{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T08:40:20Z","timestamp":1737362420571,"version":"3.33.0"},"publisher-location":"Berlin, Heidelberg","reference-count":43,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540728948"},{"type":"electronic","value":"9783540728955"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007]]},"DOI":"10.1007\/978-3-540-72895-5_8","type":"book-chapter","created":{"date-parts":[[2007,8,11]],"date-time":"2007-08-11T08:59:57Z","timestamp":1186822797000},"page":"225-249","source":"Crossref","is-referenced-by-count":1,"title":["Semantic Video Indexing"],"prefix":"10.1007","author":[{"given":"Cees G. M.","family":"Snoek","sequence":"first","affiliation":[]},{"given":"Marcel","family":"Worring","sequence":"additional","affiliation":[]},{"given":"Jan-Mark","family":"Geusebroek","sequence":"additional","affiliation":[]},{"given":"Dennis C.","family":"Koelma","sequence":"additional","affiliation":[]},{"given":"Frank J.","family":"Seinstra","sequence":"additional","affiliation":[]},{"given":"Arnold W. M.","family":"Smeulders","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"8_CR1","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1155\/S1110865703211173","volume":"2","author":"W. H. Adams","year":"2003","unstructured":"W. H. Adams, G. Iyengar, C.-Y. Lin, M.R. Naphade, C. Neti, H.J. Nock, and J.R. Smith. Semantic indexing of multimedia content using visual, audio, and text cues. EURASIP Journal on Applied Signal Processing, (2):170\u2013185, 2003.","journal-title":"EURASIP Journal on Applied Signal Processing"},{"issue":"2","key":"8_CR2","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1023\/A:1011395131992","volume":"14","author":"A.A. Alatan","year":"2001","unstructured":"A.A. Alatan, A.N. Akansu, and W. Wolf. Multimodal dialogue scene detection using hidden Markov models for content-based multimedia indexing. Multimedia Tools Applicat., 14(2):137\u2013151, 2001.","journal-title":"Multimedia Tools Applicat."},{"key":"8_CR3","volume-title":"Proc. TRECVID Workshop","author":"A. Amir","year":"2003","unstructured":"A. Amir, M. Berg, S.-F. Chang, W. Hsu, G. Iyengar, C.-Y. Lin, M.R. Naphade, A.P. Natsev, C. Neti, H.J. Nock, J.R. Smith, B.L. Tseng, Y. Wu, and D. Zhang. IBM research TRECVID-2003 video retrieval system. In Proc. TRECVID Workshop, NIST Special Publication, Gaithersburg, USA, 2003."},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"J. Baan, A. van Ballegooij, J.-M. Geusebroek, D. Hiemstra, J. den Hartog, J. List, C. Snoek, I. Patras, S. Raaijmakers, L. Todoran, J. Vendrig, A. de Vries, T. Westerveld, and M. Worring. Lazy users and automatic video retrieval tools in (the) lowlands. In E.M. Voorhees and D.K. Harman, editors, Proc. 10th Text REtrieval Conference, volume 500-250 of NIST Special Publication, Gaithersburg, USA, 2001.","DOI":"10.6028\/NIST.SP.500-250.video-lowlands"},{"issue":"1","key":"8_CR5","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1109\/6046.985555","volume":"4","author":"N. Babaguchi","year":"2002","unstructured":"N. Babaguchi, Y. Kawai, and T. Kitahashi. Event based indexing of broadcasted sports video by intermodal collaboration. IEEE Trans. Multimedia, 4(1):68\u201375, 2002.","journal-title":"IEEE Trans. Multimedia"},{"issue":"4","key":"8_CR6","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1145\/506106.506115","volume":"34","author":"H.E. Bal","year":"2000","unstructured":"H.E. Bal et al. The distributed ASCI supercomputer project. Operating Syst. Review, 34(4):76\u201396, 2000.","journal-title":"Operating Syst. Review"},{"key":"8_CR7","volume-title":"The Art of Watching Films","author":"J.M. Boggs","year":"2000","unstructured":"J.M. Boggs and D.W. Petrie. The Art of Watching Films. Mayfield Publishing Company, Mountain View, USA, 5th edition, 2000.","edition":"5th edition"},{"issue":"2","key":"8_CR8","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1147\/rd.422.0233","volume":"42","author":"R.M. Bolle","year":"1998","unstructured":"R.M. Bolle, B.