{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T20:38:40Z","timestamp":1761597520945},"reference-count":103,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2014,6,12]],"date-time":"2014-06-12T00:00:00Z","timestamp":1402531200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Inf Syst"],"published-print":{"date-parts":[[2014,10]]},"DOI":"10.1007\/s10844-014-0323-6","type":"journal-article","created":{"date-parts":[[2014,6,11]],"date-time":"2014-06-11T01:45:29Z","timestamp":1402451129000},"page":"271-306","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Image understanding and the web: a state-of-the-art review"],"prefix":"10.1007","volume":"43","author":[{"given":"Fariza","family":"Fauzi","sequence":"first","affiliation":[]},{"given":"Mohammed","family":"Belkhatir","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2014,6,12]]},"reference":[{"issue":"3","key":"323_CR1","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1017\/S1351324902002887","volume":"8","author":"S Ait-Mokhtar","year":"2002","unstructured":"Ait-Mokhtar, S., Chanod, J.-P., Roux, C. (2002). Robustness beyond shallowness: incremental deep parsing. Natural Language Engineering, 8(3), 121\u2013144.","journal-title":"Natural Language Engineering"},{"key":"323_CR3","unstructured":"Alcic, S., & Conrad, S. (2011). A clustering-based approach to web image context extraction. In Proceedings of the third international conferences on advances in multimedia (pp. 74\u201379)."},{"key":"323_CR4","unstructured":"Anick, P.G. (1991). Integrating \u201cNatural Language\u201d and Boolean query: an application of computational linguistics to full-text information retrieval. In Proceedings of the AAAI-91 workshop on natural language text retrieval."},{"key":"323_CR5","doi-asserted-by":"crossref","unstructured":"Arasu, A., & Garcia-Molina, H. (2003). Extracting structured data from web pages. In Proceedings of the 2003 ACM SIGMOD international conference on management of data (pp. 337\u2013348).","DOI":"10.1145\/872757.872799"},{"issue":"4","key":"323_CR6","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1177\/016555159702300403","volume":"23","author":"LH Armitage","year":"1997","unstructured":"Armitage, L.H., & Enser, P.G.B. (1997). Analysis of user need in image archives. Journal of Information Science, 23(4), 287\u2013299.","journal-title":"Journal of Information Science"},{"key":"323_CR7","doi-asserted-by":"crossref","unstructured":"Aslandogan, Y.A., & Yu, C.T. (2000). Evaluating strategies and systems for content based indexing of person images on the web. In Proceedings of the ACM international conference on multimedia (pp. 313\u2013321).","DOI":"10.1145\/354384.354514"},{"key":"323_CR8","doi-asserted-by":"crossref","unstructured":"Aslandogan, Y.A., Thier, C., Yu, C., Zou, J., Rishe, N. (1997). Using semantic contents and WordNet in image retrieval. In Proceedings of SIGIR.","DOI":"10.1145\/258525.258591"},{"key":"323_CR10","unstructured":"BBC News (2009). Microsoft and Yahoo Seal Web Deal. BBC News. Last updated date: 29 July 2009. Retrieved from http:\/\/news.bbc.co.uk\/2\/hi\/business\/8174763.stm ."},{"key":"323_CR13","doi-asserted-by":"crossref","unstructured":"Blaschko, M.B., & Lampert, C.H. (2008). Correlational spectral clustering. In IEEE conference on computer vision and pattern recognition 2008. CVPR 2008 (pp. 1\u20138).","DOI":"10.1109\/CVPR.2008.4587353"},{"key":"323_CR14","unstructured":"Cai, D., Yu, S., Wen, J.-R. (2003). VIPS?: a vision-based page segmentation algorithm."},{"key":"323_CR15","doi-asserted-by":"crossref","unstructured":"Cai, D., He, X., Li, Z., Ma, W.Y., Wen, J.R. (2004). Hierarchical clustering of WWW image search results using visual, textual and link information. In Proceedings of the 12th annual ACM international conference on multimedia (pp. 952\u2013959).","DOI":"10.1145\/1027527.1027747"},{"key":"323_CR17","doi-asserted-by":"crossref","unstructured":"Chakrabarti, D., Kumar, R., Punera, K. (2008). A graph-theoretic approach to web page segmentation. In Proceedings of the 17th international conference on World Wide Web (pp. 377\u2013386).","DOI":"10.1145\/1367497.1367549"},{"issue":"10","key":"323_CR19","doi-asserted-by":"crossref","first-page":"1411","DOI":"10.1109\/TKDE.2006.152","volume":"18","author":"C-H Chang","year":"2006","unstructured":"Chang, C.