{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T23:33:00Z","timestamp":1791070380374,"version":"4.1.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2001,9,1]],"date-time":"2001-09-01T00:00:00Z","timestamp":999302400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2001,9,1]],"date-time":"2001-09-01T00:00:00Z","timestamp":999302400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimedia Tools and Applications"],"published-print":{"date-parts":[[2001,9]]},"DOI":"10.1023\/a:1011315803415","type":"journal-article","created":{"date-parts":[[2002,12,23]],"date-time":"2002-12-23T09:44:13Z","timestamp":1040636653000},"page":"59-81","source":"Crossref","is-referenced-by-count":20,"title":["Scene Determination Based on Video and Audio Features"],"prefix":"10.1007","volume":"15","author":[{"given":"Silvia","family":"Pfeiffer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rainer","family":"Lienhart","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wolfgang","family":"Efflsberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"354298_CR1","doi-asserted-by":"crossref","unstructured":"H. Aoki, S. Shimotsuji, and O. Hori, \u201cA shot classification method of selecting effective key-frames for video browsing,\u201d in Proc. ACM Multimedia 96, Nov. 1996, Boston, MA, pp. 1\u201310.","DOI":"10.1145\/244130.244135"},{"key":"354298_CR2","doi-asserted-by":"crossref","unstructured":"F. Arman, R. Depommier, A. Hsu, and M.-Y. Chiu, \u201cContent-based browsing of video sequences,\u201d in Proc. ACM Multimedia 94, San Francisco, CA, Oct. 1994, pp. 97\u2013103.","DOI":"10.1145\/192593.192630"},{"key":"354298_CR3","volume-title":"Directing Television and Film","author":"A.A. Armer","year":"1990","unstructured":"A.A. Armer, Directing Television and Film, Wadsworth Publishing Co., 2nd ed., Belmont, CA, 1990.","edition":"2nd ed."},{"key":"354298_CR4","volume-title":"Dictionary of Film Terms","author":"F. Beaver","year":"1994","unstructured":"F. Beaver, Dictionary of Film Terms, Twayne Publishing, New York, 1994."},{"key":"354298_CR5","unstructured":"S. Belognie, C. Carson, H. Greenspan, and J. Malik, \u201cRecognition of images in large databases using a learning framework,\u201d UC Berkeley CS Technical Report 97\u2013939, 1997."},{"issue":"2","key":"354298_CR6","doi-asserted-by":"crossref","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, \u201cVideo query: Research directions,\u201d IBM Journal of Research and Development, Vol. 42, No. 2, pp. 233\u2013252, 1998.","journal-title":"IBM Journal of Research and Development"},{"key":"354298_CR7","volume-title":"Film Art: An Introduction","author":"D. Bordwell","year":"1993","unstructured":"D. Bordwell and K. Thompson, Film Art: An Introduction, McGraw-Hill, Inc., 4th ed., New York, NY, 1993.","edition":"4th ed."},{"key":"354298_CR8","first-page":"459","volume":"I","author":"M. Gorkani","year":"1995","unstructured":"M. Gorkani and R.W. Picard, \u201cTexture orientation for sorting photos \u201cat a Glance,\u201d\u201d in Proc. International Conference on Pattern Recognition, Jerusalem, 1995, Vol. I, pp. 459\u2013464.","journal-title":"Proc. International Conference on Pattern Recognition, Jerusalem"},{"key":"354298_CR9","unstructured":"A.G. Hauptmann and M.A. Smith, \u201cText, speech, and vision for video segmentation: The informedia project,\u201d in AAAI-95 Fall Symposium on Computational Models for Integrating Language and Vision, Nov. 1995."},{"key":"354298_CR10","unstructured":"J. Huang, S.R. Kumar, M. Mitra, W.-J. Zhu, and R. Zabih, \u201cImage indexing using color correlograms,\u201d in IEEE Computer Vision and Pattern Recognition Conference, San Juan, Puerto Rico, June 1997, pp. 762\u2013768."