{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T00:54:47Z","timestamp":1726188887448},"publisher-location":"Berlin, Heidelberg","reference-count":30,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540654599"},{"type":"electronic","value":"9783540492566"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[1999]]},"DOI":"10.1007\/3-540-49256-9_15","type":"book-chapter","created":{"date-parts":[[2007,11,17]],"date-time":"2007-11-17T09:56:34Z","timestamp":1195293394000},"page":"231-254","source":"Crossref","is-referenced-by-count":11,"title":["Multilevel Integration of Vision and Speech Understanding Using Bayesian Networks"],"prefix":"10.1007","author":[{"given":"Sven","family":"Wachsmuth","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hans","family":"Brandt-Pook","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gudrun","family":"Socher","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Franz","family":"Kummert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerhard","family":"Sagerer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2002,9,24]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"G. Adorni, M. D. Manzo, and F. Giunchiglia. Natural language driven image generation. In COLING, pages 495\u2013500, 1984.","DOI":"10.3115\/980491.980597"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"L. E. Bernstein. For speech perception by humans or machines, three senses are better than one. In International Conference on Spoken Language Processing, pages 1477\u20131480, 1996.","DOI":"10.1109\/ICSLP.1996.607895"},{"issue":"3","key":"15_CR3","first-page":"1","volume":"13","author":"S. Dickenson","year":"1994","unstructured":"S. Dickenson and D. Metaxas. Integrating qualitative and quantitative shape recovery. International Journal of Computer Vision, 13(3):1\u201320, 1994.","journal-title":"International Journal of Computer Vision"},{"key":"15_CR4","unstructured":"T. Fuhr, G. Socher, C. Scheering, and G. Sagerer. A three-dimensional spatial model for the interpretation of image data. In P. Olivier and K.-P. Gapp, editors, Representation and Processing of Spatial Expressions, pages 103\u2013118. Lawrence Erlbaum Associates, 1997."},{"key":"15_CR5","unstructured":"G. Heidemann and H. Ritter. Objekterkennung mit Neuronalen Netzen. Technical Report 2, Situierte K\u00fcnstliche Kommunikatoren, SFB 360, Universit\u00e4t Bielefeld, 1996."},{"key":"15_CR6","first-page":"186","volume":"8","author":"H. Kollnig","year":"1993","unstructured":"H. Kollnig and H.-H. Nagel. Ermittlung von begrifflichen Beschreibungen von Geschehen in Stra\u00dfenverkehrsszenen mit Hilfe unscharfer Mengen. In Informatik Froschung und Entwicklung, 8, pages 186\u2013196, 1993.","journal-title":"Informatik Froschung und Entwicklung"},{"key":"15_CR7","unstructured":"S. M. Kosslyn. Mental imagery. In D. A. O. et al, editor, Visual Cognition and Action, pages 73\u20137, Cambridge, Mass, 1990. MIT Press."},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"F. Kummert, G. A. Fink, and G. Sagerer. Schritthaltende hybride Objektdetektion. In Mustererkennung 97, 19, pages 137\u201344, Berlin, 1997. DAGM-Symposium Braunschweig, Springer-Verlag.","DOI":"10.1007\/978-3-642-60893-3_13"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"F. Lavagetto, S. Lepsoy, C. Braccini, and S. Curinga. Lip motion modeling and speech driven estimation. In Proc. Int. Conf. on Acoustics, Speech and Signal Processing, pages 183\u201386, 1997.","DOI":"10.1109\/ICASSP.1997.599593"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"K. Lee. Automatic Speech Recognition: The Development of the SPHINX System. Kluwer Academic Publishers, 1989.","DOI":"10.1007\/978-1-4615-3650-5"},{"key":"15_CR11","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1109\/ICIP.1997.638720","volume":"2","author":"A. Ma\u00dfmann","year":"1997","unstructured":"A. Ma\u00dfmann, S. Posch, and D. Schl\u00fcter. Using markov random fields for contour-based grouping. In Proceedings of International Conference on Image Processing, volume 2, pages 207\u201342, 1997.","journal-title":"Proceedings of International Conference on Image Processing"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"T. Maybury, editor. Intelligent Multimedia Interfaces. AAAI Press\/The MIT Press, 1993.","DOI":"10.1145\/259963.260410"},{"key":"15_CR13","unstructured":"D. McDonald and E. J. Conklin. Salience as a simplifying metaphor for natural language generation. In Proceedings of AAAI-81, pages 49\u201351, 1981."},{"key":"15_CR14","unstructured":"K. Nagao. Abduction and dynamic preference in plan-based dialogue understanding. In International Joint Conference on Artificial Intelligence, pages 1186\u2013192. Morgan Kaufmann Publishers, Inc., 1993."