-H., Kayed, M., Girgis, M. R., Shaalan, K.F. (2006). A survey of web information extraction systems. IEEE Transactions on Knowledge and Data Engineering, 18(10), 1411\u20131428.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"323_CR20","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wenyin, L., Hu, C., Li, M., Zhang, H.J. (2001). Ifind: a web image search engine. In Proceedings of ACM SIGIR (p. 450).","DOI":"10.1145\/383952.384091"},{"key":"323_CR21","doi-asserted-by":"crossref","unstructured":"Chen, Y., Ma, W. Y., Zhang, H.J. (2003). Detecting web page structure for adaptive viewing on small form factor devices. In Proceedings of the 12th international conference on World Wide Web (pp. 20\u201324).","DOI":"10.1145\/775152.775184"},{"issue":"6","key":"323_CR22","doi-asserted-by":"crossref","first-page":"498","DOI":"10.1002\/asi.10237","volume":"54","author":"Y Choi","year":"2003","unstructured":"Choi, Y., & Rasmussen, E.M. (2003). Searching for images: the analysis of users\u2019 queries for image retrieval in American History. Journal of the American Society for Information Science and Technology, 54(6), 498\u2013511.","journal-title":"Journal of the American Society for Information Science and Technology"},{"issue":"1","key":"323_CR23","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1002\/aris.1440370103","volume":"37","author":"GG Chowdhury","year":"2003","unstructured":"Chowdhury, G. G. (2003). Natural language processing. Annual Review of Information Science and Technology, 37(1), 51\u201389.","journal-title":"Annual Review of Information Science and Technology"},{"issue":"1","key":"323_CR24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1002\/meet.14504701424","volume":"47","author":"E Chung","year":"2010","unstructured":"Chung, E., & Yoon, J. (2010). An exploratory analysis on unsuccessful image searches. Proceedings of the American Society for Information Science and Technology, 47(1), 1\u20132.","journal-title":"Proceedings of the American Society for Information Science and Technology"},{"issue":"4","key":"323_CR25","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1109\/TKDE.2004.1269666","volume":"16","author":"TAS Coelho","year":"2004","unstructured":"Coelho, T.A.S., Calado, P.P., Souza, L.V., Ribeiro-Neto, B. (2004). Using multiple evidence ranking. IEEE Transactions on Knowledge and Data Engineering, 16(4), 408\u2013417.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"8","key":"323_CR26","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1016\/S0306-4379(98)00028-3","volume":"23","author":"V Crescenzi","year":"1998","unstructured":"Crescenzi, V., & Mecca, G. (1998). Grammars have exceptions. Information Systems, 23(8), 539\u2013565.","journal-title":"Information Systems"},{"key":"323_CR28","unstructured":"Crescenzi, V., Mecca, G., Merialdo, P. (2001). Roadrunner: towards automatic data extraction from large web sites. In Proceedings of the 27th VLDB conference (pp. 109\u2013118)."},{"issue":"2","key":"323_CR29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1348246.1348248","volume":"40","author":"R Datta","year":"2008","unstructured":"Datta, R., Joshi, D., Li, J., Wang, J.Z. (2008). Image retrieval: ideas, influences, and trends of the new age. ACM Computing Surveys, 40(2), 1\u201360.","journal-title":"ACM Computing Surveys"},{"key":"323_CR30","first-page":"449","volume":"6","author":"MC De Marneffe","year":"2006","unstructured":"De Marneffe, M.C., Maccartney, B., Manning, C.D. (2006). Generating typed dependency parses from phrase structure parses. Proceedings of LREC, 6, 449\u2013454.","journal-title":"Proceedings of LREC"},{"key":"323_CR31","first-page":"1000","volume":"45","author":"K Deschacht","year":"2007","unstructured":"Deschacht, K., & Moens, M.F. (2007). Text analysis for automatic image annotation. Annual Meeting-Association for Computational Linguistics, 45, 1000.","journal-title":"Annual Meeting-Association for Computational Linguistics"},{"key":"323_CR32","doi-asserted-by":"crossref","unstructured":"Deschacht, K., & Moens, M.F. (2008). Finding the best picture: cross-media retrieval of content. In Proceedings of the European conference on advances in information retrieval (pp. 