},{"key":"354298_CR11","unstructured":"M. Hunke, Locating and Tracking of Human Faces With Neural Networks, Master's thesis, University of Karlsruhe, 1994. http:\/\/ernie.sfsu.edu\/~hunke\/"},{"key":"354298_CR12","volume-title":"Concepts, Algorithms, and Scientific Applications","author":"B. J\u00e4hne","year":"1995","unstructured":"B. J\u00e4hne, Digital Image Processing. Concepts, Algorithms, and Scientific Applications, Springer-Verlag: Berlin, Heidelberg, New York, 1995."},{"key":"354298_CR13","unstructured":"S. Lawrence, C.L. Giles, A.C. Tsoi, and A.D. Back, \u201cFace recognition: A convolutional neural network approach,\u201d in IEEE Transactions on Neural Networks, Special Issue on Neural Network and Pattern Recognition, accepted for publication."},{"key":"354298_CR14","doi-asserted-by":"crossref","unstructured":"W. Li, S. Gauch, J. Gauch, and K.M. Pua, \u201cVISION: A digital video library,\u201d ACM Multimedia Magazine, pp. 19\u201327, 1996.","DOI":"10.1145\/226931.226936"},{"key":"354298_CR15","unstructured":"R. Lienhart, \u201cMethods of content analysis, indexing and comparison of digital video sequences,\u201d Ph.D. thesis, Shaker Verlag, July 1998. (in German)."},{"key":"354298_CR16","doi-asserted-by":"crossref","unstructured":"R. Lienhart, W. Effelsberg, and R. Jain, \u201cTowards a visual grep: A systematic analysis of various methods to compare video sequences,\u201d in Proc. SPIE 3312, Storage and Retrieval for Image and Video Databases VI, I.K. Sethi and R.C. Jain (Eds.), 1998, pp. 271\u2013282.","DOI":"10.1117\/12.298460"},{"issue":"1\/2","key":"354298_CR17","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1023\/A:1008066223044","volume":"20","author":"Z. Liu","year":"1998","unstructured":"Z. Liu, Y. Wang, and T. Chen, \u201cAudio feature extraction and analysis for scene segmentation and classification,\u201d Journal of VLSI Signal Processing System, Systems for Signal, Image, and Video Technology, Vol. 20, No. 1\/2, pp. 61\u201379, 1998.","journal-title":"Journal of VLSI Signal Processing System, Systems for Signal, Image, and Video Technology"},{"key":"354298_CR18","doi-asserted-by":"crossref","unstructured":"C.Y. Low, Q. Tian, and H. Zhang, \u201cAn automatic news video parsing, indexing and browsing system,\u201d in Proc. ACM Multimedia 96, Boston, MA, Nov. 1996, pp. 425\u2013426.","DOI":"10.1145\/244130.244453"},{"key":"354298_CR19","doi-asserted-by":"crossref","unstructured":"K. Minami, A. Akutsu, H. Hamada, and Y. Tonomura, \u201cEnhanced video handling based on audio analysis,\u201d in Proc. IEEE International Conference on Multimedia and Systems, Ottawa, Canada. June 1997, pp. 219\u2013226.","DOI":"10.1109\/MMCS.1997.609596"},{"key":"354298_CR20","doi-asserted-by":"crossref","unstructured":"A. Merlino, D. Morey, and M. Maybury, \u201cBroadcast news navigation using story segmentation,\u201d in Proc. ACM Multimedia 97, Seattle, USA, Nov. 1997, pp. 381\u2013391.","DOI":"10.1145\/266180.266390"},{"key":"354298_CR21","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1109\/ICIP.1997.638830","volume":"2","author":"J. Nam","year":"1997","unstructured":"J. Nam, A. Cetin, and A. Tewfik, \u201cSpeaker identification and video analysis for hierarchical video shot classification,\u201d in Proc. IEEE International Conference on Image Processing 97, Vol. 2, 1997, pp. 550\u2013553.","journal-title":"Proc. IEEE International Conference on Image Processing 97"},{"key":"354298_CR22","doi-asserted-by":"crossref","unstructured":"G. Pass, R. Zabih, and J. Miller, \u201cComparing images using color coherence vectors,\u201d in Proc.ACMMultimedia 96, Boston, MA, USA, Nov. 1996, pp. 65\u201373.","DOI":"10.1145\/244130.244148"},{"key":"354298_CR23","doi-asserted-by":"crossref","unstructured":"A. Pentland, B. Moghaddam, and T. Starner, \u201cView-based and modular eigenspaces for face recognition,\u201d in IEEE Conf. on Computer Vision and Pattern Recognition, Seattle, WA, July, 1994.","DOI":"10.1109\/CVPR.1994.323814"},{"key":"354298_CR24","doi-asserted-by":"crossref","unstructured":"S. Pfeiffer, \u201cThe importance of perceptive adaptation of sound features for audio content processing,\u201d in Proc. SPIE Conferences, Electronic Imaging 1999, Storage and Retrieval for Image and Video Databases VII, Jan. 1999, San Jose, CA, pp. 328\u2013337.","DOI":"10.1117\/12.333852"},{"key":"354298_CR25","unstructured":"H. A. Rowley, S. Baluja, and T. Kanade, \u201cHuman face recognition in visual scenes,\u201d Technical Report Carnegie Mellon University, CMU-CS-95-158R, School of Computer Science, Nov. 1995."