{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T07:30:23Z","timestamp":1747899023408,"version":"3.40.3"},"publisher-location":"Boston, MA","reference-count":65,"publisher":"Springer US","isbn-type":[{"type":"print","value":"9781461432227"},{"type":"electronic","value":"9781461432234"}],"license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-1-4614-3223-4_11","type":"book-chapter","created":{"date-parts":[[2012,2,2]],"date-time":"2012-02-02T16:49:22Z","timestamp":1328201362000},"page":"361-384","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Text Mining in Multimedia"],"prefix":"10.1007","author":[{"given":"Zheng-Jun","family":"Zha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jialie","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,1,7]]},"reference":[{"key":"11_CR1_En","unstructured":"Altavista\u2019s a\/v photo finder. http:\/\/www.altavista.com\/sites\/search\/simage."},{"key":"11_CR2_En","volume-title":"Text Mining in Social Networks","author":"CC Aggarwal","year":"2012","unstructured":"C. C. Aggarwal, H. Wang. Text Mining in Social Networks. Social Network Data Analytics, Springer, 2011."},{"key":"11_CR3_En","doi-asserted-by":"crossref","unstructured":"D. Cai, X. He, Z. Li, W.-Y. Ma, and J.-R. Wen. Hierarchical clustering of www image search results using visual, textual and link information. In Proceedings of the ACM Conference on Multimedia, 2004.","DOI":"10.1145\/1027527.1027747"},{"key":"11_CR4_En","unstructured":"S.-F. Chang, W. Hsu, W. Jiang, L. Kennedy, D. Xu, A. Yanagawa, and E. Zavesky. Columbia university trecvid-2006 video search and high-level feature extraction. In Proceedings of NIST TRECVID workshop, 2006."},{"key":"11_CR5_En","doi-asserted-by":"crossref","unstructured":"L. Chen and A. Roy. Event detection from Flickr data through wavelet-based spatial analysis. In Proceedings of the ACM conference on Information and knowledge management, pages 523\u2013532. ACM, 2009.","DOI":"10.1145\/1645953.1646021"},{"key":"11_CR6_En","volume-title":"and J","author":"L Chen","year":"2010","unstructured":"L. Chen, D. Xu, I. W. Tsang, and J. Luo. Tag-based web photo retrieval improved by batch mode re-tagging. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, 2010."},{"key":"11_CR7_En","unstructured":"W. Dai, Y. Chen, G.-R. Xue, Q. Yang, and Y. Yu. Translated learning: Transfer learning across difference feature spaces. In NIPS, pages 353\u2013360, 2008."},{"key":"11_CR8_En","volume-title":"and Y","author":"J Fan","year":"2010","unstructured":"J. Fan, Y. Shen, N. Zhou, and Y. Gao. Harvesting large-scaleweaklytagged image databases from the web. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, 2010."},{"key":"11_CR9_En","doi-asserted-by":"crossref","unstructured":"H. Feng, R. Shi, and T.-S. Chua. A bootstrapping framework for annotating and retrieving www images. In Proceedings of the ACM Conference on Multimedia, 2004.","DOI":"10.1145\/1027527.1027748"},{"key":"11_CR10_En","doi-asserted-by":"crossref","unstructured":"S. Feng, C. Lang, and D. Xu. Beyond tag relevance: integrating visual attention model and multi-instance learning for tag saliency ranking. In Proceedings of International Conference on Image and Video Retrieval, 2010.","DOI":"10.1145\/1816041.1816084"},{"key":"11_CR11_En","volume-title":"and A","author":"R Fergus","year":"2004","unstructured":"R. Fergus, P. Perona, and A. Zisserman. A visual category filter for google images. In Proceedings of the European Conference on Computer Vision, 2004."},{"key":"11_CR12_En","unstructured":"C. Frankel, M. J. Swain, and V. Athitsos. Webseer: An image search engine for the world wide web. Technical report, University of Chicago, Computer Science Department, 1996."