{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T02:28:14Z","timestamp":1783823294898,"version":"3.55.0"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2019,4,27]],"date-time":"2019-04-27T00:00:00Z","timestamp":1556323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1007\/s00530-019-00613-z","type":"journal-article","created":{"date-parts":[[2019,4,27]],"date-time":"2019-04-27T14:04:15Z","timestamp":1556373855000},"page":"639-653","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Toward efficient indexing structure for scalable content-based music retrieval"],"prefix":"10.1007","volume":"25","author":[{"given":"Jialie","family":"Shen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Rui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,4,27]]},"reference":[{"issue":"11","key":"613_CR1","doi-asserted-by":"publisher","first-page":"1587","DOI":"10.1109\/TCSVT.2008.2005607","volume":"18","author":"J Shen","year":"2008","unstructured":"Shen, J., Tao, D., Li, X.: Modality mixture projections for semantic video event detection. IEEE Trans. Circuits Syst. Video Tech. 18(11), 1587\u20131596 (2008)","journal-title":"IEEE Trans. Circuits Syst. Video Tech."},{"issue":"2","key":"613_CR2","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/s11263-013-0658-4","volume":"106","author":"Y Gong","year":"2014","unstructured":"Gong, Y., Ke, Q., Isard, M., Lazebnik, S.: A multi-view embedding space for modeling internet images, tags, and their semantics. Int. J. Comput. Vision 106(2), 210\u2013233 (2014)","journal-title":"Int. J. Comput. Vision"},{"key":"613_CR3","unstructured":"Chen, J., Zhang, H., He, X., Nie, L., Liu, W., Chua, T.: Attentive collaborative filtering: Multimedia recommendation with item- and component-level attention. In: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, Shinjuku, Tokyo, Japan, August 7\u201311, 2017, pp. 335\u2013344 (2017)"},{"key":"613_CR4","unstructured":"He, X., He, Z., Du, X., Chua, T.: Adversarial personalized ranking for recommendation. In: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, SIGIR 2018, Ann Arbor, MI, USA, July 08-12, 2018, pp. 355\u2013364 (2018)"},{"issue":"12","key":"613_CR5","doi-asserted-by":"publisher","first-page":"2354","DOI":"10.1109\/TKDE.2018.2831682","volume":"30","author":"X He","year":"2018","unstructured":"He, X., He, Z., Song, J., Liu, Z., Jiang, Y., Chua, T.: NAIS: neural attentive item similarity model for recommendation. IEEE Trans. Knowl. Data Eng. 30(12), 2354\u20132366 (2018)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"613_CR6","doi-asserted-by":"crossref","unstructured":"He, X., Gao, M., Kan, M., Wang, D.: Birank: Towards ranking on bipartite graphs, to appear in IEEE Trans. Knowl. Data Eng. (2017)","DOI":"10.1109\/TKDE.2016.2611584"},{"issue":"3","key":"613_CR7","doi-asserted-by":"publisher","first-page":"45:1","DOI":"10.1145\/3177849","volume":"51","author":"Y\u00a0V\u00a0S Murthy","year":"2018","unstructured":"Murthy, Y\u00a0.V\u00a0.S., Koolagudi, S\u00a0.G.: Content-based music information retrieval (CB-MIR) and its applications toward the music industry: a review. ACM Comput. Surv. 51(3), 45:1\u201345:46 (2018)","journal-title":"ACM Comput. Surv."},{"key":"613_CR8","unstructured":"Essid, S., Richard, G.: Fusion of multimodal information in music content analysis. In: Multimodal Music Processing, pp. 37\u201352 (2012)"},{"issue":"2","key":"613_CR9","doi-asserted-by":"publisher","first-page":"13:1","DOI":"10.1145\/2846092","volume":"34","author":"Z Cheng","year":"2016","unstructured":"Cheng, Z., Shen, J.: On effective location-aware music recommendation. ACM Trans. Inf. Syst. 34(2), 13:1\u201313:32 (2016)","journal-title":"ACM Trans. Inf. Syst."},{"key":"613_CR10","unstructured":"Cheng, Z., Shen, J., Hoi, S.\u00a0C.\u00a0H.: On effective personalized music retrieval by exploring online user behaviors. In: Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval, SIGIR 2016, Pisa, Italy, July 17-21, 2016, pp. 125\u2013134 (2016)"},{"key":"613_CR11","unstructured":"Cheng, Z., Shen, J., Zhu, L., Kankanhalli, M.