-L. Yeo, and M.M. Yeung. Video query: Research directions. IBM Journal of Research and Development, 42(2):233\u2013252, 1998.","journal-title":"IBM Journal of Research and Development"},{"key":"8_CR9","volume-title":"Film Art: An Introduction","author":"D. Bordwell","year":"1997","unstructured":"D. Bordwell and K. Thompson. Film Art: An Introduction. McGraw-Hill, New York, USA, 5th edition, 1997.","edition":"5th edition"},{"issue":"2","key":"8_CR10","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1006\/jvci.1997.0404","volume":"10","author":"R. Brunelli","year":"1999","unstructured":"R. Brunelli, O. Mich, and C.M. Modena. A survey on the automatic indexing of video data. J. Visual Commun. Image Representation, 10(2):78\u2013112, 1999.","journal-title":"J. Visual Commun. Image Representation"},{"issue":"2","key":"8_CR11","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1023\/A:1009715923555","volume":"2","author":"C.J.C. Burges","year":"1998","unstructured":"C.J.C. Burges. A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, 2(2):121\u2013167, 1998.","journal-title":"Data Mining and Knowledge Discovery"},{"key":"8_CR12","unstructured":"C.-C. Chang and C.-J. Lin. LIBSVM: a library for Support Vector Machines, 2001. http:\/\/www.csie.ntu.edu.tw\/~cjlin\/libsvm\/."},{"issue":"1","key":"8_CR13","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1109\/TMM.2003.819583","volume":"6","author":"J. Fan","year":"2004","unstructured":"J. Fan, A.K. Elmagarmid, X. Zhu, W.G. Aref, and L. Wu. ClassView: hierarchical video shot classification, indexing, and accessing. IEEE Trans. Multimedia, 6(1):70\u201386, 2004.","journal-title":"IEEE Trans. Multimedia"},{"issue":"1\u20132","key":"8_CR14","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/S0167-6393(01)00061-9","volume":"37","author":"J.L. Gauvain","year":"2002","unstructured":"J.L. Gauvain, L. Lamel, and G. Adda. The LIMSI broadcast news transcription system. Speech Commun., 37(1\u20132):89\u2013108, 2002.","journal-title":"Speech Commun."},{"issue":"12","key":"8_CR15","doi-asserted-by":"publisher","first-page":"1338","DOI":"10.1109\/34.977559","volume":"23","author":"J.M. Geusebroek","year":"2001","unstructured":"J.M. Geusebroek, R. van den Boomgaard, A.W.M. Smeulders, and H. Geerts. Color invariance. IEEE Trans. Pattern Anal. Machine Intell., 23(12):1338\u20131350, 2001.","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"issue":"6","key":"8_CR16","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1109\/76.867923","volume":"10","author":"N. Haering","year":"2000","unstructured":"N. Haering, R. Qian, and I. Sezan. A semantic event-detection approach and its application to detecting hunts in wildlife video. IEEE Trans. Circuits Syst. Video Technol., 10(6):857\u2013868, 2000.","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"8_CR17","first-page":"674","volume":"3115","author":"A.G. Hauptmann","year":"2004","unstructured":"A.G. Hauptmann. Towards a large scale concept ontology for broadcast video. In CIVR, volume 3115 of LNCS, pages 674\u2013675. Springer-Verlag, 2004.","journal-title":"CIVR"},{"key":"8_CR18","volume-title":"Proc. TRECVID Workshop","author":"A.G. Hauptmann","year":"2003","unstructured":"A.G. Hauptmann, R.V. Baron, M.-Y. Chen, M. Christel, P. Duygulu, C. Huang, R. Jin, W.-H. Lin, T. Ng, N. Moraveji, N. Papernick, C.G.M. Snoek, G. Tzanetakis, J. Yang, R. Yang, and H.D. Wactlar. Informedia at TRECVID 2003: Analyzing and searching broadcast news video. In Proc. TRECVID Workshop, NIST Special Publication, Gaithersburg, USA, 2003."},{"issue":"1","key":"8_CR19","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/34.824819","volume":"22","author":"A.K. Jain","year":"2000","unstructured":"A.K. Jain, R.P.W. Duin, and J. Mao. Statistical pattern recognition: A review. IEEE Trans. Pattern Anal. Machine Intell., 22(1):4\u201337, 2000.","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"key":"8_CR20","volume-title":"Proc. TRECVID Workshop","author":"C.-Y. Lin","year":"2003","unstructured":"C.-Y. Lin, B.L. Tseng, and J.R. Smith. Video collaborative annotation forum: Establishing ground-truth labels on large multimedia datasets. In Proc. TRECVID Workshop, NIST Special Publication, Gaithersburg, USA, 2003."