{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,2]],"date-time":"2022-04-02T19:43:27Z","timestamp":1648928607464},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2011,9,20]],"date-time":"2011-09-20T00:00:00Z","timestamp":1316476800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2013,3]]},"DOI":"10.1007\/s11042-011-0877-z","type":"journal-article","created":{"date-parts":[[2011,9,19]],"date-time":"2011-09-19T12:11:36Z","timestamp":1316434296000},"page":"387-406","source":"Crossref","is-referenced-by-count":2,"title":["Narrative theme navigation for sitcoms supported by fan-generated scripts"],"prefix":"10.1007","volume":"63","author":[{"given":"Gerald","family":"Friedland","sequence":"first","affiliation":[]},{"given":"Luke","family":"Gottlieb","sequence":"additional","affiliation":[]},{"given":"Adam","family":"Janin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2011,9,20]]},"reference":[{"key":"877_CR1","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1145\/1386352.1386412","volume-title":"CIVR \u201908: proceedings of the 2008 international conference on content-based image and video retrieval","author":"J Adcock","year":"2008","unstructured":"Adcock J, Cooper M, Pickens J (2008) Experiments in interactive video search by addition and subtraction. In: CIVR \u201908: proceedings of the 2008 international conference on content-based image and video retrieval. ACM, New York, pp\u00a0465\u2013474. doi: 10.1145\/1386352.1386412"},{"issue":"7\u20138","key":"877_CR2","first-page":"692","volume":"22","author":"S Ayache","year":"2007","unstructured":"Ayache S, Qu\u00e9not G (2007) Evaluation of active learning strategies for video indexing. Image Commun. 22(7\u20138):692\u2013704. doi: 10.1016\/j.image.2007.05.010","journal-title":"Image Commun."},{"key":"877_CR3","doi-asserted-by":"crossref","unstructured":"Benitez AB, Ab ABB, Smith JR, Chang SF (2000) Medianet: a multimedia information network for knowledge representation","DOI":"10.1117\/12.403791"},{"issue":"7","key":"877_CR4","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1016\/j.image.2008.04.018","volume":"23","author":"S Berrani","year":"2008","unstructured":"Berrani S, Manson G, Lechat P (2008) A non-supervised approach for repeated sequence detection in TV broadcast streams. Signal Process Image Commun 23(7):525\u2013537","journal-title":"Signal Process Image Commun"},{"key":"877_CR5","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1145\/1101149.1101235","volume-title":"MULTIMEDIA \u201905: proceedings of the 13th annual ACM international conference on multimedia","author":"M Bertini","year":"2005","unstructured":"Bertini M, Del\u00a0Bimbo A, Torniai C (2005) Automatic video annotation using ontologies extended with visual information. In: MULTIMEDIA \u201905: proceedings of the 13th annual ACM international conference on multimedia. ACM, New York, pp\u00a0395\u2013398. doi: 10.1145\/1101149.1101235"},{"key":"877_CR6","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1145\/217279.215080","volume-title":"MULTIMEDIA \u201995: proceedings of the third ACM international conference on multimedia","author":"MG Brown","year":"1995","unstructured":"Brown MG, Foote JT, Jones GJF, Sparck\u00a0Jones K, Young SJ (1995) Automatic content-based retrieval of broadcast news. In: MULTIMEDIA \u201995: proceedings of the third ACM international conference on multimedia. ACM, New York, pp 35\u201343. doi: 10.1145\/217279.215080"},{"issue":"2","key":"877_CR7","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1006\/jvci.1997.0404","volume":"10","author":"R Brunelli","year":"1999","unstructured":"Brunelli R, Mich O, Modena CM (1999) A survey on the automatic indexing of video data. J Vis Commun Image Represent 10(2):78\u2013112. doi: 10.1006\/jvci.1997.0404","journal-title":"J Vis Commun Image Represent"},{"issue":"9","key":"877_CR8","doi-asserted-by":"crossref","first-page":"1520","DOI":"10.1109\/TPAMI.2007.70801","volume":"30","author":"E Bruno","year":"2008","unstructured":"Bruno E, Moenne-Loccoz N, Marchand-Maillet S (2008) Design of multimodal dissimilarity spaces for retrieval of video documents. IEEE Trans Pattern Anal Mach