539\u2013546).","DOI":"10.1007\/978-3-540-78646-7_53"},{"issue":"2","key":"323_CR33","doi-asserted-by":"crossref","first-page":"229","DOI":"10.3758\/BF03203370","volume":"23","author":"ST Dumais","year":"1991","unstructured":"Dumais, S.T. (1991). Improving the retrieval of information from external sources. Behavior Research Methods, Instruments & Computers, 23(2), 229\u2013236.","journal-title":"Behavior Research Methods, Instruments & Computers"},{"issue":"1","key":"323_CR34","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/S0031-3203(01)00038-3","volume":"35","author":"J Eakins","year":"2002","unstructured":"Eakins, J. (2002). Towards intelligent image retrieval. Pattern Recognition, 35(1), 3\u201314.","journal-title":"Pattern Recognition"},{"key":"323_CR35","unstructured":"Evans, S. (2009). Google launches \u2018Similar Images\u2019 search tool. Computer Business Review. Last updated date: 28 October 2009. Retrieved from http:\/\/www.cbronline.com\/news\/google\\launches\\similar\\images\\search\\tool\\281009 ."},{"issue":"5","key":"323_CR37","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1016\/j.ijhcs.2010.01.001","volume":"68","author":"F Fauzi","year":"2010","unstructured":"Fauzi, F., & Belkhatir, M. (2010). A user study to investigate semantically relevant contextual information of WWW images. International Journal of Human Computer Studies, 68(5), 270\u2013287.","journal-title":"International Journal of Human Computer Studies"},{"key":"323_CR39","unstructured":"Feng, Y., & Lapata, M. (2008). Automatic image annotation using auxiliary text information. In Proceedings of the 46th annual meeting of the association for computational linguistics: human language technologies (pp. 272\u2013280)."},{"key":"323_CR40","unstructured":"Feng, Y., & Lapata, M. (2010). Topic models for image annotation and text illustration. In Proceedings of the 2010 annual conference of the North American chapter of the association for computational linguistics (pp. 831\u2013839)."},{"key":"323_CR41","doi-asserted-by":"crossref","unstructured":"Feng, H., Shi, R., Chua, T.-S. (2004). A bootstrapping framework for annotating and retrieving WWW images. In Proceedings of the 12th annual ACM international conference on multimedia (p. 960).","DOI":"10.1145\/1027527.1027748"},{"key":"323_CR43","unstructured":"Frankel, C., Swain, M. J., Athitsos, V. (1996). Webseer?: an image search engine for the World Wide Web. World Wide Web Internet and Web Information Systems, 1\u201324."},{"key":"323_CR45","doi-asserted-by":"crossref","unstructured":"Gao, B., Liu, T. Y., Qin, T., Zheng, X., Cheng, Q.S., Ma, W.Y. (2005). Web image clustering by consistent utilization of visual features and surrounding texts. In Proceedings of the 13th annual ACM international conference on multimedia (pp. 112\u2013121).","DOI":"10.1145\/1101149.1101167"},{"key":"323_CR200","doi-asserted-by":"crossref","unstructured":"Ghoshal, A., Ircing, P., Khudanpur, S. (2005). Hidden Markov models for automatic annotation and contentbased retrieval of images and video. In Proceedings of the 28th annual international ACM SIGIR conference on research and development in information retrieval (SIGIR \u201905). (pp. 544\u2013551) New York, NY: ACM. USA,. doi: 10.1145\/1076034.1076127 .","DOI":"10.1145\/1076034.1076127"},{"issue":"2","key":"323_CR47","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1007\/s10115-005-0231-8","volume":"10","author":"ZU Gong","year":"2006","unstructured":"Gong, Z.U., Hou, L.H., Cheang, C.W. (2006). Web image indexing by using associated texts. Knowledge and Information Systems, 10(2), 243\u2013264.","journal-title":"Knowledge and Information Systems"},{"issue":"2","key":"323_CR48","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/S0306-4573(00)00033-9","volume":"37","author":"A Goodrum","year":"2001","unstructured":"Goodrum, A., & Spink, A. (2001). Image searching on the excite web search engine. Information Processing & Management, 37(2), 295\u2013311.","journal-title":"Information Processing & Management"},{"key":"323_CR49","unstructured":"Hammer, J., Garcia-Molina, H., Cho, J., Aranha, R., Crespo, A. (1997). Extracting semistructured information from the web. World Wide Web Internet and Web Information Systems, 1\u20138."