\u00a0S., Nie, L.: Exploiting music play sequence for music recommendation. In: Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI 2017, Melbourne, Australia, August 19-25, 2017, pp. 3654\u20133660 (2017)"},{"issue":"2","key":"613_CR12","first-page":"17:1","volume":"8","author":"M Schedl","year":"2017","unstructured":"Schedl, M., Yang, Y., Herrera-Boyer, P.: Introduction to intelligent music systems and applications. ACM TIST 8(2), 17:1\u201317:8 (2017)","journal-title":"ACM TIST"},{"issue":"2","key":"613_CR13","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/s00530-017-0542-0","volume":"24","author":"J Hsu","year":"2018","unstructured":"Hsu, J., Zhen, Y., Lin, T., Chiu, Y.: Affective content analysis of music emotion through EEG. Multimedia Syst. 24(2), 195\u2013210 (2018)","journal-title":"Multimedia Syst."},{"key":"613_CR14","unstructured":"Deldjoo, Y., Constantin, M.\u00a0G., Ionescu, B., Schedl, M., Cremonesi, P.: MMTF-14K: a multifaceted movie trailer feature dataset for recommendation and retrieval. In: Proceedings of the 9th ACM Multimedia Systems Conference, MMSys 2018, Amsterdam, The Netherlands, June 12-15, 2018, pp. 450\u2013455 (2018)"},{"issue":"6","key":"613_CR15","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1109\/TMM.2006.884618","volume":"8","author":"J Shen","year":"2006","unstructured":"Shen, J., Shepherd, J., Ngu, A.: Towards effective content-based music retrieval with multiple acoustic feature combination. IEEE Trans. Multimedia 8(6), 1179\u20131189 (2006)","journal-title":"IEEE Trans. Multimedia"},{"issue":"2","key":"613_CR16","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1109\/TMM.2008.2009719","volume":"11","author":"J Shen","year":"2009","unstructured":"Shen, J., Tao, D., Li, X.: Quc-tree: integrating query context information for efficient music retrieval. IEEE Trans. Multimedia 11(2), 313\u2013323 (2009)","journal-title":"IEEE Trans. Multimedia"},{"key":"613_CR17","doi-asserted-by":"crossref","unstructured":"Yang, C.: Efficient acoustic index for music retrieval with various degrees of similarity. In: Proc. of ACM MM Conference (2002)","DOI":"10.1145\/641007.641125"},{"key":"613_CR18","doi-asserted-by":"crossref","unstructured":"Ryyn\u00e4nen, M., Klapuri, A.: Query by humming of midi and audio using locality sensitive hashing. In: Proceedings of ICASSP, pp. 2249\u20132252 (2008)","DOI":"10.1109\/ICASSP.2008.4518093"},{"issue":"8","key":"613_CR19","doi-asserted-by":"publisher","first-page":"1969","DOI":"10.1109\/TMM.2013.2269313","volume":"15","author":"Y Yu","year":"2013","unstructured":"Yu, Y., Zimmermann, R., Wang, Y., Oria, V.: Scalable content-based music retrieval using chord progression histogram and tree-structure lsh. IEEE Trans. Multimedia 15(8), 1969\u20131981 (2013)","journal-title":"IEEE Trans. Multimedia"},{"issue":"3","key":"613_CR20","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1145\/502807.502809","volume":"33","author":"C B\u00f6hm","year":"2001","unstructured":"B\u00f6hm, C., Berchtold, S., Keim, D.A.: Searching in high-dimensional spaces: index structures for improving the performance of multimedia databases. ACM Comput. Surv. 33(3), 322\u2013373 (2001)","journal-title":"ACM Comput. Surv."},{"issue":"5","key":"613_CR21","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1109\/76.718510","volume":"8","author":"Y Rui","year":"1998","unstructured":"Rui, Y., Huang, T.S., Ortega, M., Mehrotra, S.: Relevance feedback: a power tool for interactive content-based image retrieval. IEEE Trans. Circuits Syst. Video Techn. 8(5), 644\u2013655 (1998)","journal-title":"IEEE Trans. Circuits Syst. Video Techn."},{"issue":"2","key":"613_CR22","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1145\/280277.280279","volume":"30","author":"V Gaede","year":"1998","unstructured":"Gaede, V., G\u00fcnther, O.: Multidimensional access methods. ACM Comput. Surv. 30(2), 170\u2013231 (1998)","journal-title":"ACM Comput. Surv."},{"issue":"9","key":"613_CR23","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1109\/34.790428","volume":"21","author":"S Santini","year":"1999","unstructured":"Santini, S., Jain, R.: Similarity measures. IEEE Trans. Pattern Anal. Mach. Intell. 