Intell 30(9):1520\u20131533. doi: 10.1109\/TPAMI.2007.70801","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"877_CR9","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1109\/76.718507","volume":"8","author":"S fu Chang","year":"1998","unstructured":"fu Chang S, Chen W, Meng HJ, Sundaram H, Zhong D (1998) A fully automated content-based video search engine supporting spatiotemporal queries. IEEE Trans Circuits Syst Video Technol 8:602\u2013615","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"877_CR10","doi-asserted-by":"crossref","first-page":"561","DOI":"10.1145\/641007.641120","volume-title":"MULTIMEDIA \u201902: proceedings of the tenth ACM international conference on multimedia","author":"MG Christel","year":"2002","unstructured":"Christel MG, Hauptmann AG, Wactlar HD, Ng TD (2002) Collages as dynamic summaries for news video. In: MULTIMEDIA \u201902: proceedings of the tenth ACM international conference on multimedia. ACM, New York, pp 561\u2013569. doi: 10.1145\/641007.641120"},{"key":"877_CR11","doi-asserted-by":"crossref","first-page":"1054","DOI":"10.1145\/1291233.1291463","volume-title":"MULTIMEDIA \u201907: proceedings of the 15th international conference on multimedia","author":"TS Chua","year":"2007","unstructured":"Chua TS (2007) Towards the next plateau: innovative multimedia research beyond trecvid. In: MULTIMEDIA \u201907: proceedings of the 15th international conference on multimedia. ACM, New York, pp 1054\u20131054. doi: 10.1145\/1291233.1291463"},{"key":"877_CR12","doi-asserted-by":"crossref","unstructured":"Friedland G, Vinyals O (2008) Live speaker identification in conversations. In: Proceedings of ACM multimedia. ACM, pp\u00a01017\u20131018","DOI":"10.1145\/1459359.1459558"},{"key":"877_CR13","doi-asserted-by":"crossref","unstructured":"Friedland G, Gottlieb L, Janin A (2009) Joke-o-Mat: browsing sticoms punchline-by-punchline. In: Proceedings of ACM multimedia. ACM, pp 1115\u20131116","DOI":"10.1145\/1631272.1631525"},{"key":"877_CR14","doi-asserted-by":"crossref","unstructured":"Friedland G, Yeo C, Hung H (2009) Visual speaker localization aided by acoustic models. In: Proceedings of ACM multimedia. ACM, pp 195\u2013202","DOI":"10.1145\/1631272.1631301"},{"key":"877_CR15","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1145\/1877850.1877854","volume-title":"Proceedings of the 3rd international workshop on automated information extraction in media production","author":"G Friedland","year":"2010","unstructured":"Friedland G, Gottlieb L, Janin A (2010) Narrative theme navigation for sitcoms supported by fan-generated scripts. In: Proceedings of the 3rd international workshop on automated information extraction in media production. ACM, New York, pp\u00a03\u20138. doi: 10.1145\/1877850.1877854"},{"issue":"1\u20132","key":"877_CR16","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/S0167-6393(01)00061-9","volume":"37","author":"JL Gauvain","year":"2002","unstructured":"Gauvain JL, Lamel L, Adda G (2002) The limsi broadcast news transcription system. Speech Commun 37(1\u20132):89\u2013108. doi: 10.1016\/S0167-6393(01)00061-9","journal-title":"Speech Commun"},{"key":"877_CR17","first-page":"564","volume-title":"MULTIMEDIA \u201904: proceedings of the 12th annual ACM international conference on multimedia","author":"KS Goh","year":"2004","unstructured":"Goh KS, Chang EY, Lai WC Multimodal concept-dependent active learning for image retrieval. In: MULTIMEDIA \u201904: proceedings of the 12th annual ACM international conference on multimedia. ACM, New York, pp 564\u2013571 (2004). doi: 10.1145\/1027527.1027664"},{"issue":"5","key":"877_CR18","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1145\/253769.253798","volume":"40","author":"A Gupta","year":"1997","unstructured":"Gupta A, Jain R (1997) Visual information retrieval. Commun ACM 40(5):70\u201379. doi: 10.1145\/253769.253798","journal-title":"Commun ACM"},{"key":"877_CR19","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1145\/1282280.1282286","volume-title":"CIVR \u201907: proceedings of the 6th ACM international conference on image and video retrieval","author":"A Haubold","year":"2007","unstructured":"Haubold