},{"issue":"2","key":"323_CR51","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/1230812.1230816","volume":"3","author":"X He","year":"2007","unstructured":"He, X., Cai, D., Wen, J.R., Ma, W.Y., Zhang, H.J. (2007). Clustering and searching WWW images using link and page layout analysis. ACM Transactions on Multimedia Computing, Communications, and Applications, 3(2), 10.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"issue":"4","key":"323_CR52","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1145\/1121949.1121983","volume":"49","author":"MA Hearst","year":"2006","unstructured":"Hearst, M.A. (2006). Clustering versus faceted categories for information exploration. Communications of the ACM, 49(4), 59\u201361.","journal-title":"Communications of the ACM"},{"issue":"5","key":"323_CR53","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1016\/j.ijhcs.2004.03.002","volume":"61","author":"L Hollink","year":"2004","unstructured":"Hollink, L., Schreiber, A. T., Wielinga, B. J., Worring, M. (2004). Classification of user image descriptions. International Journal of Human-Computer Studies, 61(5), 601\u2013626.","journal-title":"International Journal of Human-Computer Studies"},{"issue":"2","key":"323_CR54","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1016\/j.datak.2009.10.002","volume":"69","author":"JL Hong","year":"2010","unstructured":"Hong, J.L., Siew, E.-G., Egerton, S. (2010). Information extraction for search engines using fast heuristic techniques. Data & Knowledge Engineering, 69(2), 169\u2013196.","journal-title":"Data & Knowledge Engineering"},{"key":"323_CR55","doi-asserted-by":"crossref","unstructured":"Hua, Z., Wang, X. J., Liu, Q., Lu, H. (2005). Semantic knowledge extraction and annotation for web images. In Proceedings of the 13th annual ACM international conference on multimedia (pp. 467\u2013470).","DOI":"10.1145\/1101149.1101253"},{"key":"323_CR56","doi-asserted-by":"crossref","unstructured":"Hughes, A., Wilkens, T., Wildemuth, B., Marchionini, G. (2003). Text or pictures? An eyetracking study of how people view digital video surrogates. In Proceedings of the international conference on image and video retrieval (pp. 271\u2013280).","DOI":"10.1007\/3-540-45113-7_27"},{"key":"323_CR57","unstructured":"Inoue, M. (2004). On the need for annotation-based image retrieval. In Proceedings of the workshop on information retrieval in context (Irix), Sheffield, UK (pp. 44\u201346)."},{"key":"323_CR58","doi-asserted-by":"crossref","first-page":"3","DOI":"10.2201\/NiiPi.2009.6.2","volume":"6","author":"M Inoue","year":"2009","unstructured":"Inoue, M. (2009). Image retrieval: research and use in the information explosion. Progress in Informatics, 6, 3.","journal-title":"Progress in Informatics"},{"key":"323_CR60","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1117\/12.373443","volume":"3964","author":"A Jaimes","year":"2000","unstructured":"Jaimes, A., & Chang, S.F. (2000). A conceptual framework for indexing visual information at multiple levels. IS&T\/SPIE Internet Imaging, 3964, 2\u201315.","journal-title":"IS&T\/SPIE Internet Imaging"},{"key":"323_CR62","doi-asserted-by":"crossref","unstructured":"Jin, Y., Khan, L., Wang, L., Awad, M. (2005). Image annotations by combining multiple evidence & wordnet. In Proceedings of the 13th annual ACM international conference on multimedia (pp. 706\u2013715).","DOI":"10.1145\/1101149.1101305"},{"key":"323_CR63","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1016\/0020-0271(73)90043-0","volume":"9","author":"KS Jones","year":"1973","unstructured":"Jones, K.S. (1973). Index term weighting. Information Storage and Retrieval, 9, 619\u2013633.","journal-title":"Information Storage and Retrieval"},{"issue":"12","key":"323_CR64","doi-asserted-by":"crossref","first-page":"1346","DOI":"10.1002\/asi.20229","volume":"56","author":"C J\u00f6rgensen","year":"2005","unstructured":"J\u00f6rgensen, C., & J\u00f6rgensen, P. (2005). Image querying by image professionals. Journal of the American Society for Information Science and Technology, 56(12), 1346\u20131359.","journal-title":"Journal of the American Society for Information Science and Technology"},{"key":"323_CR65","doi-asserted-by":"crossref","unstructured":"Joshi, P. M., & Liu, S. (2009). Web document text and images extraction using DOM analysis and natural language processing. In Proceedings of the 9th ACM