},{"key":"15_CR15","unstructured":"K. Nagao and J. Rekimoto. Ubiquitous talker: Spoken language interaction with real world objects. In International Joint Conference on Artificial Intelligence, pages 1284\u2013290, 1995."},{"key":"15_CR16","unstructured":"P. Olivier, T. Maeda, and J. ichi Tsujii. Automatic depiction of spatial descriptions. In Proceedings of AAAI-94, pages 1405\u20131410, Seattle, WA, 1994."},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"W. Richards, A. Jepson, and J. Feldman. Priors, preferences and categorial percepts. In W. Richards and D. Knill, editors, Perception as Bayesian Inference, pages 93\u2013122. Cambridge University Press, 1996.","DOI":"10.1017\/CBO9780511984037.005"},{"key":"15_CR18","unstructured":"G. Socher. Qualitative Scene Descriptions from Images for Integrated Speech and Image Understanding. Dissertationen zur K\u00fcnstlichen Intelligenz (DISKI 170). infix-Verlag, Sankt Augustin, 1997."},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"G. Socher, T. Merz, and S. Posch. 3-D Reconstruction and Camera Calibration from Images with Known Objects. In D. Pycock, editor, Proc. 6th British Machine Vision Conference, pages 167\u2013176, 1995.","DOI":"10.5244\/C.9.17"},{"key":"15_CR20","unstructured":"G. Socher, G. Sagerer, and P. Perona. Baysian Reasoning on Qualitative Descriptions from Images and Speech. In H. Buxton and A. Mukerjee, editors, ICCV\u201998 Workshop on Conceptual Description of Images, Bombay, India, 1998."},{"key":"15_CR21","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1007\/BF00849725","volume":"8","author":"R. K. Srihari","year":"1994","unstructured":"R. K. Srihari. Computational models for integrating linguistic and visual information: A survey. In Artificial Intelligence Review, 8, pages 349\u2013369, Netherlands, 1994. Kluwer Academic Publishers.","journal-title":"Artificial Intelligence Review"},{"key":"15_CR22","unstructured":"R. K. Srihari and D. T. Burhans. Visual semantics: Extracting visual information from text accompanying pictures. In Proceedings of AAAI-94, pages 793\u2013798, Seattle, WA, 1994."},{"key":"15_CR23","unstructured":"J. K. Tsotsos and etal. The PLAYBOT Project. In J. Aronis, editor, IJCAI\u2019Workshop on AI Applications for Disabled People, Montreal, 1995."},{"issue":"4","key":"15_CR24","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1016\/S0262-8856(97)00088-7","volume":"16","author":"J. K. Tsotsos","year":"1998","unstructured":"J. K. Tsotsos, G. Verghese, S. Dickenson, M. Jenkin, A. Jepson, E. Milios, F. Nuflo, S. Stevenson, M. Black, D. Metaxas, S. Culhane, Y. Yet, and R. Mann. Playbot: A visuallyguided robot for physically disabled children. Image and Vision Computing, 16(4):275\u2013292, 1998.","journal-title":"Image and Vision Computing"},{"key":"15_CR25","unstructured":"G. Verghese and J. K. Tsotsos. Real-time model-based tracking using perspective alignment. In Proceedings of Vision Interface\u2019 pages 202\u2013209, 1994."},{"key":"15_CR26","unstructured":"C. Vorwerg, G. Socher, T. Fuhr, G. Sagerer, and G. Rickheit. Projective relations for 3D space: computational model, application, and psychological evaluation. In Proceedings of the 14th National Joint Conference on Artificial Intelligence AAAI-97, Rhode Island, 1997."},{"key":"15_CR27","unstructured":"S. Wachsmuth, G. A. Fink, and G. Sagerer. Integration of parsing and incremental speech recognition. In Proceedings EUSIPCO-98, 1998."},{"key":"15_CR28","first-page":"479","volume":"8","author":"W. Wahlster","year":"1989","unstructured":"W. Wahlster. One word says more than a thousand pictures. on the automatic verbalization of the results of image sequence analysis systems. In Computers and Artificial Intelligence, 8, pages 479\u2013492, 1989.","journal-title":"Computers and Artificial Intelligence"},{"key":"15_CR29","unstructured":"D. L. Waltz. Generating and understanding scene descriptions. In B. Webber and I. Sag, editors, Elements of Discourse Understanding, pages 266\u2013282, New York, NY, 1981. Cambridge University Press."},{"key":"15_CR30","unstructured":"M. Zancanaro, O. Stock, and C. Strapparava. Dialogue cohension sharing and adjusting in an enhanced multimodal environment. In International Joint Conference on Artificial Intelligence, pages 1230\u20131236. Morgan Kaufmann Publishers, Inc., 1993."}],"container-title":["Lecture Notes in Computer Science","Computer Vision Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-49256-9_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,4]],"date-time":"2019-05-04T16:05:03Z","timestamp":1556985903000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-49256-9_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1999]]},"ISBN":["9783540654599","9783540492566"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/3-540-49256-9_15","relation":{},"ISSN":["0302-9743"],"issn-type":[{"type":"print","value":"0302-9743"}],"subject":[],"published":{"date-parts":[[1999]]}}}