},{"key":"11_CR13_En","doi-asserted-by":"crossref","unstructured":"B. Gao, T.-Y. Liu, Q. Tao, X. Zheng, Q. Cheng, and W.-Y. Ma. Web image clustering by consistent utilization of visual features and surrounding texts. In Proceedings of the ACM Conference on Multimedia, 2005.","DOI":"10.1145\/1101149.1101167"},{"key":"11_CR14_En","doi-asserted-by":"crossref","unstructured":"B. Geng, L. Yang, C. Xu, and X.-S. Hua. Content-aware ranking for visual search. In Proceedings of the International Conference on Computer Vision and Pattern Recognition, 2010.","DOI":"10.1109\/CVPR.2010.5540003"},{"key":"11_CR15_En","unstructured":"G. Griffin, A. Holub, and P. Perona. Caltech-256 object category dataset. Technical Report 7694, California Institute of Technology, 2007."},{"key":"11_CR16_En","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/MMUL.2007.61","volume":"14","author":"W Hsu","year":"2007","unstructured":"W. Hsu, L. Kennedy,, and S.-F. Chang. Reranking methods for visual search. IEEE Multimedia, 14:14\u201322, 2007.","journal-title":"IEEE Multimedia"},{"key":"11_CR17_En","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.1109\/TPAMI.2008.121","volume":"30","author":"F Jing","year":"2008","unstructured":"F. Jing and S. Baluja. Visualrank: Applying pagerank to large-scale image search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30:1877\u20131890, 2008.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"11_CR18_En","volume-title":"and B","author":"F Jing","year":"2005","unstructured":"F. Jing, M. Li, H.-J. Zhang, and B. Zhang. A unified framework for image retrieval using keyword and visual features. IEEE Transactions on Image Processing, 2005."},{"key":"11_CR19_En","doi-asserted-by":"crossref","unstructured":"F. Jing, C. Wang, Y. Yao, K. Deng, L. Zhang, and W.-Y. Ma. Igroup: Web image search results clustering. In Proceedings of the ACM Conference on Multimedia, pages 377\u2013384, 2006.","DOI":"10.1145\/1180639.1180720"},{"key":"11_CR20_En","doi-asserted-by":"crossref","unstructured":"L. S. Kennedy, S. F. Chang, and I. V. Kozintsev. To search or to label? predicting the performance of search-based automatic image classifiers. In Proceedings of the ACM International Workshop on Multimedia Information Retrieval, 2006.","DOI":"10.1145\/1178677.1178712"},{"key":"11_CR21_En","doi-asserted-by":"crossref","unstructured":"G. Li, M. Wang, Y. T. Zheng, Z.-J. Zha, H. Li, and T.-S. Chua. Shottagger: Tag location for internet videos. In Proceedings of the ACM International Conference on Multimedia Retrieval, 2011.","DOI":"10.1145\/1991996.1992033"},{"key":"11_CR22_En","doi-asserted-by":"crossref","unstructured":"X. Li, C. G. Snoek, and M. Worring. Learning social tag relevance by neighbor voting. Pattern Recognition Letters, 11(7), 2009.","DOI":"10.1109\/TMM.2009.2030598"},{"key":"11_CR23_En","volume-title":"and M","author":"X Li","year":"2010","unstructured":"X. Li, C. G. Snoek, and M. Worring. Unsupervised multi-feature tag relevance learning for social image retrieval. In Proceedings of the International Conference on Image and Video Retrieval, 2010."},{"key":"11_CR24_En","volume-title":"and H","author":"D Liu","year":"2010","unstructured":"D. Liu, X. C. Hua, M. Wang, and H. Zhang. Image retagging. In Proceedings of the ACM Conference on Multimedia, 2010."},{"key":"11_CR25_En","doi-asserted-by":"crossref","unstructured":"D. Liu, X.-S. Hua, L. Yang, M.Wang, and H.-J. Zhang. Tag ranking. In Proceedings of the International Conference on World Wide Web, 2009.","DOI":"10.1145\/1526709.1526757"},{"key":"11_CR26_En","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1007\/s11042-010-0647-3","volume":"51","author":"D Liu","year":"2010","unstructured":"D. Liu, X.