{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T21:40:02Z","timestamp":1748554802182,"version":"3.41.0"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319219622"},{"type":"electronic","value":"9783319219639"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-21963-9_50","type":"book-chapter","created":{"date-parts":[[2015,8,3]],"date-time":"2015-08-03T01:19:45Z","timestamp":1438564785000},"page":"547-554","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Speaker Diarization Utilizing Face Clustering Information"],"prefix":"10.1007","author":[{"given":"Ioannis","family":"Kapsouras","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anastasios","family":"Tefas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikos","family":"Nikolaidis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis","family":"Pitas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,8,4]]},"reference":[{"key":"50_CR1","doi-asserted-by":"crossref","unstructured":"Asthana, A., Zafeiriou, S., Cheng, S., Pantic, M.: Robust discriminative response map fitting with constrained local models. In: Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3444\u20133451 (2013)","DOI":"10.1109\/CVPR.2013.442"},{"key":"50_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/978-3-540-79547-6_4","volume-title":"Computer Vision Systems","author":"H Baltzakis","year":"2008","unstructured":"Baltzakis, H., Argyros, A., Lourakis, M., Trahanias, P.: Tracking of human hands and faces through probabilistic fusion of multiple visual cues. In: Gasteratos, A., Vincze, M., Tsotsos, J.K. (eds.) ICVS 2008. LNCS, vol. 5008, pp. 33\u201342. Springer, Heidelberg (2008)"},{"key":"50_CR3","unstructured":"Chen, S., Gopalakrishnan, P.: Speaker, environment and channel change detection and clustering via the bayesian information criterion. In: Proceedings of DARPA Broadcast News Transcription and Understanding Workshop (1998)"},{"issue":"3","key":"50_CR4","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1007\/s11042-012-1080-6","volume":"68","author":"E El Khoury","year":"2014","unstructured":"El Khoury, E., Snac, C., Joly, P.: Audiovisual diarization of people in video content. Multimedia Tools Appl. 68(3), 747\u2013775 (2014)","journal-title":"Multimedia Tools Appl."},{"issue":"1","key":"50_CR5","first-page":"80","volume":"55","author":"MM Elmansori","year":"2011","unstructured":"Elmansori, M.M., Omar, K.: An enhanced face detection method using skin color and back-propagation neural network. Eur. J. Sci. Res. 55(1), 80 (2011)","journal-title":"Eur. J. Sci. Res."},{"key":"50_CR6","doi-asserted-by":"crossref","unstructured":"Friedland, G., Hung, H., Yeo, C.: Multi-modal speaker diarization of real-world meetings using compressed-domain video features. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2009, pp. 4069\u20134072 (2009)","DOI":"10.1109\/ICASSP.2009.4960522"},{"key":"50_CR7","unstructured":"Ng, A.Y., Jordan, M.I., Weiss, Y.: On spectral clustering: Analysis and an algorithm. In: Proceedings of NIPS, pp. 849\u2013856. MIT Press (2001)"},{"issue":"1","key":"50_CR8","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1109\/TPAMI.2011.47","volume":"34","author":"A Noulas","year":"2012","unstructured":"Noulas, A., Englebienne, G., Krose, B.: Multimodal speaker diarization. IEEE Trans. Pattern Anal. Mach. Intell. 34(1), 79\u201393 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"#cr-split#-50_CR9.1","unstructured":"Ojala, T., Pietikainen, M., Harwood, D.: Performance evaluation of texture measures with classification based on kullback discrimination of distributions. In: Proceedings of the 12th IAPR International Conference on Pattern Recognition, 1994. Vol. 1 - Conference A: Computer Vision amp"},{"key":"#cr-split#-50_CR9.2","unstructured":"Image Processing, vol. 1, pp. 582-585 (1994)"},{"key":"50_CR10","doi-asserted-by":"crossref","unstructured":"Orfanidis, G., Tefas, A., Nikolaidis, N., Pitas, I.: Facial image clustering in stereo videos using local binary patterns and double spectral analysis. In: IEEE Symposium Series on Computational Intelligence (SSCI) (2014)","DOI":"10.1109\/CIDM.2014.7008670"},{"issue":"2","key":"50_CR11","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/BF02910057","volume":"1","author":"G Stamou","year":"2007","unstructured":"Stamou, G., Krinidis, M., Nikolaidis, N., Pitas, I.: A monocular system for person tracking: Implementation and testing. J. Multimodal User Interfaces 1(2), 31\u201347 (2007)","journal-title":"J. Multimodal User Interfaces"},{"key":"50_CR12","doi-asserted-by":"crossref","unstructured":"Uricar, M., Franc, V., Hlav, V.: Detector of facial landmarks learned by the structured output svm. In: Proceedings of VISAPP 2012, pp. 547\u2013556 (2012)","DOI":"10.5220\/0003863705470556"},{"issue":"5","key":"50_CR13","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1016\/j.image.2014.03.004","volume":"29","author":"O Zoidi","year":"2014","unstructured":"Zoidi, O., Nikolaidis, N., Tefas, A., Pitas, I.: Stereo object tracking with fusion of texture, color and disparity information. Signal Proc. Image Commun. 29(5), 573\u2013589 (2014)","journal-title":"Signal Proc. Image Commun."},{"key":"50_CR14","doi-asserted-by":"crossref","unstructured":"Zoidi, O., Nikolaidis, N., Pitas, I.: Appearance based object tracking in stereo sequences. In: Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2434\u20132438 (2013)","DOI":"10.1109\/ICASSP.2013.6638092"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-21963-9_50","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T21:09:21Z","timestamp":1748552961000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-21963-9_50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319219622","9783319219639"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-21963-9_50","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"4 August 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}