A, Kender JR (2007) Vast mm: multimedia browser for presentation video. In: CIVR \u201907: proceedings of the 6th ACM international conference on image and video retrieval. ACM, New York, pp\u00a041\u201348. doi: 10.1145\/1282280.1282286"},{"key":"877_CR20","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1145\/1101149.1101256","volume-title":"MULTIMEDIA \u201905: proceedings of the 13th annual ACM international conference on multimedia","author":"L Hollink","year":"2005","unstructured":"Hollink L, Worring M (2005) Building a visual ontology for video retrieval. In: MULTIMEDIA \u201905: proceedings of the 13th annual ACM international conference on multimedia. ACM, New York, pp\u00a0479\u2013482. doi: 10.1145\/1101149.1101256"},{"key":"877_CR21","doi-asserted-by":"crossref","unstructured":"Hoogs A, Rittscher J, Stein G, Schmiederer J (2003) Video content annotation using visual analysis and a large semantic knowledgebase. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, pp\u00a0327\u2013334","DOI":"10.1109\/CVPR.2003.1211487"},{"key":"877_CR22","series-title":"Lecture notes in computer science","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1007\/978-3-540-77051-0_8","volume-title":"Proceedings of the second international conference on semantic and digital media technologies, SAMT 2007","author":"M Huijbregts","year":"2007","unstructured":"Huijbregts M, Ordelman R, de\u00a0Jong F (2007) Annotation of heterogeneous multimedia content using automatic speech recognition. In: Proceedings of the second international conference on semantic and digital media technologies, SAMT 2007. Lecture notes in computer science, vol\u00a04816. Springer, Berlin, pp\u00a078\u201390. http:\/\/doc.utwente.nl\/62090\/"},{"key":"877_CR23","first-page":"1591","volume-title":"Proceedings of the ACM international conference on multimedia 2010","author":"A Janin","year":"2010","unstructured":"Janin A, Gottlieb L, Friedland G (2010) Joke-o-Mat HD: browsing sitcoms with human derived transcripts. In: Proceedings of the ACM international conference on multimedia 2010. ACM, New York, pp\u00a01591\u20131594. doi: 10.1145\/1873951.1874295"},{"key":"877_CR24","unstructured":"Jong FD, luc Gauvain J, Hartog JD, Netter K (1998) Olive: speech based video retrieval"},{"key":"877_CR25","doi-asserted-by":"crossref","unstructured":"Larson M, Newman E, Jones G (2008) Overview of videoclef 2008: automatic generation of topic-based feeds for dual language audio-visual content. In: Working notes for the CLEF 2008 workshop, Aarhus","DOI":"10.1007\/978-3-642-04447-2_119"},{"key":"877_CR26","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1145\/1282280.1282373","volume-title":"CIVR \u201907: proceedings of the 6th ACM international conference on image and video retrieval","author":"A Natsev","year":"2007","unstructured":"Natsev A, Te\u0161i\u0107 J, Xie L, Yan R, Smith JR (2007) Ibm multimedia search and retrieval system. In: CIVR \u201907: proceedings of the 6th ACM international conference on image and video retrieval. ACM, New York, pp\u00a0645\u2013645. doi: 10.1145\/1282280.1282373"},{"key":"877_CR27","unstructured":"NIST Rich Transcription Evaluation. http:\/\/www.itl.nist.gov\/iad\/mig\/tests\/rt\/"},{"key":"877_CR28","unstructured":"NIST TRECVid Evaluation. http:\/\/www-nlpir.nist.gov\/projects\/trecvid\/"},{"key":"877_CR29","doi-asserted-by":"crossref","unstructured":"Niu F, Goela N, Divakaran A, Abdel-Mottaleb M (2008) Audio scene segmentation for video with generic content. In: Proceedings of SPIE, vol\u00a06820, p\u00a068200S","DOI":"10.1117\/12.760267"},{"issue":"1\u20132","key":"877_CR30","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/0167-6393(95)00009-D","volume":"17","author":"DA Reynolds","year":"1995","unstructured":"Reynolds DA (1995) Speaker identification and verification using gaussian mixture speaker models. Speech Commun 17(1\u20132):91\u2013108. doi: 10.1016\/0167-6393(95)00009-D","journal-title":"Speech Commun"},{"key":"877_CR31","doi-asserted-by":"crossref","unstructured":"Reynolds DA, Torres-Carrasquillo P (2005) Approaches and applications of audio diarization. In: Proceedings of the IEEE