},{"key":"8_CR21","volume-title":"Foundations of Statistical Natural Language Processing","author":"C.D. Manning","year":"1999","unstructured":"C.D. Manning and H. Sch\u00fctze. Foundations of Statistical Natural Language Processing. The MIT Press, Cambridge, USA, 1999."},{"issue":"3","key":"8_CR22","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1016\/j.jvcir.2004.04.010","volume":"15","author":"M.R. Naphade","year":"2004","unstructured":"M.R. Naphade. On supervision and statistical learning for semantic multimedia analysis. J. Visual Commun. Image Representation, 15(3):348\u2013369, 2004.","journal-title":"J. Visual Commun. Image Representation"},{"issue":"4","key":"8_CR23","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1109\/TNN.2002.1021881","volume":"13","author":"M.R. Naphade","year":"2002","unstructured":"M.R. Naphade and T.S. Huang. Extracting semantics from audiovisual content: The final frontier in multimedia retrieval. IEEE Trans. Neural Networks, 13(4):793\u2013810, 2002.","journal-title":"IEEE Trans. Neural Networks"},{"key":"8_CR24","unstructured":"NIST. TREC Video Retrieval Evaluation. http:\/\/www-nlpir.nist.gov\/projects\/trecvid\/."},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"J.C. Platt. Probabilities for SV machines. In A.J. Smola, P.L. Bartlett, B. Sch\u00f6lkopf, and D. Schuurmans, editors, Advances in Large Margin Classifiers, pages 61\u201374. MIT Press, 2000.","DOI":"10.7551\/mitpress\/1113.003.0008"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"G.M. Qu\u00e9not, D. Moraru, L. Besacier, and P. Mulhem. CLIPS at TREC-11: Experiments in video retrieval. In E.M. Voorhees and L.P. Buckland, editors, Proc. 11th Text REtrieval Conference, volume 500-251 of NIST Special Publication, Gaithersburg, USA, 2002.","DOI":"10.6028\/NIST.SP.500-251.video-clips-imag"},{"issue":"5","key":"8_CR27","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/s005300050140","volume":"7","author":"T. Sato","year":"1999","unstructured":"T. Sato, T. Kanade, E.K. Hughes, M.A. Smith, and S. Satoh. Video OCR: Indexing digital news libraries by recognition of superimposed caption. Multimedia Syst., 7(5):385\u2013395, 1999.","journal-title":"Multimedia Syst."},{"issue":"3","key":"8_CR28","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1023\/B:VISI.0000011202.85607.00","volume":"56","author":"H. Schneiderman","year":"2004","unstructured":"H. Schneiderman and T. Kanade. Object detection using the statistics of parts. Int\u2019l J. Comput. Vision, 56(3):151\u2013177, 2004.","journal-title":"Int\u2019l J. Comput. Vision"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"F.J. Seinstra, C.G.M. Snoek, D. Koelma, J.M. Geusebroek, and M. Worring. User transparent parallel processing of the 2004 NIST TRECVID data set. In Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS\u201905), pages 90\u201398, Denver, USA, 2005.","DOI":"10.1109\/IPDPS.2005.443"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"A.F. Smeaton, W. Kraaij, and P. Over. The TREC VIDeo retrieval evaluation (TRECVID): A case study and status report. In Proc. RIAO 2004, Avignon, France, 2004.","DOI":"10.1145\/1027527.1027678"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"A.F. Smeaton, P. Over, and W. Kraaij. TRECVID: Evaluating the effectiveness of information retrieval tasks on digital video. In Proceedings of the ACM MM\u201904 (Multimedia), pages 652\u2013655, New York, USA, 2004.","DOI":"10.1145\/1027527.1027678"},{"issue":"12","key":"8_CR32","doi-asserted-by":"publisher","first-page":"1349","DOI":"10.1109\/34.895972","volume":"22","author":"A.W.M. Smeulders","year":"2000","unstructured":"A.W.M. Smeulders, M. Worring, S. Santini, A. Gupta, and R. Jain. Content based image retrieval at the end of the early years. IEEE Trans. Pattern Anal. Machine Intell., 22(12):1349\u20131380, 2000.","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"issue":"3","key":"8_CR33","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1109\/93.621578","volume":"4","author":"J.R. Smith","year":"1997","unstructured":"J.R. Smith and S.