag Refinement by Regularized LDA [C]// Proceedings of the ACM Multimedia Conference. New York, USA: ACM Press, 2009: 573-576.
[9]	Zhu GY, Yan SC, Ma Y.Image tag refinement towards low-rank, content-tag prior and error sparsity [C]// Proceedings of the ACM Multimedia Conference. New York, USA: ACM Press, 2010: 461-470.
[10]	Wang H, Huang H, Ding C.Image annotation using multi-label correlated Green's function[C]// Proceedings of IEEE International Conference on Computer Vision. Piscataway, NJ, USA: IEEE Computer Society, 2009: 1-8
[11]	Wang H, Huang H, Ding C.Multi-label Feature Transform for Image Classifications [C]// Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer Press, 2010: 793-806.
[12]	Wang H, Huang H, Ding C.Image Annotation Using Bi-Relational Graph of Images and Semantic Labels[C]// IEEE Conference on Computer Vision and Pattern Recognition, Piscataway, NJ, USA: IEEE Computer Society, 2011: 793-800.
[13]	Xiang Y, Zhou XD, Liu ZT, et al.Semantic context modeling with maximal margin conditional random fields for automatic image annotation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE Computer Society, 2010: 3368-3375.
[14]	Chua TS, Tang JH, Hong RH.NUS-WIDE: A real-world web image database from national university of singapore[C]// Proceedings of ACM Conference on Image and Video Retrieval. New York, USA: ACM, 2009: 1-9.
[15]	Huiskes M J, Lew M S.The MIR Flickr retrieval evaluation[C]// Proceedings of the ACM Intenational Conference on Multimedia Information Retrieval. New York, USA: ACM, 2008: 39-43.