symposium on document engineering (p. 218).","DOI":"10.1145\/1600193.1600241"},{"issue":"2","key":"323_CR66","doi-asserted-by":"crossref","first-page":"980","DOI":"10.1109\/TCE.2010.5506029","volume":"56","author":"J Kang","year":"2010","unstructured":"Kang, J., Yang, J., Choi, J. (2010). Repetition-based web page segmentation by detecting tag patterns for small-screen devices. IEEE Transactions on Consumer Electronics, 56(2), 980\u2013986.","journal-title":"IEEE Transactions on Consumer Electronics"},{"issue":"5","key":"323_CR67","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1109\/TKDE.2005.84","volume":"17","author":"H-Y Kao","year":"2005","unstructured":"Kao, H.-Y., Ho, J.-M., Chen, M.-S. (2005). WISDOM?: Web intra-page informative structure mining based on document object model. IEEE Transactions on Knowledge and Data Engineering, 17(5), 614\u2013627.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"323_CR68","unstructured":"Katz, G., & Giesbrecht, E. (2006). Automatic identification of non-compositional multi-word expressions using latent semantic analysis. In Proceedings of the workshop on multiword expressions: identifying and exploiting underlying properties (pp. 12\u201319)."},{"key":"323_CR69","doi-asserted-by":"crossref","unstructured":"Kennedy, L.S., & Naaman, M. (2008). Generating diverse and representative image search results for landmarks. In Proceedings of the 17th international conference on World Wide Web (pp. 297\u2013306).","DOI":"10.1145\/1367497.1367539"},{"issue":"1","key":"323_CR70","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1145\/1013208.1013210","volume":"36","author":"ML Kherfi","year":"2004","unstructured":"Kherfi, M.L., Ziou, D., Bernardi, A. (2004). Image retrieval from the World Wide Web: issues, techniques, and systems. ACM Computing Surveys (CSUR), 36(1), 35\u201367.","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"323_CR72","doi-asserted-by":"crossref","unstructured":"Kohlschutter, C., & Nejdl, W. (2008). A densitometric approach to web page segmentation. In Proceeding of the 17th ACM conference on information and knowledge management.","DOI":"10.1145\/1458082.1458237"},{"key":"323_CR73","doi-asserted-by":"crossref","unstructured":"La Cascia, M., Sethi, S., Sclaroff, S. (1998). Combining textual and visual cues for content-based image retrieval on the World Wide Web. In Proceedings of IEEE workshop on content-based access of image and video libraries, 1998 (pp. 24\u201328).","DOI":"10.1109\/IVL.1998.694480"},{"key":"323_CR74","doi-asserted-by":"crossref","unstructured":"Larson, M., Kofler, C., Hanjalic, A. (2011). Reading between the tags to predict real-world size-class for visually depicted objects in images. In Proceedings of ACM multimedia.","DOI":"10.1145\/2072298.2072335"},{"key":"323_CR75","doi-asserted-by":"crossref","unstructured":"Leong, C.W., & Mihalcea, R. (2009). Explorations in automatic image annotation using textual features. In Proceedings of the third linguistic annotation workshop on - ACL-IJCNLP \u201909 (pp. 56\u201359).","DOI":"10.3115\/1698381.1698390"},{"key":"323_CR76","unstructured":"Leong, C.W., Mihalcea, R., Hassan, S. (2010). Text mining for automatic image tagging. In Proceedings of the 23rd international conference on computational linguistics (pp. 647\u2013655)."},{"issue":"11","key":"323_CR77","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1109\/2.881694","volume":"33","author":"MS Lew","year":"2000","unstructured":"Lew, M. S. (2000). Next-generation web searches for visual content. IEEE Computer, 33(11), 46\u201353.","journal-title":"IEEE Computer"},{"key":"323_CR78","doi-asserted-by":"crossref","unstructured":"Li, J., Liu, T., Wang, W., Gao, W. (2006). A broadcast model for web image annotation. In Proceedings of the 7th pacific rim conference on multimedia.","DOI":"10.1007\/11922162_29"},{"key":"323_CR80","doi-asserted-by":"crossref","unstructured":"Lin, D. (1999). Automatic identification of non-compositional phrases. In Proceedings of the 37th annual meeting of the association for computational linguistics on computational linguistics (pp. 317\u2013324).","DOI":"10.3115\/1034678.1034730"},{"issue":"1","key":"323_CR82","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1016\/j.patcog.2006.04.045","volume":"40","author":"Y Liu","year":"2007","unstructured":"Liu, Y., Zhang, D., Lu, G., Ma, W.