21(9), 871\u2013883 (1999)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"613_CR24","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1145\/502807.502809","volume":"33","author":"C B\u00f6hm","year":"2001","unstructured":"B\u00f6hm, C., Berchtold, S., Keim, D.A.: Searching in high-dimensional spaces: index structures for improving the performance of multimedia databases. ACM Comput. Surv. 33(3), 322\u2013373 (2001)","journal-title":"ACM Comput. Surv."},{"key":"613_CR25","unstructured":"Ciaccia, P., Patella, M., Zezula, P.: M-tree: An efficient access method for similarity search in metric spaces. In: Proc. of the 23rd VLDB conference (VLDB\u201997) (1997)"},{"key":"613_CR26","unstructured":"Weber, R., Schek, H.\u00a0J., Blott, S.: A quantitative analysis and performance study for similarity-search methods in high-dimensional spaces. In: Proc. of 24th VLDB Conference (VLDB\u201998) (1998)"},{"key":"613_CR27","doi-asserted-by":"crossref","unstructured":"Chakrabarti, K., Mehrotra, S.: The hybrid tree: an index structure for high dimensional feature spaces. In: Proc. of ICDE Conference (ICDE\u201999) (1999)","DOI":"10.1109\/ICDE.1999.754960"},{"key":"613_CR28","unstructured":"Yu, C., Ooi, B.\u00a0C., Tan, K.\u00a0L., Jagadish, H.\u00a0V.: Indexing the distance: an efficient method to knn processing. In: Proc. of 27th VLDB Conference (VLDB\u201901) (2001)"},{"key":"613_CR29","doi-asserted-by":"crossref","unstructured":"Yu, Y., Crucianu, M., Oria, V., Damiani, E.: Combining multi-probe histogram and order-statistics based lsh for scalable audio content retrieval. In: Proc. of ACM MM Conference (2010)","DOI":"10.1145\/1873951.1874004"},{"key":"613_CR30","unstructured":"Wu, G., Han, J., Guo, Y., Liu, L., Ding, G., Ni, Q., Shao, L.: Unsupervised deep video hashing via balanced code for large-scale video retrieval. to appear in IEEE Trans. on Image Processing"},{"issue":"2","key":"613_CR31","doi-asserted-by":"publisher","first-page":"949","DOI":"10.1109\/TIP.2017.2766445","volume":"27","author":"Y Guo","year":"2018","unstructured":"Guo, Y., Ding, G., Han, J.: Robust quantization for general similarity search. IEEE Trans. Image Process. 27(2), 949\u2013963 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"613_CR32","unstructured":"Wu, G., Han, J., Lin, Z., Ding, G., Zhang, B., Ni, Q.: Joint image-text hashing for fast large-scale cross-media retrieval using self-supervised deep learning. to appear in IEEE Trans. on Industrial Electronics"},{"key":"613_CR33","unstructured":"Wu, G., Lin, Z., Han, J., Liu, L., Ding, G., Zhang, B., Shen, J.: Unsupervised deep hashing via binary latent factor models for large-scale cross-modal retrieval. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018, July 13-19, 2018, Stockholm, Sweden., pp. 2854\u20132860 (2018)"},{"key":"613_CR34","unstructured":"Berchtold, S., Bohm, C., Kriegel, H., Sander, J., Jagadish, H.: Independent quantization: an index compression technique for high-dimensional data spaces. In: Proc. of 16th ICDE Conference (ICDE\u201900) (2000)"},{"key":"613_CR35","unstructured":"McFee, B., Lanckriet, G.\u00a0R.\u00a0G.: Large-scale music similarity search with spatial trees. In: ISMIR (2011)"},{"key":"613_CR36","unstructured":"Rabiner, L., Juang, B.-H.: Fundamentals of speech recognition (1993)"},{"key":"613_CR37","unstructured":"Nam, U., Berger, J.: Addressing the same but different-different but similar problem in automatic music classification. In: Proc. of ISMIR (2001)"},{"key":"613_CR38","unstructured":"Li, G., Khokhar, A.A.: Content-based indexing and retrieval of audio data using wavelets. In: Proceedings of IEEE International Conference on Multimedia and Expo(II), pp. 885\u2013888 (2000)"},{"issue":"6","key":"613_CR39","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1007\/s00530-002-0065-0","volume":"8","author":"L Lu","year":"2003","unstructured":"Lu, L., Zhang, H., Li, S.Z.: Content-based audio classification and segmentation by using support vector machines. Multimedia Syst. 8(6), 482\u2013492 (2003)","journal-title":"Multimedia Syst."