ICASSP","DOI":"10.1109\/ICASSP.2005.1416463"},{"key":"877_CR32","doi-asserted-by":"crossref","first-page":"811","DOI":"10.1145\/1291233.1291417","volume-title":"MULTIMEDIA \u201907: proceedings of the 15th international conference on multimedia","author":"O Rooij de","year":"2007","unstructured":"de\u00a0Rooij O, Snoek CGM, Worring M (2007) Query on demand video browsing. In: MULTIMEDIA \u201907: proceedings of the 15th international conference on multimedia. ACM, New York, pp\u00a0811\u2013814. doi: 10.1145\/1291233.1291417"},{"issue":"1","key":"877_CR33","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1109\/93.752960","volume":"6","author":"S Satoh","year":"1999","unstructured":"Satoh S, Nakamura Y, Kanade T (1999) Name-it: naming and detecting faces in news videos. IEEE Multimed 6(1):22\u201335","journal-title":"IEEE Multimed"},{"issue":"4","key":"877_CR34","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1561\/1500000014","volume":"2","author":"CGM Snoek","year":"2009","unstructured":"Snoek CGM, Worring M (2009) Concept-based video retrieval. Foundam Trends Inf Retr 2(4):215\u2013322. doi: 10.1561\/1500000014","journal-title":"Foundam Trends Inf Retr"},{"issue":"3","key":"877_CR35","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1109\/MMUL.2008.66","volume":"15","author":"Q Sun","year":"2008","unstructured":"Sun Q, H\u00fcrst W (2008) Video browsing on handheld devices: interface designs for the next generation of mobile video players. IEEE Multimed 15(3):76\u201383. doi: 10.1109\/MMUL.2008.66","journal-title":"IEEE Multimed"},{"key":"877_CR36","doi-asserted-by":"crossref","unstructured":"Vinyals O, Friedland G (2008) Towards semantic analysis of conversations: a system for the live identification of speakers in meetings. In: Proceedings of IEEE international conference on semantic computing, pp\u00a0456\u2013459","DOI":"10.1109\/ICSC.2008.58"},{"issue":"5","key":"877_CR37","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1109\/2.493456","volume":"29","author":"H Wactlar","year":"1996","unstructured":"Wactlar H, Kanade T, Smith M, Stevens S (1996) Intelligent access to digital video: informedia project. Computer 29(5):46\u201352","journal-title":"Computer"},{"key":"877_CR38","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1007\/978-3-540-68585-2_47","volume-title":"Multimodal technologies for perception of humans: international evaluation workshops CLEAR 2007 and RT 2007, Baltimore, MD, USA, 8\u201311 May 2007, revised selected papers","author":"C Wooters","year":"2008","unstructured":"Wooters C, Huijbregts M (2008) The ICSI RT07s speaker diarization system. In: Multimodal technologies for perception of humans: international evaluation workshops CLEAR 2007 and RT 2007, Baltimore, MD, USA, 8\u201311 May 2007, revised selected papers. Springer, Berlin, Heidelberg, pp\u00a0509\u2013519. doi: 10.1007\/978-3-540-68585-2_47"},{"key":"877_CR39","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1145\/1180639.1180699","volume-title":"MULTIMEDIA \u201906: proceedings of the 14th annual ACM international conference on multimedia","author":"C Xu","year":"2006","unstructured":"Xu C, Wang J, Wan K, Li Y, Duan L (2006) Live sports event detection based on broadcast video and web-casting text. In: MULTIMEDIA \u201906: proceedings of the 14th annual ACM international conference on multimedia. ACM, New York, pp 221\u2013230. doi: 10.1145\/1180639.1180699"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-011-0877-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-011-0877-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-011-0877-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,5]],"date-time":"2021-12-05T15:06:14Z","timestamp":1638716774000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-011-0877-z"}},"subtitle":["Video navigation based on acoustic detection of actors and narrative elements"],"short-title":[],"issued":{"date-parts":[[2011,9,20]]},"references-count":39,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2013,3]]}},"alternative-id":["877"],"URL":"https:\/\/doi.org\/10.1007\/s11042-011-0877-z","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,9,20]]}}}