{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T18:20:37Z","timestamp":1760984437197,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2012,6,5]],"date-time":"2012-06-05T00:00:00Z","timestamp":1338854400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001868","name":"National Science Council Taiwan","doi-asserted-by":"publisher","award":["NSC 100-2218-E-001-009"],"award-info":[{"award-number":["NSC 100-2218-E-001-009"]}],"id":[{"id":"10.13039\/501100001868","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2012,6,5]]},"DOI":"10.1145\/2324796.2324859","type":"proceedings-article","created":{"date-parts":[[2012,7,3]],"date-time":"2012-07-03T11:53:15Z","timestamp":1341316395000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["Supervised dictionary learning for music genre classification"],"prefix":"10.1145","author":[{"given":"Chin-Chia Michael","family":"Yeh","sequence":"first","affiliation":[{"name":"Research Center for IT Innovation Academia Sinica, Taipei, Taiwan"}]},{"given":"Yi-Hsuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Research Center for IT Innovation Academia Sinica, Taipei, Taiwan"}]}],"member":"320","published-online":{"date-parts":[[2012,6,5]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"European Conf. Signal Processing","author":"Benetos E.","year":"2008","unstructured":"E. Benetos and C. Kotropoulos . A tensor-based approach for automatic music genre classification . In European Conf. Signal Processing , 2008 . E. Benetos and C. Kotropoulos. A tensor-based approach for automatic music genre classification. In European Conf. Signal Processing, 2008."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-9019-7"},{"key":"e_1_3_2_1_3_1","first-page":"507","volume-title":"ISMIR","author":"Bergstra J.","year":"2010","unstructured":"J. Bergstra , M. I. Mandel , and D. Eck . Scalable genre and tag prediction with spectral covariance . In ISMIR , pages 507 -- 512 , 2010 . J. Bergstra, M. I. Mandel, and D. Eck. Scalable genre and tag prediction with spectral covariance. In ISMIR, pages 507--512, 2010."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041381"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082307"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.916370"},{"key":"e_1_3_2_1_7_1","first-page":"387","volume-title":"ISMIR","author":"Chang K. K.","year":"2010","unstructured":"K. K. Chang , J.-S. R. Jang , and C. S. Iliopoulos . Music genre classification via compressive sampling . In ISMIR , pages 387 -- 392 , 2010 . K. K. Chang, J.-S. R. Jang, and C. S. Iliopoulos. Music genre classification via compressive sampling. In ISMIR, pages 387--392, 2010."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827596304010"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1214\/009053604000000067"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2098858"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2112350"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1037\/1528-3542.7.2.377"},{"key":"e_1_3_2_1_13_1","first-page":"339","volume-title":"ISMIR","author":"Hamel P.","year":"2010","unstructured":"P. Hamel and D. Eck . Learning features from music audio with deep belief networks . In ISMIR , pages 339 -- 344 , 2010 . P. Hamel and D. Eck. Learning features from music audio with deep belief networks. In ISMIR, pages 339--344, 2010."},{"key":"e_1_3_2_1_14_1","first-page":"729","volume-title":"ISMIR","author":"Hamel P.","year":"2011","unstructured":"P. Hamel , S. Lemieux , Y. Bengio , and D. Eck . Temporal pooling and multiscale learning for automatic annotation and ranking of music audio . In ISMIR , pages 729 -- 734 , 2011 . P. Hamel, S. Lemieux, Y. Bengio, and D. Eck. Temporal pooling and multiscale learning for automatic annotation and ranking of music audio. In ISMIR, pages 729--734, 2011."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/2095116.2095209"},{"key":"e_1_3_2_1_16_1","first-page":"681","volume-title":"ISMIR","author":"Henaff M.","year":"2011","unstructured":"M. Henaff , K. Jarrett , K. Kavukcuoglu , and Y. LeCun . Unsupervised learning of sparse features for scalable audio classification . In ISMIR , pages 681 -- 686 , 2011 . M. Henaff, K. Jarrett, K. Kavukcuoglu, and Y. LeCun. Unsupervised learning of sparse features for scalable audio classification. In ISMIR, pages 681--686, 2011."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.909434"},{"key":"e_1_3_2_1_19_1","volume-title":"Machine Learning Research","author":"Jenatton R.","year":"2011","unstructured":"R. Jenatton , J. Mairal , G. Obozinski , and F. Bach . Proximal methods for hierarchical sparse coding. J . Machine Learning Research , 2011 . R. Jenatton, J. Mairal, G. Obozinski, and F. Bach. Proximal methods for hierarchical sparse coding. J. Machine Learning Research, 2011."