-S. Hua, and H.-J. Zhang. Content-based tag processing for internet social images. Multimedia Tools and Application, 51:723\u2013738, 2010.","journal-title":"Multimedia Tools and Application"},{"key":"11_CR27_En","volume-title":"and H","author":"D Liu","year":"2010","unstructured":"D. Liu, S. Yan, Y. Rui, and H. J. Zhang. Unified tag analysis with multi-edge graph. In Proceedings of the ACM Conference on Multimedia, 2010."},{"key":"11_CR28_En","volume-title":"and H","author":"X Liu","year":"2009","unstructured":"X. Liu, B. Cheng, S. Yan, J. Tang, T. C. Chua, and H. Jin. Label to region by bi-layer sparsify priors. In Proceedings of the ACM Conference on Multimedia, 2009."},{"key":"11_CR29_En","volume-title":"and H","author":"X Liu","year":"2010","unstructured":"X. Liu, S. Yan, J. Luo, J. Tang, Z. Huang, and H. Jin. Nonparametric label-to-region by search. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, 2010."},{"key":"11_CR30_En","doi-asserted-by":"crossref","unstructured":"Y. Liu, T. Mei, and X.-S. Hua. Crowdreranking: Exploring multiple search engines for visual search reranking. In Proceedings of the ACM SIGIR Conference, 2009.","DOI":"10.1145\/1571941.1572027"},{"key":"11_CR31_En","unstructured":"T. Mei, Z.-J. Zha, Y. Liu, M. Wang, and et al. Msra at trecvid 2008: High-level feature extraction and automatic search. In Proceedings of NIST TRECVID workshop, 2008."},{"key":"11_CR32_En","doi-asserted-by":"crossref","unstructured":"S. J. Pan and Q. Yang. A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 2010.","DOI":"10.1109\/TKDE.2009.191"},{"key":"11_CR33_En","volume-title":"and T","author":"G-J Qi","year":"2012","unstructured":"G.-J. Qi, C. C. Aggarwal, and T. Huang. Towards semantic knowledge propagation from text corpus to web images. In Proceedings of the International Conference on World Wide Web, 2011."},{"key":"11_CR34_En","volume-title":"and J","author":"M Rege","year":"2008","unstructured":"M. Rege, M. Dong, and J. Hua. Graph theoretical framework for simultaneously integrating visual and textual features for efficient web image clustering. In Proceedings of the International Conference on World Wide Web, 2008."},{"key":"11_CR35_En","volume-title":"and A","author":"F Schroff","year":"2007","unstructured":"F. Schroff, A. Criminisi, and A. Zisserman. Harvesting images databases from the web. In Proceedings of the International Conference on Computer Vision, 2007."},{"key":"11_CR36_En","doi-asserted-by":"crossref","unstructured":"D. A. Shamma, R. Shaw, P. L. Shafton, and Y. Liu. Watch what i watch: using community activeity to understand content. In Proceedings of the ACM Workshop on Multimedia Information Retrieval, 2007.","DOI":"10.1145\/1290082.1290120"},{"key":"11_CR37_En","volume-title":"and R","author":"X Shi","year":"2010","unstructured":"X. Shi, Q. Liu, W. Fan, P. S. Yu, and R. Zhu. Transfer learning on heterogenous feature spaces via spectral tranformation. In Proceedings of the International Conference on Data Mining, 2010."},{"key":"11_CR38_En","doi-asserted-by":"crossref","unstructured":"B. Sigurbj\u00a8ornsson and R. V. Zwol. Flickr tag recommendation based on collective knowledge. In Proceedings of International Conference on World Wide Web, 2008.","DOI":"10.1145\/1367497.1367542"},{"key":"11_CR39_En","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1109\/93.621578","volume":"4","author":"J Smith","year":"1995","unstructured":"J. Smith and S.