{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T11:08:46Z","timestamp":1764587326633,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2005,8,15]],"date-time":"2005-08-15T00:00:00Z","timestamp":1124064000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2005,8,15]]},"DOI":"10.1145\/1076034.1076097","type":"proceedings-article","created":{"date-parts":[[2005,11,7]],"date-time":"2005-11-07T17:34:39Z","timestamp":1131384879000},"page":"361-368","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["Automatic music video summarization based on audio-visual-text analysis and alignment"],"prefix":"10.1145","author":[{"given":"Changsheng","family":"Xu","sequence":"first","affiliation":[{"name":"Institute for Infocomm Research, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Shao","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, Singapore and National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Namunu C.","family":"Maddage","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, Singapore and National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohan S.","family":"Kankanhalli","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2005,8,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.859068"},{"key":"e_1_3_2_1_2_1","volume-title":"Proc. IEEE International Conference on Multimedia and Explore","author":"Xu C","year":"2002","unstructured":"Xu C , Zhu Y and Tian Q , Automatic music summarization based on temporal, spectral and cepstral features , In Proc. IEEE International Conference on Multimedia and Explore , Lausanne, Switzerland , 2002 , 117--120. Xu C, Zhu Y and Tian Q, Automatic music summarization based on temporal, spectral and cepstral features, In Proc. IEEE International Conference on Multimedia and Explore, Lausanne, Switzerland, 2002, 117--120."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/957013.957043"},{"key":"e_1_3_2_1_4_1","volume-title":"Proc. Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","author":"Bartsch M A","year":"2001","unstructured":"Bartsch M A and Wakefield G H , To Catch a Chorus : Using Chroma-based Representations for Audio Thumbnailing , In Proc. Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) , New Paltz, New York , 2001 , 15--18. Bartsch M A and Wakefield G H, To Catch a Chorus: Using Chroma-based Representations for Audio Thumbnailing, In Proc. Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), New Paltz, New York, 2001, 15--18."},{"key":"e_1_3_2_1_5_1","volume-title":"Proc. International Conference on Music Information Retrieval","author":"Cooper M","year":"2002","unstructured":"Cooper M and Foote J , Automatic Music Summarization via Similarity Analysis , In Proc. International Conference on Music Information Retrieval , Paris, France , 2002 , 81--85. Cooper M and Foote J, Automatic Music Summarization via Similarity Analysis, In Proc. International Conference on Music Information Retrieval, Paris, France, 2002, 81--85."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/957013.957057"},{"key":"e_1_3_2_1_7_1","volume-title":"Proc. of Asian Conference on Computer Vision","author":"Yow D.","year":"1995","unstructured":"Yow , D. , Yeo , B.L. , Yeung , M. , and Liu , G ., Analysis and presentation of soccer highlights from digital video , In Proc. of Asian Conference on Computer Vision , Singapore , 1995 , vol. II , 499--503. Yow, D., Yeo, B.L., Yeung, M., and Liu, G., Analysis and presentation of soccer highlights from digital video, In Proc. of Asian Conference on Computer Vision, Singapore, 1995, vol. II, 499--503."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2002.1035774"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/641007.641119"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1006\/jvci.1996.0030"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2003.1246738"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/957013.957103"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2004.1394641"},{"key":"e_1_3_2_1_14_1","volume-title":"Song Structure. MUSIC TECH magazine. www.musictechmag.co.uk (Oct","author":"Ten Minute Master No","year":"2003","unstructured":"Ten Minute Master No 18 : Song Structure. MUSIC TECH magazine. www.musictechmag.co.uk (Oct . 2003 ), 62--63. Ten Minute Master No 18: Song Structure. MUSIC TECH magazine. www.musictechmag.co.uk (Oct. 2003), 62--63."},{"key":"e_1_3_2_1_15_1","volume-title":"Proc. IEEE International Conference on Acoustics Speech and Signal Processing","author":"Goto M A","year":"2003","unstructured":"Goto M A , Chorus-section detecting method for musical audio signals , In Proc. IEEE International Conference on Acoustics Speech and Signal Processing , Hong Kong , 6-10 April , 2003 . Goto M A, Chorus-section detecting method for musical audio signals, In Proc. IEEE International Conference on Acoustics Speech and Signal Processing, Hong Kong, 6-10 April, 2003."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/646284.688010"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1027527.1027549"},{"key":"e_1_3_2_1_18_1","volume-title":"Science of Sound","author":"Rossing T.D.","year":"2001","unstructured":"Rossing , T.D. , Moore , F.R. , and Wheeler , P.A. , Science of Sound . Addison Wesley , 3 rd Edition 2001 . Rossing, T.D., Moore, F.R., and Wheeler, P.A., Science of Sound. Addison Wesley, 3rd Edition 2001.","edition":"3"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/375360.375365"},{"key":"e_1_3_2_1_20_1","volume-title":"Proc. ISMIR","author":"Sheh A.","year":"2003","unstructured":"Sheh , A. , and Ellis , D.P.W. , Chord Segmentation and Recognition using EM-Trained Hidden Markov Models . In Proc. ISMIR 2003 . Sheh, A., and Ellis, D.P.W., Chord Segmentation and Recognition using EM-Trained Hidden Markov Models. In Proc. ISMIR 2003."},{"key":"e_1_3_2_1_21_1","volume-title":"Dept. of Engineering","author":"Young S","year":"2002","unstructured":"Young S , The HTK Book , Dept. of Engineering , University of Cambridge , Version 3.2, 2002 . Young S et al., The HTK Book, Dept. of Engineering, University of Cambridge, Version 3.2, 2002."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","DOI":"10.1109\/9780470544402","volume-title":"Discrete-Time Processing of Speech Signals","author":"Deller J. R.","year":"1999","unstructured":"Deller , J. R. , Hansen , J.H.L. , and Proakis , H. J. G . Discrete-Time Processing of Speech Signals , IEEE Press ( 1999 ). Deller, J. R., Hansen, J.H.L., and Proakis, H. J. G. Discrete-Time Processing of Speech Signals, IEEE Press (1999)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1162\/15324430152733142"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/93.311653"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/645318.649240"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/500933.500941"},{"key":"e_1_3_2_1_27_1","volume-title":"The Associated Board of the Royal Schools of Music, 14 Bedford Square","author":"Rudiments","year":"1949","unstructured":"Rudiments and Theory of Music. The Associated Board of the Royal Schools of Music, 14 Bedford Square , London , WC 1B 3JG, 1949 . Rudiments and Theory of Music. The Associated Board of the Royal Schools of Music, 14 Bedford Square, London, WC1B 3JG, 1949."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/57167.57203"}],"event":{"name":"SIGIR05: The 28th ACM\/SIGIR International Symposium on Information Retrieval 2005","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Salvador Brazil","acronym":"SIGIR05"},"container-title":["Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1076034.1076097","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1076034.1076097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T16:08:16Z","timestamp":1750262896000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1076034.1076097"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005,8,15]]},"references-count":28,"alternative-id":["10.1145\/1076034.1076097","10.1145\/1076034"],"URL":"https:\/\/doi.org\/10.1145\/1076034.1076097","relation":{},"subject":[],"published":{"date-parts":[[2005,8,15]]},"assertion":[{"value":"2005-08-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}