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2009.5346483"},{"key":"e_1_3_2_1_21_1","article-title":"Multipitch estimation of piano music by exemplar-based sparse representation","author":"Lee C.-T.","year":"2012","unstructured":"C.-T. Lee , Y.-H. Yang , and H. H. Chen . Multipitch estimation of piano music by exemplar-based sparse representation . IEEE Trans. Multimedia , 2012 . to appear. C.-T. Lee, Y.-H. Yang, and H. H. Chen. Multipitch estimation of piano music by exemplar-based sparse representation. IEEE Trans. Multimedia, 2012. to appear.","journal-title":"IEEE Trans. Multimedia"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2009.2012913"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/860435.860487"},{"key":"e_1_3_2_1_24_1","volume-title":"Evaluation of feature extractors and psycho-acoustic transformations for music genre classification","author":"Lidy T.","year":"2005","unstructured":"T. Lidy and A. Rauber . Evaluation of feature extractors and psycho-acoustic transformations for music genre classification , 2005 . T. Lidy and A. Rauber. Evaluation of feature extractors and psycho-acoustic transformations for music genre classification, 2005."},{"key":"e_1_3_2_1_25_1","volume-title":"ISMIR","author":"Lidy T.","year":"2007","unstructured":"T. Lidy , A. Rauber , A. Pertusa , and J. M. I\u00f1esta . Combining audio and symbolic descriptors for music classification from audio . In ISMIR , 2007 . T. Lidy, A. Rauber, A. Pertusa, and J. M. I\u00f1esta. Combining audio and symbolic descriptors for music classification from audio. In ISMIR, 2007."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.911304"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553463"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587630"},{"key":"e_1_3_2_1_30_1","first-page":"399","volume-title":"ISMIR","author":"Mandel M. I.","year":"2010","unstructured":"M. I. Mandel , D. Eck , and Y. Bengio . Learning tags that vary within a song . In ISMIR , pages 399 -- 404 , 2010 . M. I. Mandel, D. Eck, and Y. Bengio. Learning tags that vary within a song. In ISMIR, pages 399--404, 2010."},{"key":"e_1_3_2_1_31_1","volume-title":"Learning content similarity for music recommendation. CoRR, abs\/1105.2344","author":"McFee B.","year":"2011","unstructured":"B. McFee , L. Barrington , and G. R. G. Lanckriet . Learning content similarity for music recommendation. CoRR, abs\/1105.2344 , 2011 . B. McFee, L. Barrington, and G. R. G. Lanckriet. Learning content similarity for music recommendation. CoRR, abs\/1105.2344, 2011."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.899293"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2112333"},{"key":"e_1_3_2_1_34_1","volume-title":"ISMIR","author":"Pampalk E.","year":"2003","unstructured":"E. Pampalk , S. Dixon , and G. Widmer . Exploring music collections by browsing different views . In ISMIR , 2003 . E. Pampalk, S. Dixon, and G. Widmer. Exploring music collections by browsing different views. In ISMIR, 2003."},{"key":"e_1_3_2_1_35_1","first-page":"628","volume-title":"ISMIR","author":"Pampalk E.","year":"2005","unstructured":"E. Pampalk , A. Flexer , and G. Widmer . Improvements of audio-based music similarity and genre classification . In ISMIR , pages 628 -- 633 , 2005 . E. Pampalk, A. Flexer, and G. Widmer. Improvements of audio-based music similarity and genre classification. In ISMIR, pages 628--633, 2005."},{"key":"e_1_3_2_1_36_1","first-page":"583","volume-title":"Music genre classification: A multilinear approach","author":"Panagakis I.","year":"2008","unstructured":"I. Panagakis , E. Benetos , and C. Kotropoulos . Music genre classification: A multilinear approach , pages 583 -- 588 . Citeseer , 2008 . I. Panagakis, E. Benetos, and C. Kotropoulos. Music genre classification: A multilinear approach, pages 583--588. Citeseer, 2008."},{"key":"e_1_3_2_1_37_1","first-page":"249","volume-title":"ISMIR","author":"Panagakis Y.","year":"2009","unstructured":"Y. Panagakis , C. Kotropoulos , and G. R. Arce . Music genre classification using locality preserving non-negative tensor factorization and sparse representations . In ISMIR , pages 249 -- 254 , 2009 . Y. Panagakis, C. Kotropoulos, and G. R. Arce. Music genre classification using locality preserving non-negative tensor factorization and sparse representations. In ISMIR, pages 249--254, 2009."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2036813"},{"key":"e_1_3_2_1_39_1","first-page":"625","volume-title":"ISMIR","author":"Paulus J.","year":"2010","unstructured":"J. Paulus , M. M\u00fcller , and A. Klapuri . State of the art report: Audio-based music structure analysis . In ISMIR , pages 625 -- 636 , 2010 . J. Paulus, M. M\u00fcller, and A. Klapuri. State of the art report: Audio-based music structure analysis. In ISMIR, pages 625--636, 2010."