{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T07:26:12Z","timestamp":1725866772185},"publisher-location":"Cham","reference-count":53,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319247243"},{"type":"electronic","value":"9783319247267"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-24726-7_15","type":"book-chapter","created":{"date-parts":[[2016,9,30]],"date-time":"2016-09-30T05:06:34Z","timestamp":1475211994000},"page":"321-344","source":"Crossref","is-referenced-by-count":0,"title":["On Shape Recognition and Language"],"prefix":"10.1007","author":[{"given":"Petros","family":"Maragos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vassilis","family":"Pitsikalis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Athanasios","family":"Katsamanis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Pavlakos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stavros","family":"Theodorakis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,10,1]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1007\/s10209-007-0104-x","volume":"6","author":"U. Agris","year":"2008","unstructured":"Agris, U., Zieren, J., Canzler, U., Bauer, B., Kraiss, K.F.: Recent developments in visual sign language recognition. Univ. Access Inf. Soc. 6, 323\u2013362 (2008)","journal-title":"Univ. Access Inf. Soc."},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Antonakos, E., Pitsikalis, V., Maragos, P.: Classification of extreme facial events in sign language videos. EURASIP J. Image Video Process. 2014, 14 (2014)","DOI":"10.1186\/1687-5281-2014-14"},{"key":"15_CR3","doi-asserted-by":"crossref","DOI":"10.1093\/acprof:osobl\/9780199896684.001.0001","volume-title":"How the Brain Got Language: The Mirror System Hypothesis","author":"M.A. Arbib","year":"2012","unstructured":"Arbib, M.A.: How the Brain Got Language: The Mirror System Hypothesis. Oxford University Press, New York (2012)"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Bayer, I., Silbermann, T.: A multi modal approach to gesture recognition from audio and video data. In: Proceedings of the ACM International Conference on Multimodal Interaction, Sydney, pp.\u00a0461\u2013466 (2013)","DOI":"10.1145\/2522848.2532592"},{"key":"15_CR5","volume-title":"Pattern Recognition and Machine Learning","author":"C.M. Bishop","year":"2006","unstructured":"Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)"},{"issue":"3","key":"15_CR6","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1145\/965105.807503","volume":"14","author":"R.A. Bolt","year":"1980","unstructured":"Bolt, R.A.: Put-that-there: voice and gesture at the graphics interface. ACM Comput. Graph. 14 (3), 262\u2013270 (1980)","journal-title":"ACM Comput. Graph."},{"key":"15_CR7","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.neuroimage.2012.11.031","volume":"67","author":"C. Bordier","year":"2013","unstructured":"Bordier, C., Puja, F., Macaluso, E.: Sensory processing during viewing of cinematographic material: computational modeling and functional neuroimaging. NeuroImage 67, 213\u2013226 (2013)","journal-title":"NeuroImage"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Bowden, R., Windridge, D., Kadir, T., Zisserman, A., Brady, M.: A linguistic feature vector for the visual interpretation of sign language. In: Proceedings of the European Conference on Computer Vision (ECCV), Prague (2004)","DOI":"10.1007\/978-3-540-24670-1_30"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Buehler, P., Everingham, M., Zisserman, A.: Learning sign language by watching TV (using weakly aligned subtitles). In: Proceedings of the IEEE International Conference on Computer Vision & Pattern Recognition (CVPR), Miami, pp.\u00a02961\u20132968 (2009)","DOI":"10.1109\/CVPR.2009.5206523"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Chow, Y.-L., Schwartz, R.: The N-best algorithm: an efficient procedure for finding top N sentence hypotheses. In: HLT\u201989 Proceedings of the Workshop on Speech and Natural Language, Morristown, pp.\u00a0199\u2013202 (1989)","DOI":"10.3115\/1075434.1075467"},{"issue":"6","key":"15_CR11","doi-asserted-by":"crossref","first-page":"681","DOI":"10.1109\/34.927467","volume":"23","author":"T.F. Cootes","year":"2001","unstructured":"Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. IEEE Trans. Pattern Anal. Mach. Intell. 