-Y. (2007). A survey of content-based image retrieval with high-level semantics. Pattern Recognition, 40(1), 262\u2013282.","journal-title":"Pattern Recognition"},{"issue":"2","key":"323_CR83","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1016\/j.patcog.2008.04.012","volume":"42","author":"J Liu","year":"2009","unstructured":"Liu, J., Li, M., Liu, Q., Lu, H., Ma, S. (2009). Image annotation via graph learning. Pattern Recognition, 42(2), 218\u2013228.","journal-title":"Pattern Recognition"},{"issue":"3","key":"323_CR84","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1109\/TKDE.2009.109","volume":"22","author":"W Liu","year":"2010","unstructured":"Liu, W., Meng, X., Meng, W. (2010). Vide: a vision-based approach for deep web data extraction. IEEE Transactions on Knowledge and Data Engineering, 22(3), 447\u2013460.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"323_CR85","doi-asserted-by":"crossref","unstructured":"Lu, Y., Hu, C., Zhu, X., Zhang, H.J., Yang, Q. (2000). A unified framework for semantics and feature based relevance feedback in image retrieval systems. In Proceedings of the 8th annual ACM international conference on multimedia (pp. 31\u201337).","DOI":"10.1145\/354384.354403"},{"key":"323_CR86","doi-asserted-by":"crossref","unstructured":"Luo, J., Yu, J., Joshi, D., Hao, W. (2008). Event recognition: viewing the world with a third eye. In Proceedings of the 16th ACM international conference on multimedia (pp. 1071\u20131080).","DOI":"10.1145\/1459359.1459574"},{"key":"323_CR89","doi-asserted-by":"crossref","unstructured":"Meghini, C., Sebastiani, F., Straccia, U. (2001). A model for multimedia information retrieval. Journal of the ACM (JACM), 48(5).","DOI":"10.1145\/502102.502103"},{"key":"323_CR92","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1023\/A:1019248722478","volume":"2","author":"S Mukherjea","year":"1999","unstructured":"Mukherjea, S., & Hirata, K. (1999). Amore: a World Wide Web image retrieval engine. World Wide Web, 2, 115\u2013132.","journal-title":"World Wide Web"},{"key":"323_CR94","doi-asserted-by":"crossref","unstructured":"Olivares, X., Ciaramita, M., Van Zwol, R. (2008). Boosting image retrieval through aggregating search results based on visual annotations. In Proceedings of ACM Multimedia.","DOI":"10.1145\/1459359.1459386"},{"key":"323_CR95","unstructured":"Ortega-Binderberger, M., Mehrotra, S., Chakrabarti, K., Porkaew, K. (2000). Webmars: a multimedia search engine for full document retrieval and cross media browsing. In Proceedings of the sixth international workshop on advances in multimedia information systems (pp. 72\u201381)."},{"key":"323_CR98","unstructured":"Panofsky, E. (1962). Studies in iconology. New York: Harper & Row."},{"key":"323_CR100","unstructured":"Pedersen, T., & Kolhatkar, V. (2009). Wordnet:: Senserelate:: Allwords: a broad coverage word sense tagger that maximizes semantic relatedness. In Proceedings of human language technologies: the 2009 annual conference of the North American chapter of the association for computational linguistics, companion volume: demonstration session (pp. 17\u201320)."},{"key":"323_CR101","unstructured":"Pnueli, A., Bergman, R., Schein, S., Barkol, O. (2009). Web page layout via visual segmentation. Retrieved from http:\/\/www.davidaitken.com\/hplabs.pdf ."},{"issue":"3","key":"323_CR102","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1177\/0165551507084140","volume":"34","author":"H-T Pu","year":"2008","unstructured":"Pu, H.-T. (2008). An analysis of failed queries for web image retrieval. Journal of Information Science, 34(3), 275\u2013289.","journal-title":"Journal of Information Science"},{"key":"323_CR103","doi-asserted-by":"crossref","unstructured":"Quack, T., Leibe, B., Van Gool, L. (2008). World-scale mining of objects and events from community photo collections. In Proceedings of the international conference on content-based image and video retrieval (pp. 47\u201356).","DOI":"10.1145\/1386352.1386363"},{"key":"323_CR104","doi-asserted-by":"crossref","unstructured":"Rege, M., Dong, M., Hua, J. (2008). Graph theoretical framework for simultaneously integrating visual and textual features for efficient web image clustering. In Proceedings of the 