ABSTRACT
Social tagging provides valuable and crucial information for large-scale web image retrieval. It is ontology-free and easy to obtain; however, irrelevant tags frequently appear, and users typically will not tag all semantic objects in the image, which is also called semantic loss. To avoid noises and compensate for the semantic loss, tag recommendation is proposed in literature. However, current recommendation simply ranks the related tags based on the single modality of tag co-occurrence on the whole dataset, which ignores other modalities, such as visual correlation. This paper proposes a multi-modality recommendation based on both tag and visual correlation, and formulates the tag recommendation as a learning problem. Each modality is used to generate a ranking feature, and Rankboost algorithm is applied to learn an optimal combination of these ranking features from different modalities. Experiments on Flickr data demonstrate the effectiveness of this learning-based multi-modality recommendation strategy.
- E. Akbas and F. Yarman Vural. Automatic image annotation by ensemble of visual descriptors. CVPR'07., June 2007.Google ScholarCross Ref
- M. Ames and M. Naaman. Why we tag: motivations for annotation in mobile and online media. In CHI'07, 2007. Google ScholarDigital Library
- J. Amores, N. Sebe, and P. Radeva. Context--based object-class recognition and retrieval by generalized correlograms. IEEE Trans. Pattern Anal. Mach. Intell., 29(10):1818--1833, 2007. Google ScholarDigital Library
- Z. Bar-Yossef and M. Gurevich. Random sampling from a search engine's index. In WWW '06 Proceedings, 2006. Google ScholarDigital Library
- J. Blythe and Y. Gil. Incremental formalization of document annotations through ontology-based paraphrasing. In WWW '04, 2004. Google ScholarDigital Library
- S. Boll, P. Sandhaus, A. Scherp, and U. Westermann. Semantics, content, and structure of many for the creation of personal photo albums. In Proceedings of ACM Multimedia '07, 2007. Google ScholarDigital Library
- Y. Freund, R. Iyer, R. E. Schapire, and Y. Singer. An efficient boosting algorithm for combining preferences. In Proceedings of ICML'98, 1998. Google ScholarDigital Library
- G. Koloniari, Y. Petrakis, E. Pitoura, and T. Tsotsos. Query workload--aware overlay construction using histograms. In Proceedings of CIKM '05, 2005. Google ScholarDigital Library
- H. Li, Y. Wang, D. Zhang, M. Zhang, and E. Y. Chang. Pfp: Parallel fp-growth for query recommendation. In ACM Recommendation Systems, Lausanne, 2008. Google ScholarDigital Library
- X. Li, C. G. Snoek, and M. Worring. Learning tag relevance by neighbor voting for social image retrieval. In Proceedings of MIR '08, 2008. Google ScholarDigital Library
- J. Liu, B. Wang, M. Li, Z. Li, W. Ma, H. Lu, and S. Ma. Dual cross-media relevance model for image annotation. In Multimedia'07, 2007. Google ScholarDigital Library
- J. Mairal, F. Bach, J. Ponce, G. Sapiro, and A. Zisserman. Supervised dictionary learning, 2008.Google Scholar
- M. Naaman and R. Nair. Zonetag's collaborative tag suggestions: What is this person doing in my phone?. In IEEE Multimedia,, 2008. Google ScholarDigital Library
- G.-J. Qi, X.-S. Hua, Y. Rui, J. Tang, T. Mei, and H.-J. Zhang. Correlative multi-label video annotation. In Proceedings of ACM Multimedia'07, 2007. Google ScholarDigital Library
- Y. Qi, K. S. Candan, J. Tatemura, S. Chen, and F. Liao. Supporting olap operations over imperfectly integrated taxonomies. In SIGMOD'08 Conference, 2008. Google ScholarDigital Library
- X. Rui, M. Li, Z. Li, W.-Y. Ma, and N. Yu. Bipartite graph reinforcement model for web image annotation. In Multimedia'07, 2007. Google ScholarDigital Library
- S. Sen, S. K. Lam, A. M. Rashid, D. Cosley, D. Frankowski, J. Osterhouse, F. M. Harper, and J. Riedl. tagging, communities, vocabulary, evolution. In CSCW '06, 2006. Google ScholarDigital Library
- B. Sigurbjornsson and R. van Zwol. Flickr tag recommendation based on collective knowledge. In WWW '08, 2008. Google ScholarDigital Library
- C. G. M. Snoek, B. Huurnink, L. Hollink, M. D. Rijke, G. Schreiber, and M. Worring. Adding semantics to detectors for video retrieval. IEEE Transactions on Multimedia, 9, 2007. Google ScholarDigital Library
- C. Wang, F. Jing, L. Zhang, and H.-J. Zhang. Content-based image annotation refinement. Proceedings of CVPR 07, 2007.Google ScholarCross Ref
- L. Wu, X.-S. Hua, N. Yu, W.-Y. Ma, and S. Li. Flickr distance. Proceedings of ACM Multimedia'08, 2008. Google ScholarDigital Library
- L. Wu, M. Li, Z. Li, W.-Y. Ma, and N. Yu. Visual language modeling for image classification. Proceedings of MIR'07, 2007. Google ScholarDigital Library
- R. Yan and A. Hauprmann. Query expansion using probabilistic local feedback with application to multimedia retrieval. In Proceedings of CIKM '07, 2007. Google ScholarDigital Library
- J. Yu, J. Amores, N. Sebe, P. Radeva, and Q. Tian. Distance learning for similarity estimation. IEEE Trans. Pattern Anal. Mach. Intell., 30(3):451--462, 2008. Google ScholarDigital Library
- Y.-T. Zheng, S.-Y. Neo, T.-S. Chua, and Q. Tian. Visual synset: towards a higher-level visual representation. In Proceedings of CVPR'08, 2008.Google Scholar
Index Terms
- Learning to tag
Recommendations
Post-based collaborative filtering for personalized tag recommendation
iConference '11: Proceedings of the 2011 iConferenceSocial tagging provides a collaborative approach for information organization. The tags created by users in social tagging system not only contain rich semantic information about the described web objects, but also provide a window for information ...
Personalized PageRank vectors for tag recommendations: inside FolkRank
RecSys '11: Proceedings of the fifth ACM conference on Recommender systemsThis paper looks inside FolkRank, one of the well-known folksonomy-based algorithms, to present its fundamental properties and promising possibilities for improving performance in tag recommendations. Moreover, we introduce a new way to compute a ...
Folksonomy link prediction based on a tripartite graph for tag recommendation
Nowadays social tagging has become a popular way to annotate, search, navigate and discover online resources, in turn leading to the sheer amount of user-generated metadata. This paper addresses the problem of recommending suitable tags during ...
Comments