23 (6), 681\u2013685 (2001)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Cour, T., Sapp, B., Nagle, A., Taskar, B.: Talking pictures: temporal grouping and dialog-supervised person recognition. In: Proceedings of the IEEE International Conference on Computer Vision & Pattern Recognition (CVPR), San Francisco (2010)","DOI":"10.1109\/CVPR.2010.5540106"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of the IEEE International Conference on Computer Vision & Pattern Recognition (CVPR), San Diego, pp.\u00a0886\u2013893 (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"15_CR14","volume-title":"Pattern Classification","author":"R.O. Duda","year":"2001","unstructured":"Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. Wiley, New York (2001)","edition":"2"},{"key":"15_CR15","volume-title":"Language, Cognition, and the Brain: Insights from Sign Language Research","author":"K. Emmorey","year":"2002","unstructured":"Emmorey, K.: Language, Cognition, and the Brain: Insights from Sign Language Research. Lawrence Erlbaum Associates, Mahwah (2002)"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Escalera, S., Gonz\u00e0lez, J., Bar\u00f3, X., Reyes, M., Guyon, I., Athitsos, V., Escalante, H., Sigal, L., Argyros, A., Sminchisescu, C., Bowden, R., Sclaroff, S.: ChaLearn multi-modal gesture recognition 2013: grand challenge and workshop summary. In: Proceedings of the ACM International Conference on Multimodal Interaction, Sydney, pp.\u00a0365\u2013368 (2013)","DOI":"10.1145\/2522848.2532597"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Escalera, S., Gonz\u00e0lez, J., Bar\u00f3, X., Reyes, M., Lopes, O., Guyon, I., Athistos, V., Escalante, H.J.: Multi-modal gesture recognition challenge 2013: dataset and results. In: Proceedings of the ACM International Conference on Multimodal Interaction, pp.\u00a0445\u2013452 (2013)","DOI":"10.1145\/2522848.2532595"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.A.: Describing objects by their attributes. In: Proceedings of the IEEE International Conference on Computer Vision & Pattern Recognition (CVPR), Miami (2009)","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Fei-Fei, L., Perona, P.: A Bayesian hierarchical model for learning natural scene categories. In: Proceedings of the IEEE International Conference on Computer Vision & Pattern Recognition (CVPR), San Diego (2005)","DOI":"10.1109\/CVPR.2005.16"},{"key":"15_CR20","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4615-3626-0","volume-title":"Vector Quantization and Signal Compression","author":"A. Gersho","year":"1992","unstructured":"Gersho, A., Gray, R.M.: Vector Quantization and Signal Compression. Springer Science & Business Media, Boston (1992)"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Glotin, H., Vergyr, D., Neti, C., Potamianos, G., Luettin, J.: Weighting schemes for audio-visual fusion in speech recognition. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Salt Lake City, pp.\u00a0173\u2013176 (2001)","DOI":"10.1109\/ICASSP.2001.940795"},{"issue":"1","key":"15_CR22","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1016\/j.cviu.2006.10.019","volume":"108","author":"A. Jaimes","year":"2007","unstructured":"Jaimes, A., Sebe, N.: Multimodal human\u2013computer interaction: a survey. Comput. Vis. Image Underst. 108 (1), 116\u2013134 (2007)","journal-title":"Comput. Vis. Image Underst."},{"key":"15_CR23","volume-title":"Statistical Methods for Speech Recognition","author":"F. Jelinek","year":"1997","unstructured":"Jelinek, F.: Statistical Methods for Speech Recognition. MIT Press, Cambridge (1997)"},{"issue":"3","key":"15_CR24","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1353\/sls.2011.0002","volume":"11","author":"R.E. Johnson","year":"2011","unstructured":"Johnson, R.E., Liddell, S.K.: A segmental framework for representing signs phonetically. Sign Lang. Stud. 11 (3), 408\u2013463 (2011)","journal-title":"Sign Lang. Stud."},{"key":"15_CR25","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511807572","volume-title":"Gesture: Visible Action as Utterance","author":"A. Kendon","year":"2004","unstructured":"Kendon, A.: Gesture: Visible Action as Utterance. Cambridge University Press, Cambridge\/New York (2004)"},{"key":"15_CR26","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1075\/ais.6.05kop","volume-title":"Alignment in Communication: Towards a New Theory of Communication","author":"S. Kopp","year":"2013","unstructured":"Kopp, S., Bergmann, K.: Automatic and strategic alignment of co-verbal gestures in dialogue. In: Wachsmuth, I., de\u00a0Ruiter, J., Kopp, S., Jaecks, P. (eds.) Alignment in Communication: Towards a New Theory of Communication, pp.