17th international conference on World Wide Web (p. 317).","DOI":"10.1145\/1367497.1367541"},{"issue":"5","key":"323_CR106","doi-asserted-by":"crossref","first-page":"1741","DOI":"10.1016\/j.ipm.2008.03.004","volume":"44","author":"A Rorissa","year":"2008","unstructured":"Rorissa, A. (2008). User-generated descriptions of individual images versus labels of groups of images: a comparison using basic level theory. Information Processing & Management, 44(5), 1741\u20131753.","journal-title":"Information Processing & Management"},{"issue":"11","key":"323_CR107","doi-asserted-by":"crossref","first-page":"2230","DOI":"10.1002\/asi.21401","volume":"61","author":"A Rorissa","year":"2010","unstructured":"Rorissa, A. (2010). A comparative study of Flickr tags and index terms in a general image collection. Journal of the American Society for Information Science and Technology, 61(11), 2230\u20132242.","journal-title":"Journal of the American Society for Information Science and Technology"},{"issue":"3","key":"323_CR108","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/S0169-023X(00)00051-3","volume":"36","author":"A Sahuguet","year":"2001","unstructured":"Sahuguet, A., & Azavant, F. (2001). Building intelligent web applications using lightweight wrappers. Data & Knowledge Engineering, 36(3), 283\u2013316.","journal-title":"Data & Knowledge Engineering"},{"key":"323_CR109","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1006\/cviu.1999.0765","volume":"75","author":"S Sclaroff","year":"1999","unstructured":"Sclaroff, S., Cascia, M.L., Sethi, S. (1999). Unifying textual and visual cues for content-based image retrieval on the World Wide Web. Computer Vision and Image, 75, 86\u201398.","journal-title":"Computer Vision and Image"},{"issue":"3","key":"323_CR110","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1300\/J104v06n03_04","volume":"6","author":"S Shatford","year":"1986","unstructured":"Shatford, S. (1986). Analyzing the subject of a picture: a theoretical approach. Cataloging & Classification Quarterly, 6(3), 39\u201362.","journal-title":"Cataloging & Classification Quarterly"},{"key":"323_CR111","doi-asserted-by":"crossref","unstructured":"Shen, H.T., Ooi, B.C., Tan, K.-L. (2000). Giving meanings to WWW images. In Proceedings of the 8th annual ACM international conference on multimedia (pp. 39\u2013s47).","DOI":"10.1145\/354384.376098"},{"key":"323_CR112","doi-asserted-by":"crossref","unstructured":"Simon, I., Snavely, N., Seitz, S.M. (2007). Scene summarization for online image collections. In Proceedings of IEEE 11th international conference on computer vision (pp. 1\u20138).","DOI":"10.1109\/ICCV.2007.4408863"},{"key":"323_CR113","unstructured":"Slawski, B. (2008). Microsoft granted patent on vision-based document segmentation (VIPS). Internet Marketing and Search Engine Optimization (SEO) Services, Consulting, and Research. Retrieved from http:\/\/www.seobythesea.com\/2008\/09\/microsoft-granted-patent-on-vision-based-document-segmentation-vips\/ ."},{"issue":"12","key":"323_CR114","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.1109\/34.895972","volume":"22","author":"AWM Smeulders","year":"2000","unstructured":"Smeulders, A.W.M., Worring, M., Santini, S., Gupta, A., Jain, R. (2000). Content-based image retrieval at the end of the early years. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(12), 1349\u20131380.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"323_CR115","unstructured":"Smith, J.R., & Chang, S.F. (1997). An image and video search engine for the world-wide web. In Symposium on electronic imaging: science and technology-storage & retrieval for image and video databases V."},{"key":"323_CR116","doi-asserted-by":"crossref","unstructured":"Spengler, A., & Gallinari, P. (2009). Learning to extract content from news web pages. In Proceedings of the 2009 international conference on advanced information networking and applications workshop (pp. 709\u2013714).","DOI":"10.1109\/WAINA.2009.97"},{"key":"323_CR118","doi-asserted-by":"crossref","unstructured":"Tang, J., Yan, S., Hong, R., Qi, G. (2009). Inferring semantic concepts from community-contributed images and noisy tags. In Proceedings of the 17th ACM international conference on multimedia (p. 223).","DOI":"10.1145\/1631272.1631305"},{"key":"323_CR300","unstructured":"Tian, G., Guan, G., Wang, Z., Feng, D. (2012). What is Happening: Annotating Images with Verbs. In: Proceedings of the 20th ACM International Conference on Multimedia-MULTIMEDIA 2012 (pp. 1077\u20131080)."