},{"key":"354298_CR26","doi-asserted-by":"crossref","unstructured":"C. Saraceno and R. Leonardi, \u201cAudio as a support to scene change detection and characterization of video sequences,\u201d in Proc. 22nd IEEE International Conference on Acoustics, Speech, and Signal Processing, Munich, Germany, May 1997, pp. 2597\u20132600.","DOI":"10.1109\/ICASSP.1997.595320"},{"key":"354298_CR27","doi-asserted-by":"crossref","unstructured":"Y. Taniguchi, A. Akutsu, and Y. Tonomura, \u201cPanoramaExcerpts: Extracting and packing panoramas for video browsing,\u201d in Proc. ACM Multimedia 97, Seattle, USA, Nov. 1997, pp. 427\u2013436.","DOI":"10.1145\/266180.266396"},{"key":"354298_CR28","doi-asserted-by":"crossref","unstructured":"M.M. Yeung, B.-L. Yeo, W. Wolf, and B. Lu, \u201cVideo browsing using clustering and scene transitions on compressed sequences,\u201d in Proc. SPIE 2417, 1995, pp. 399\u2013413.","DOI":"10.1117\/12.206067"},{"key":"354298_CR29","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1109\/ICPR.1996.546973","volume":"C","author":"M.M. Yeung","year":"1996","unstructured":"M.M. Yeung and B.-L. Yeo, \u201cTime-constrained clustering for segmentation of video into story units,\u201d in Proc. International Conference on Pattern Recognition, Vol. C, 1996, pp. 375\u2013380.","journal-title":"Proc. International Conference on Pattern Recognition"},{"key":"354298_CR30","doi-asserted-by":"crossref","unstructured":"M. Yeung and B.-L. Yeo, \u201cVideo content characterization and compaction for digital library applications,\u201d in SPIE 3022, Storage and Retrieval of Image and Video Databases 1997, Jan. 1997, pp. 45\u201358.","DOI":"10.1117\/12.263440"},{"key":"354298_CR31","doi-asserted-by":"crossref","unstructured":"R. Zabih, J. Miller, and K. Mai, \u201cA feature-based algorithm for detecting and classifying scene breaks,\u201d in Proc. ACM Multimedia 95, San Francisco, CA, Nov. 1995, pp. 189\u2013200.","DOI":"10.1145\/217279.215266"},{"issue":"6","key":"354298_CR32","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1007\/BF01225243","volume":"2","author":"H.J. Zhang","year":"1995","unstructured":"H.J. Zhang, S. Tau, S. Smoliar, and G. Yihong, \u201cAutomatic parsing and indexing of news video,\u201d Multimedia Systems, Vol. 2, No. 6, pp. 256\u2013266, 1995.","journal-title":"Multimedia Systems"},{"key":"354298_CR33","first-page":"2670","volume":"96","author":"D. Zhong","year":"1996","unstructured":"D. Zhong, H.J. Zhang, and S.-F. Chang, \u201cClustering Methods for Video Browsing and Annotation,\u201d in Sorage and Retrieval for Still Image andVideo Databases IV, IS&T\/SPIE's Electronic Imaging Science & Technology 96, 2670, San Jose, CA, Feb. 1996.","journal-title":"Sorage and Retrieval for Still Image andVideo Databases IV, IS&T\/SPIE's Electronic Imaging Science & Technology"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1011315803415.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1011315803415\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1011315803415.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T06:38:02Z","timestamp":1748241482000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1011315803415"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001,9]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2001,9]]}},"alternative-id":["354298"],"URL":"https:\/\/doi.org\/10.1023\/a:1011315803415","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2001,9]]}}}