\u00a087\u2013107. John Benjamins Publ. Co., Amsterdam (2013)"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: Proceedings of the IEEE International Conference on Computer Vision & Pattern Recognition (CVPR), Anchorage (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"15_CR28","volume-title":"Grammar","author":"S.K. Liddell","year":"2003","unstructured":"Liddell, S.K.: Grammar, Gesture and Meaning in American Sign Language. Cambridge University Press, Cambridge (2003)"},{"key":"15_CR29","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-0-387-76316-3","volume-title":"Multimodal Processing and Interaction: Audio, Video, Text","author":"P. Maragos","year":"2008","unstructured":"Maragos, P., Gros, P., Katsamanis, A., Papandreou, G.: Cross-modal integration for performance improving in multimedia: a review. In: Maragos, P., Potamianos, A., Gros, P. (eds.) Multimodal Processing and Interaction: Audio, Video, Text, pp.\u00a03\u201348. Springer, New York (2008)"},{"key":"15_CR30","unstructured":"McNeill, D.: Gesture: a psycholinguistic approach. In: The Encyclopedia of Language and Linguistics, pp.\u00a01\u201315. Elsevier, Boston (2006)"},{"issue":"2","key":"15_CR31","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1075\/lia.5.2.01mcn","volume":"5","author":"D. McNeill","year":"2014","unstructured":"McNeill, D.: Gesture-speech unity: phylogenesis, ontogenesis microgenesis. Lang. Interact. Acquis. 5 (2), 137\u2013184 (2014)","journal-title":"Lang. Interact. Acquis."},{"key":"15_CR32","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1109\/TPAMI.2005.112","volume":"27","author":"S. Ong","year":"2005","unstructured":"Ong, S., Ranganath, S.: Automatic sign language analysis: a survey and the future beyond lexical meaning. IEEE Trans. Pattern Anal. Mach. Intell. 27, 873\u2013891 (2005)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Ostendorf, M., Kannan, A., Austin, S., Kimball, O., Schwartz, R., Rohlicek, J.R.: Integration of diverse recognition methodologies through reevaluation of N-best sentence hypotheses. In: HLT\u201991 Proceedings of the Workshop on Speech and Natural Language, pp.\u00a083\u201387 (1991)","DOI":"10.3115\/112405.112416"},{"issue":"3","key":"15_CR34","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1145\/330534.330538","volume":"43","author":"S. Oviatt","year":"2000","unstructured":"Oviatt, S., Cohen, P.: Perceptual user interfaces: multimodal interfaces that process what comes naturally. Commun. ACM 43 (3), 45\u201353 (2000)","journal-title":"Commun. ACM"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Parikh, D., Grauman, K.: Relative attributes. In: Proceedings of the International Conference on Computer Vision (ICCV), Barcelona (2011)","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"15_CR36","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1007\/s00530-008-0142-0","volume":"14","author":"K. Pastra","year":"2008","unstructured":"Pastra, K.: COSMOROE: a cross-media relations framework for modelling multimedia dialectics. Multimed. Syst. 14, 299\u2013323 (2008)","journal-title":"Multimed. Syst."},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Theodorakis, S., Pitsikalis, V., Katsamanis, A., Maragos, P.: Kinect-based multimodal gesture recognition using a two-pass fusion scheme. In: Proceeding of the IEEE International Conference on Image Processing (ICIP), Paris, pp.\u00a01495\u20131499 (2014)","DOI":"10.1109\/ICIP.2014.7025299"},{"key":"15_CR38","first-page":"255","volume":"16","author":"V. Pitsikalis","year":"2015","unstructured":"Pitsikalis, V., Katsamanis, A., Theodorakis, S., Maragos, P.: Multimodal gesture recognition via multiple hypotheses rescoring. J. Mach. Learn. Res. 16, 255\u2013284 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"15_CR39","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW.2011.5981681","volume-title":"Advances in phonetics-based sub-unit modeling for transcription alignment and sign language recognition","author":"V. Pitsikalis","year":"2011","unstructured":"Pitsikalis, V., Theodorakis, S., Vogler, C., Maragos, P.: Advances in phonetics-based sub-unit modeling for transcription alignment and sign language recognition. In: Proceedings of the IEEE Conference on Computer Vision & Pattern Recognition Workshops, Colorado Springs (2011)"},{"key":"15_CR40","volume-title":"Fundamentals of Speech Recognition","author":"L.R. Rabiner","year":"1993","unstructured":"Rabiner, L.R., Juang, B.H.: Fundamentals of Speech Recognition. Prentice Hall, Englewood Cliffs (1993)"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Rose, R.C., Paul, D.B.: A hidden Markov model based keyword recognition system. