论文信息 - The Effect of Automatic Tagging Using Multilingual Metadata for Image Retrieval

The Effect of Automatic Tagging Using Multilingual Metadata for Image Retrieval

One of multimedia content acquisition method on the Web is using tag which is describe of content. However, different words may be tagged to the same or similar subjects, because tagging is performed in an essentially arbitrary manner by a human. In addition, tags are provided in specific language from the content. This model proposes the method of automatically tagging which compensate insufficient described content by using multilanguage. Our experimental evaluations showed that users could obtain more appropriate images with this method.

Reiko Hishiyama | Arinori Takahashi

[1] Toru Ishida,et al. Language Service Management with the Language Grid , 2010, LREC.

[2] Lailatul Qadri Zakaria,et al. Modelling image semantic descriptions from web 2.0 documents using a hybrid approach , 2009, iiWAS.

[3] Andrew Smith. Using Major Events to Promote Peripheral Urban Areas: Deptford and the 2007 Tour de France , 2008 .

[4] Ivor W. Tsang,et al. Text-based image retrieval using progressive multi-instance learning , 2011, 2011 International Conference on Computer Vision.

[5] James Allan,et al. Simultaneous multilingual search for translingual information retrieval , 2008, CIKM '08.

[6] Lei Wu,et al. Tag Completion for Image Retrieval , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7] Gary R. Bradski,et al. ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[8] Robert S. Taylor. Question-Negotiation and Information Seeking in Libraries , 1968, Coll. Res. Libr..

[9] Ximena Olivares,et al. Visual diversification of image search results , 2009, WWW '09.

[10] Saurabh Varshney,et al. Improving Performance Of English-Hindi Cross Language Information Retrieval Using Transliteration Of Query Terms , 2014, ArXiv.