},{"issue":"5","key":"613_CR40","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1109\/TSA.2002.800560","volume":"10","author":"G Tzanetakis","year":"2002","unstructured":"Tzanetakis, G., Cook, P.R.: Musical genre classification of audio signals. IEEE Trans. Speech Audio Process. 10(5), 293\u2013302 (2002)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"613_CR41","doi-asserted-by":"crossref","unstructured":"Li, T., Ogihara, M., Li, Q.: A comparative study on content-based music genre classification. In: Proc. of ACM SIGIR Conference (SIGIR\u201903) (2003)","DOI":"10.1145\/860435.860487"},{"issue":"6","key":"613_CR42","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1109\/TMM.2006.884618","volume":"8","author":"J Shen","year":"2006","unstructured":"Shen, J., Shepherd, J., Ngu, A.H.H.: Towards effective content-based music retrieval with multiple acoustic feature combination. IEEE Trans. Multimedia 8(6), 1179\u20131189 (2006)","journal-title":"IEEE Trans. Multimedia"},{"issue":"1","key":"613_CR43","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/TMM.2007.911305","volume":"10","author":"Y Song","year":"2008","unstructured":"Song, Y., Zhang, C.: Content-based information fusion for semi-supervised music genre classification. IEEE Trans. Multimedia 10(1), 145\u2013152 (2008)","journal-title":"IEEE Trans. Multimedia"},{"issue":"6","key":"613_CR44","doi-asserted-by":"publisher","first-page":"708","DOI":"10.1109\/89.876309","volume":"8","author":"T Tolonen","year":"2000","unstructured":"Tolonen, T., Karjalainen, M.: A computationally efficient multipitch analysis model. IEEE Trans. Speech Audio Process. 8(6), 708\u2013716 (2000)","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"1","key":"613_CR45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"NLA Dempster","year":"1977","unstructured":"Dempster, N.L.A., Rubin, D.: Maximum likelihood from incomplete data via the em algorithm. J. R. Stat. Soc. Ser. B 39(1), 1\u201322 (1977)","journal-title":"J. R. Stat. Soc. Ser. B"},{"issue":"3","key":"613_CR46","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1145\/1508850.1508856","volume":"27","author":"J Shen","year":"2009","unstructured":"Shen, J., Shepherd, J., Cui, B., Tan, K.: A novel framework for efficient automated singer identification in large music databases. ACM Trans. Inf. Syst. 27(3), 18 (2009)","journal-title":"ACM Trans. Inf. Syst."},{"key":"613_CR47","unstructured":"Jordan, M.I.: Why the logistic function? a tutorial discussion on probabilities and neural networks. Massachusetts Institute of Technology, Tech. Rep. 9503 (1995)"},{"key":"613_CR48","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-21606-5","volume-title":"The elements of statistical learning: data mining, inference, and prediction","author":"T Hastie","year":"2001","unstructured":"Hastie, T., Tibshirani, R., Friedman, J.: The elements of statistical learning: data mining, inference, and prediction. Springer, New York (2001)"},{"key":"613_CR49","unstructured":"Collins, M., Schapire, R.\u00a0E., Singer, Y.: Logistic regression, adaboost and bregman distances. In: Proc. of the 13th Annual Conference on Computational Learning Theory (COLT\u201900) (2000)"},{"key":"613_CR50","unstructured":"Bottou, L., Bousquet, O.: The tradeoffs of large scale learning. In: NIPS (2007)"},{"key":"613_CR51","unstructured":"Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.-A.: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11, 3371\u20133408 (2010)"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-019-00613-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00530-019-00613-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-019-00613-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T10:38:15Z","timestamp":1721212695000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00530-019-00613-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,27]]},"references-count":51,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["613"],"URL":"https:\/\/doi.org\/10.1007\/s00530-019-00613-z","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4,27]]},"assertion":[{"value":"27 April 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}