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Albuquerque, pp.\u00a0129\u2013132 (1990)","DOI":"10.1109\/ICASSP.1990.115555"},{"key":"15_CR42","volume-title":"Mind, Language, and Society: Philosophy in the Real World","author":"J.R. Searle","year":"1999","unstructured":"Searle, J.R.: Mind, Language, and Society: Philosophy in the Real World. Basic Books, New York (1999)"},{"key":"15_CR43","doi-asserted-by":"crossref","unstructured":"Sivic, J., Russell, B.C., Efros, A.A., Zisserman, A., Freeman, W.T.: Discovering objects and their location in images. In: Proceedings of the International Conference on Computer Vision (ICCV), Beijing, (2005)","DOI":"10.1109\/ICCV.2005.77"},{"issue":"12","key":"15_CR44","doi-asserted-by":"crossref","first-page":"1371","DOI":"10.1109\/34.735811","volume":"20","author":"T. Starner","year":"1998","unstructured":"Starner, T., Weaver, J., Pentland, A.: Real-time American sign language recognition using desk and wearable computer based video. IEEE Trans. Pattern Anal. Mach. Intell. 20 (12), 1371\u20131375 (1998)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR45","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1016\/j.imavis.2014.04.012","volume":"32","author":"S. Theodorakis","year":"2014","unstructured":"Theodorakis, S., Pitsikalis, V., Maragos, P.: Dynamic\u2013static unsupervised sequentiality, statistical subunits and lexicon for sign language recognition. Image Vis. Comput. 32, 533\u2013549 (2014)","journal-title":"Image Vis. Comput."},{"key":"15_CR46","unstructured":"Theodoridis, S., Koutroumbas, K.: Pattern Recognition, 4th edn. Academic Press (2008)"},{"key":"15_CR47","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/7551.001.0001","volume-title":"Origins of Human Communication","author":"M. Tomasello","year":"2008","unstructured":"Tomasello, M.: Origins of Human Communication. MIT Press, Cambridge (2008)"},{"key":"15_CR48","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1016\/j.brainres.2006.05.078","volume":"1111","author":"A. Vatakis","year":"2006","unstructured":"Vatakis, A., Spence, C.: Audiovisual synchrony perception for music, speech, and object actions. Brain Res. 1111, 134\u2013142 (2006)","journal-title":"Brain Res."},{"issue":"3","key":"15_CR49","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1006\/cviu.2000.0895","volume":"81","author":"C. Vogler","year":"2001","unstructured":"Vogler, C., Metaxas, D.: A framework for recognizing the simultaneous aspects of American sign language. Comput. Vis. Image Underst. 81 (3), 358\u2013384 (2001)","journal-title":"Comput. Vis. Image Underst."},{"issue":"11","key":"15_CR50","doi-asserted-by":"crossref","first-page":"1870","DOI":"10.1109\/29.103088","volume":"38","author":"J. Wilpon","year":"1990","unstructured":"Wilpon, J., Rabiner, L.R., Lee, C.H., Goldman, E.R.: Automatic recognition of keywords in unconstrained speech using hidden Markov models. IEEE Trans. Acoust. Speech Signal Process. 38 (11), 1870\u20131878 (1990)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"15_CR51","unstructured":"Wittgenstein, L.: Philosophical Investigations. (Translated by Anscombe, G.E.M., and Editors Hacker, P.M.S., Schulte, J., 4th edn.). Wiley-Blackwell Publ. (2009) (1953)"},{"key":"15_CR52","doi-asserted-by":"crossref","unstructured":"Wittgenstein, L.: The Big Typescript: TS 213 (Edited and translated by Luckhardt, C.G., Aue, M.E.). Blackwell Publication (2005)","DOI":"10.1002\/9780470752906"},{"key":"15_CR53","doi-asserted-by":"crossref","unstructured":"Wu, J., Cheng, J., Zhao, C., Lu, H.: Fusing multi-modal features for gesture recognition. In: Proceedings of the ACM International Conference on Multimodal Interaction, Sydney, pp.\u00a0453\u2013460 (2013)","DOI":"10.1145\/2522848.2532589"}],"container-title":["Mathematics and Visualization","Perspectives in Shape Analysis"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-24726-7_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,14]],"date-time":"2019-09-14T00:35:24Z","timestamp":1568421324000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-24726-7_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319247243","9783319247267"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-24726-7_15","relation":{},"ISSN":["1612-3786","2197-666X"],"issn-type":[{"type":"print","value":"1612-3786"},{"type":"electronic","value":"2197-666X"}],"subject":[],"published":{"date-parts":[[2016]]}}}