-F. Chang. Visually searching the Web for content. IEEE Multimedia, 4(3):12\u201320, 1997.","journal-title":"IEEE Multimedia"},{"key":"8_CR34","unstructured":"C.G.M. Snoek. The Authoring Metaphor to Machine Understanding of Multimedia. PhD thesis, University of Amsterdam, 2005."},{"issue":"4","key":"8_CR35","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1109\/TMM.2005.850966","volume":"7","author":"C.G.M. Snoek","year":"2005","unstructured":"C.G.M. Snoek and M. Worring. Multimedia event-based video indexing using time intervals. IEEE Trans. Multimedia, 7(4):638\u2013647, 2005.","journal-title":"IEEE Trans. Multimedia"},{"issue":"1","key":"8_CR36","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/B:MTAP.0000046380.27575.a5","volume":"25","author":"C.G.M. Snoek","year":"2005","unstructured":"C.G.M. Snoek and M. Worring. Multimodal video indexing: A review of the state-of-the-art. Multimedia Tools Applicat., 25(1):5\u201335, 2005.","journal-title":"Multimedia Tools Applicat."},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"C.G.M. Snoek, M. Worring, J. van Gemert, J.M. Geusebroek, D. Koelma, G.P. Nguyen, O. de Rooij, and F. Seinstra. MediaMill: Exploring news video archives based on learned semantics. In Proceedings of the ACM International Conference on Multimedia, pages 225\u2013226, Singapore, November 2005.","DOI":"10.1145\/1101149.1101188"},{"issue":"10","key":"8_CR38","doi-asserted-by":"publisher","first-page":"1678","DOI":"10.1109\/TPAMI.2006.212","volume":"28","author":"C.G.M. Snoek","year":"2006","unstructured":"C.G.M. Snoek, M. Worring, J.M. Geusebroek, D.C. Koelma, F.J. Seinstra, and A.W.M. Smeulders. The semantic pathfinder: Using an authoring metaphor for generic multimedia indexing. IEEE Trans. Pattern Anal. Machine Intell., 28(10):1678\u20131689, 2006.","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"issue":"2","key":"8_CR39","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1145\/1142020.1142021","volume":"2","author":"C.G.M. Snoek","year":"2006","unstructured":"C.G.M. Snoek, M. Worring, and A.G. Hauptmann. Learning rich semantics from news video archives by style analysis. ACM Trans. Multimedia Computing, Comm. Applications, 2(2):91\u2013108, 2006.","journal-title":"ACM Trans. Multimedia Computing, Comm. Applications"},{"key":"8_CR40","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-3264-1","volume-title":"The Nature of Statistical Learning Theory","author":"V.N. Vapnik","year":"2000","unstructured":"V.N. Vapnik. The Nature of Statistical Learning Theory. Springer-Verlag, New York, USA, 2nd edition, 2000.","edition":"2nd edition"},{"issue":"2","key":"8_CR41","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1109\/2.745722","volume":"32","author":"H.D. Wactlar","year":"1999","unstructured":"H.D. Wactlar, M.G. Christel, Y. Gong, and A.G. Hauptmann. Lessons learned from building a terabyte digital video library. IEEE Computer, 32(2):66\u201373, 1999.","journal-title":"IEEE Computer"},{"issue":"6","key":"8_CR42","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1109\/79.888862","volume":"17","author":"Y. Wang","year":"2000","unstructured":"Y. Wang, Z. Liu, and J. Huang. Multimedia content analysis using both audio and visual clues. IEEE Signal Processing Magazine, 17(6):12\u201336, 2000.","journal-title":"IEEE Signal Processing Magazine"},{"issue":"6","key":"8_CR43","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1007\/BF01225243","volume":"2","author":"H.-J. Zhang","year":"1995","unstructured":"H.-J. Zhang, S.Y. Tan, S.W. Smoliar, and Y. Gong. Automatic parsing and indexing of news video. Multimedia Syst., 2(6):256\u2013266, 1995.","journal-title":"Multimedia Syst."}],"container-title":["Multimedia Retrieval"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-72895-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T07:59:29Z","timestamp":1737359969000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-72895-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"ISBN":["9783540728948","9783540728955"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-72895-5_8","relation":{},"subject":[],"published":{"date-parts":[[2007]]}}}