},{"key":"323_CR120","doi-asserted-by":"crossref","unstructured":"Toyama, K., Logan, R., Roseway, A. (2003). Geographic location tags on digital images. In Proceedings of the 11th ACM international conference on multimedia-MULTIMEDIA 2003 (pp. 156\u2013166).","DOI":"10.1145\/957013.957046"},{"key":"323_CR301","unstructured":"Tryfou, G., & Tsapatsoulis, N. (2012). Extraction of Web Image Information: Semantic or Visual Cues? In Proceedings of the 8th Artificial Intelligence Applications and Innovations Conference-AIAI 2012, (pp. 368\u2013373)."},{"key":"323_CR121","doi-asserted-by":"crossref","unstructured":"Wang, J., & Lochovsky, F.H. (2003). Data extraction and label assignment for web databases. In Proceedings of the 12th international conference on World Wide Web (pp. 187\u2013196).","DOI":"10.1145\/775152.775179"},{"key":"323_CR201","doi-asserted-by":"crossref","unstructured":"Wang X.-J., Ma W.-Y., Xue G.-R., Li X. (2004). Multi-model similarity propagation and its application for web image retrieval. In Proceedings of the 12th annual ACM international conference on multimedia. New York, doi: 10.1145\/1027527.1027746 .","DOI":"10.1145\/1027527.1027746"},{"key":"323_CR122","doi-asserted-by":"crossref","unstructured":"Wang, X. J., Ma, W. Y., Zhang, L., Li, X. (2005). Iteratively clustering web images based on link and attribute reinforcements. In Proceedings of the ACM international conference on multimedia (pp. 122\u2013131).","DOI":"10.1145\/1101149.1101168"},{"key":"323_CR123","doi-asserted-by":"crossref","unstructured":"Wang, C., Zhang, L., Zhang, H.-J. (2008). Learning to reduce the semantic gap in web image retrieval and annotation. In Proceedings of the 31st annual international ACM SIGIR conference on research and development in information retrieval - SIGIR 2008 (p. 355).","DOI":"10.1145\/1390334.1390396"},{"key":"323_CR124","unstructured":"Westerveld, T. (2000). Image retrieval: content versus context. In Content-based multimedia information access, RIAO."},{"issue":"4","key":"323_CR126","doi-asserted-by":"crossref","first-page":"662","DOI":"10.1109\/TMM.2011.2147777","volume":"13","author":"K Yang","year":"2011","unstructured":"Yang, K. et al. (2011). Tag tagging: towards more descriptive keywords of image content. IEEE Transactions on Multimedia, 13(4), 662\u2013673.","journal-title":"IEEE Transactions on Multimedia"},{"key":"323_CR127","doi-asserted-by":"crossref","unstructured":"Yee, K. P., Swearingen, K., Li, K., Hearst, M. (2003). Faceted metadata for image search and browsing. In Proceedings of SIGCHI (pp. 401\u2013408).","DOI":"10.1145\/642611.642681"},{"key":"323_CR128","doi-asserted-by":"crossref","unstructured":"Zhai, Y., & Liu, B. (2005). Web data extraction based on partial tree alignment. In Proceedings of the 14th international conference on World Wide Web (pp. 76\u201385).","DOI":"10.1145\/1060745.1060761"},{"key":"323_CR130","doi-asserted-by":"crossref","unstructured":"Zheng, Y.T., Zhao, M., Song, Y., Adam, H., Buddemeier, U., Bissacco, A., Brucher, F., et al. (2009). Tour the world: building a web-scale landmark recognition engine. In Proceedings of IEEE conference on computer vision and pattern recognition (pp. 1085\u20131092).","DOI":"10.1109\/CVPR.2009.5206749"}],"container-title":["Journal of Intelligent Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-014-0323-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10844-014-0323-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-014-0323-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,11]],"date-time":"2019-08-11T12:10:07Z","timestamp":1565525407000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10844-014-0323-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,6,12]]},"references-count":103,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2014,10]]}},"alternative-id":["323"],"URL":"https:\/\/doi.org\/10.1007\/s10844-014-0323-6","relation":{},"ISSN":["0925-9902","1573-7675"],"issn-type":[{"value":"0925-9902","type":"print"},{"value":"1573-7675","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,6,12]]}}}