-F. Chang. Visually searching the web for content. IEEE Multimedia, 4:12\u201320, 1995.","journal-title":"IEEE Multimedia"},{"key":"11_CR40_En","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1109\/2.410153","volume":"28","author":"R Srihari","year":"1995","unstructured":"R. Srihari. Automatic indexing and content-based retrieval of captioned images. IEEE Computer, 28:49\u201356, 1995.","journal-title":"IEEE Computer"},{"key":"11_CR41_En","doi-asserted-by":"crossref","unstructured":"A. Sun and S. S. Bhowmick. Quantifying tag representativeness of visual content of social images. In Proceedings of the ACM Conference on Multimedia, 2010.","DOI":"10.1145\/1873951.1874029"},{"key":"11_CR42_En","doi-asserted-by":"crossref","unstructured":"X. Tian, L. Yang, J. Wang, Y. Yang, X. Wu, and X.-S. Hua. Bayesian video search reranking. In Proceedings of the ACM Conference on Multimedia, 2008.","DOI":"10.1145\/1459359.1459378"},{"key":"11_CR43_En","volume-title":"and T","author":"A Ulges","year":"2008","unstructured":"A. Ulges, C. Schulze, D. Keysers, and T. M. Breuel. Identifying relevant frames in weakly labeled videos for training concept detectors. In Proceedings of the International Conference on Image and Video Retrieval, 2008."},{"key":"11_CR44_En","unstructured":"G. Wang and D. A. Forsyth. Object image retrieval by exploiting online knowledge resources. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2008."},{"key":"11_CR45_En","unstructured":"J.Wang, Y.-G. Jiang, and S.-F. Chang. Label diagnosis through self tuning for web image search. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"11_CR46_En","doi-asserted-by":"crossref","unstructured":"M. Wang, X. S. Hua, R. Hong, J. Tang, G. J. Qi, and Y. Song. Unified video annotation via multi-graph learning. IEEE Transactions on Circuits and Systems for Video Technology, 19(5), 2009.","DOI":"10.1109\/TCSVT.2009.2017400"},{"key":"11_CR47_En","doi-asserted-by":"crossref","unstructured":"M. Wang, X. S. Hua, J. Tang, and R. Hong. Beyond distance measurement: Constructing neighborhood similarity for video annotation. IEEE Transactions on Multimedia, 11(3), 2009.","DOI":"10.1109\/TMM.2009.2012919"},{"key":"11_CR48_En","doi-asserted-by":"crossref","unstructured":"M. Wang, B. Ni, X.-S. Hua, and T.-S. Chua. Assistive multimedia tagging: A survey of multimedia tagging with human-computer joint exploration. ACM Computing Survey, 2011.","DOI":"10.1145\/2333112.2333120"},{"key":"11_CR49_En","doi-asserted-by":"crossref","unstructured":"X.-J. Wang, W.-Y. Ma, G.-R. Xue, and X. Li. Multi-model similarity propagation and its application for web image retrieval. In Proceedings of the ACM Conference on Multimedia, pages 944\u2013951, 2004.","DOI":"10.1145\/1027527.1027746"},{"key":"11_CR50_En","volume-title":"and X","author":"X-J Wang","year":"2005","unstructured":"X.-J. Wang, W.-Y. Ma, L. Zhang, and X. Li. Iteratively clustering web images based on link and attribute reinforcements. In Proceedings of the ACM Conference on Multimedia, 2005."},{"key":"11_CR51_En","volume-title":"and S","author":"L Wu","year":"2008","unstructured":"L. Wu, X.-S. Hua, N. Yu, W.-Y. Ma, and S. Li. Flickr distance. In Proceedings of the ACM Conference on Multimedia, 2008."},{"key":"11_CR52_En","volume-title":"and S","author":"H Xu","year":"2009","unstructured":"H. Xu, J.Wang, X.-S. Hua, and S. Li. Tag refinement by regularized LDA. In Proceedings of the ACM Conference on Multimedia, 2009."},{"key":"11_CR53_En","doi-asserted-by":"crossref","unstructured":"R. Yan and A. G. Hauptmann. Co-retrieval: A boosted reranking approach for video retrieval. In Proceedings of the ACM Conference on Image and Video Retrieval, 2004.","DOI":"10.1007\/978-3-540-27814-6_11"},{"key":"11_CR54_En","volume-title":"and R","author":"R Yan","year":"2003","unstructured":"R. Yan, A. G. Hauptmann, and R. Jin. Multimedia search with pseudo-relevance feedback. In Proceedings of the ACM Conference on Image and Video Retrieval, 2003."