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2009.2030345"},{"key":"e_1_3_2_1_41_1","volume-title":"ISMIR","author":"Riley M.","year":"2008","unstructured":"M. Riley , E. Heinen , and J. Ghosh . A text retrieval approach to content-based audio retrieval . In ISMIR , 2008 . M. Riley, E. Heinen, and J. Ghosh. A text retrieval approach to content-based audio retrieval. In ISMIR, 2008."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2009916.2010011"},{"key":"e_1_3_2_1_43_1","volume-title":"Learning with Kernels","author":"Scholk\u00f6pf B.","year":"2002","unstructured":"B. Scholk\u00f6pf and A. J. Smola . Learning with Kernels . MIT Press , Cambridge , 2002 . B. Scholk\u00f6pf and A. J. Smola. Learning with Kernels. MIT Press, Cambridge, 2002."},{"key":"e_1_3_2_1_44_1","volume-title":"Sound and Music Computing Conf.","author":"Sch\u00f6rkhuber C.","year":"2010","unstructured":"C. Sch\u00f6rkhuber and A. Klapuri . Constant-Q transform toolbox for music processing . In Sound and Music Computing Conf. , 2010 . C. Sch\u00f6rkhuber and A. Klapuri. Constant-Q transform toolbox for music processing. In Sound and Music Computing Conf., 2010."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772862"},{"key":"e_1_3_2_1_46_1","first-page":"705","volume-title":"ISMIR","author":"Su M.-Y.","year":"2009","unstructured":"M.-Y. Su , Y.-H. Yang , Y.-C. Lin , and H.-H. Chen . An integrated approach to music boundary detection . In ISMIR , pages 705 -- 710 , 2009 . M.-Y. Su, Y.-H. Yang, Y.-C. Lin, and H.-H. Chen. An integrated approach to music boundary detection. In ISMIR, pages 705--710, 2009."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani R.","year":"1996","unstructured":"R. Tibshirani . Regression shrinkage and selection via the lasso . J. Royal Statistical Soc. , 58 : 267 -- 288 , 1996 . R. Tibshirani. Regression shrinkage and selection via the lasso. J. Royal Statistical Soc., 58:267--288, 1996.","journal-title":"J. Royal Statistical Soc."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277817"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"e_1_3_2_1_50_1","volume-title":"ISMIR","author":"Wang J.-C.","year":"2011","unstructured":"J.-C. Wang , H.-S. Lee , H.-M. Wang , and S.-K. Jeng . Learning the similarity of audio music in bag-of-frames representation from tagged music data . In ISMIR , 2011 . J.-C. Wang, H.-S. Lee, H.-M. Wang, and S.-K. Jeng. Learning the similarity of audio music in bag-of-frames representation from tagged music data. In ISMIR, 2011."},{"key":"e_1_3_2_1_51_1","volume-title":"New Music Res.","author":"Weston J.","year":"2012","unstructured":"J. Weston , S. Bengio , and P. Hamel . Multi-tasking with joint semantic spaces for large-scale music annotation and retrieval. J . New Music Res. , 2012 . to appear. J. Weston, S. Bengio, and P. Hamel. Multi-tasking with joint semantic spaces for large-scale music annotation and retrieval. J. New Music Res., 2012. to appear."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2044470"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/1290082.1290111"},{"key":"e_1_3_2_1_54_1","first-page":"1794","volume-title":"IEEE CVPR","author":"Yang J.","year":"2009","unstructured":"J. Yang , K. Yu , Y. Gong , and T. Huang . Linear spatial pyramid matching using sparse coding for image classification . In IEEE CVPR , pages 1794 -- 1801 , 2009 . J. Yang, K. Yu, Y. Gong, and T. Huang. Linear spatial pyramid matching using sparse coding for image classification. In IEEE CVPR, pages 1794--1801, 2009."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.5555\/1996401"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995524"}],"event":{"name":"ICMR '12: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Hong Kong China","acronym":"ICMR '12"},"container-title":["Proceedings of the 2nd ACM International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2324796.2324859","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2324796.2324859","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T10:52:09Z","timestamp":1750243929000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2324796.2324859"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6,5]]},"references-count":56,"alternative-id":["10.1145\/2324796.2324859","10.1145\/2324796"],"URL":"https:\/\/doi.org\/10.1145\/2324796.2324859","relation":{},"subject":[],"published":{"date-parts":[[2012,6,5]]},"assertion":[{"value":"2012-06-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}