{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T02:26:53Z","timestamp":1725503213451},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540781547"},{"type":"electronic","value":"9783540781554"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-78155-4_4","type":"book-chapter","created":{"date-parts":[[2008,2,21]],"date-time":"2008-02-21T12:46:47Z","timestamp":1203598007000},"page":"36-47","source":"Crossref","is-referenced-by-count":0,"title":["Object Category Recognition Using Probabilistic Fusion of Speech and Image Classifiers"],"prefix":"10.1007","author":[{"given":"Kate","family":"Saenko","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"4_CR1","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1145\/800250.807503","volume-title":"SIGGRAPH 1980. Proceedings of the 7th Annual Conference on Computer Graphics and interactive Techniques","author":"R. Bolt","year":"1980","unstructured":"Bolt, R.: \u201cPut-that-there\u201d: Voice and gesture at the graphics interface. In: SIGGRAPH 1980. Proceedings of the 7th Annual Conference on Computer Graphics and interactive Techniques, pp. 262\u2013270. ACM Press, New York (1980)"},{"key":"4_CR2","unstructured":"Chang, C., Lin, C.: LIBSVM: A library for support vector machines, Software (2001), http:\/\/www.csie.ntu.edu.tw\/~cjlin\/libsvm"},{"key":"4_CR3","unstructured":"Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: In: an incremental Bayesian approach tested on 101 object categories. IEEE. CVPR, Workshop on Generative-Model Based Vision (2004)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Fergus, R., Fei-Fei, L., Perona, P., Zisserman, A.: Learning Object Categories from Google\u2019s Image Search. In: Proc. of the 10th Inter. Conf. on Computer Vision, ICCV (2005)","DOI":"10.1109\/ICCV.2005.142"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Frome, A., Singer, Y., Malik, J.: Image Retrieval and Recognition Using Local Distance Functions. In: Proceedings of Neural Information Processing Systems (NIPS) (2006)","DOI":"10.7551\/mitpress\/7503.003.0057"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Grauman, K., Darrell, T.: The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), Beijing, China (October 2005), http:\/\/people.csail.mit.edu\/jjl\/libpmk\/","DOI":"10.1109\/ICCV.2005.239"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Grauman, K., Darrell, T.: Approximate Correspondences in High Dimensions. In: Proceedings of Advances in Neural Information Processing Systems (NIPS) (2006)","DOI":"10.7551\/mitpress\/7503.003.0068"},{"key":"4_CR8","unstructured":"Grauman, K., Darrell, T.: Pyramid Match Kernels: Discriminative Classification with Sets of Image Features. MIT Technical Report MIT-CSAIL-TR-2006-020, 2006. The Journal of Machine Learning (2006) (to appear)"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Haasch, A., Hofemann, N., Fritsch, J., Sagerer, G.: A multi-modal object attention system for a mobile robot, Intelligent Robots and Systems (2005)","DOI":"10.1109\/IROS.2005.1545191"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Kaiser, E., Olwal, A., McGee, D., Benko, H., Corradini, A., Li, X., Cohen, P., Feiner, S.: Mutual disambiguation of 3D multimodal interaction in augmented and virtual reality. In: Proceedings of the 5th International Conference on Multimodal Interfaces (ICMI) (2003)","DOI":"10.1145\/958432.958438"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Murphy, K., Torralba, A., Eaton, D., Freeman, W.T.: Object detection and localization using local and global features. In: Sicily workshop on object recognition, LNCS(unrefered) (2005)","DOI":"10.1007\/11957959_20"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Potamianos, G., Neti, C., Gravier, G., Garg, A., Senior, A.: Recent Advances in the Automatic Recognition of Audio-Visual Speech. In: Proc. IEEE (2003)","DOI":"10.1109\/JPROC.2003.817150"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Roy, D., Gorniak, P., Mukherjee, N., Juster, J.: A Trainable Spoken Language Understanding System for Visual Object Selection. In: Proceedings of the International Conference of Spoken Language Processing (2002)","DOI":"10.21437\/ICSLP.2002-200"},{"key":"4_CR14","unstructured":"Russell, B., Torralba, A., Murphy, K., Freeman, W.T.: LabelMe: a database and web-based tool for image annotation. MIT AI LAB MEMO AIM-2005-025 (2005)"},{"key":"4_CR15","unstructured":"Zhang, H., Berg, A., Maire, M., Malik, J.: SVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition. In: proceedings of CVPR (2006)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning for Multimodal Interaction"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-78155-4_4.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T14:55:00Z","timestamp":1708613700000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-78155-4_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540781547","9783540781554"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-78155-4_4","relation":{},"subject":[]}}