},{"key":"11_CR55_En","volume-title":"and H","author":"K Yang","year":"2010","unstructured":"K. Yang, X.-S. Hua, M. Wang, and H. C. Zhang. Tagging tags. In Proceedings of the ACM Conference on Multimedia, 2010."},{"key":"11_CR56_En","volume-title":"and Y","author":"Q Yang","year":"2009","unstructured":"Q. Yang, Y. Chen, G.-R. Xue, W. Dai, and Y. Yu. Heterogeneous transfer learning from image clustering via the social web. In Proceedings of the Joint Conference of the Annual Meeting of the ACL, 2009."},{"key":"11_CR57_En","doi-asserted-by":"crossref","unstructured":"Y.-H. Yang, P. Wu, C. W. Lee, K. H. Lin, W. Hsu, and H. H. Chen. Contextseer: Context search and recommendation at query time for shared consumer photos. In Proceedings of the ACM Conference on Multimedia, 2008.","DOI":"10.1145\/1459359.1459387"},{"key":"11_CR58_En","volume-title":"and Z","author":"Z-J Zha","year":"2008","unstructured":"Z.-J. Zha, X.-S. Hua, T. Mei, J. Wang, G.-J. Qi, and Z. Wang. Joint multi-label multi-instance learning for image classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2008."},{"key":"11_CR59_En","volume-title":"and Z","author":"Z-J Zha","year":"2009","unstructured":"Z.-J. Zha, T. Mei, J. Wang, X.-S. Hua, and Z. Wang. Graph-based semi-supervised learning with multiple labels. Journal of Visual Communication and Image Representation, 2009."},{"key":"11_CR60_En","doi-asserted-by":"crossref","unstructured":"Z.-J. Zha, M. Wang, Y.-T. Zheng, Y. Yang, R. Hong, and T.-S. Chua. Interactive video indexing with statistical active learning. IEEE Transactions on Multimedia, 2011.","DOI":"10.1109\/TMM.2011.2174782"},{"key":"11_CR61_En","volume-title":"and Z","author":"Z-J Zha","year":"2009","unstructured":"Z.-J. Zha, L. Yang, T. Mei, M. Wang, and Z. Wang. Viusal query suggestion. In Proceedings of the ACM Conference on Multimedia, 2009."},{"key":"11_CR62_En","doi-asserted-by":"crossref","unstructured":"R. Zhang, Z. M. Zhang, M. Li, W.-Y. Ma, and H.-J. Zhang. A probabilistic semantic model for image annotation and multi-modal image retrieval. In Proceedings of the International Conference on Computer Vision, pages 846\u2013851, 2005.","DOI":"10.1109\/ICCV.2005.16"},{"key":"11_CR63_En","doi-asserted-by":"crossref","unstructured":"R. Zhao and W. I. Grosky. Narrowing the semantic gap - improved text-based web document retireval using visual fetures. IEEE Transactions on Multimedia, 4, 2002.","DOI":"10.1109\/TMM.2002.1017733"},{"key":"11_CR64_En","doi-asserted-by":"crossref","unstructured":"G. Zhu, S. Yan, and Y. Ma. Image tag refinement towards lowrank, content-tag prior and error sparsity. In Proceedings of the ACM Conference on Multimedia, 2010.","DOI":"10.1145\/1873951.1874028"},{"key":"11_CR65_En","volume-title":"and Q","author":"Y Zhu","year":"2012","unstructured":"Y. Zhu, Y. Chen, Z. Lu, S. J. Pan, G.-R. Xue, Y. Yu, and Q. Yang. Heterogeneous transfer learning for image classification. In Proceedings of the AAAI Conference on Artificial Intelligence, 2011."}],"container-title":["Mining Text Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-1-4614-3223-4_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T19:16:52Z","timestamp":1742411812000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-1-4614-3223-4_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9781461432227","9781461432234"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-1-4614-3223-4_11","relation":{},"subject":[],"published":{"date-parts":[[2012]]},"assertion":[{"value":"7 January 2012","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}