{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T16:20:22Z","timestamp":1743265222469,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":41,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540009214"},{"type":"electronic","value":"9783540365921"}],"license":[{"start":{"date-parts":[[2003,1,1]],"date-time":"2003-01-01T00:00:00Z","timestamp":1041379200000},"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":[[2003]]},"DOI":"10.1007\/3-540-36592-3_6","type":"book-chapter","created":{"date-parts":[[2007,7,3]],"date-time":"2007-07-03T15:37:29Z","timestamp":1183477049000},"page":"54-67","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["A Self-Referential Perceptual Inference Framework for Video Interpretation"],"prefix":"10.1007","author":[{"given":"Christopher","family":"Town","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Sinclair","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2003,3,14]]},"reference":[{"issue":"8","key":"6_CR1","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1109\/2.940013","volume":"34","author":"M. Addlesee","year":"2001","unstructured":"M. Addlesee, R. Curwen, S. Hodges, J. Newman, P. Steggles, A. Ward, and A. Hopper. Implementing a sentient computing system. IEEE Computer, 34(8):50\u201356, 2001.","journal-title":"IEEE Computer"},{"key":"6_CR2","unstructured":"K. Barnard and D. Forsyth. Learning the semantics of words and pictures. In Proc. International Conference on Computer Vision, 2001."},{"key":"6_CR3","unstructured":"A. Bobick and Y. Ivanov. Action recognition using probabilistic parsing. In Proc. Conference on Computer Vision and Pattern Recognition, 1998."},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"H. Bunke and D. Pasche. Structural Pattern Analysis, chapter Parsing multivalued strings and its application to image and waveform recognition. World Scientific Publishing, 1990.","DOI":"10.1142\/9789814368292_0001"},{"key":"6_CR5","unstructured":"H. Buxton and S. Gong. Advanced visual surveillance using bayesian networks. In Proc. International Conference on Computer Vision, 1995."},{"issue":"4","key":"6_CR6","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0262-8856(88)90015-7","volume":"6","author":"H. Buxton","year":"1988","unstructured":"H. Buxton and N. Walker. Query based visual analysis: Spatio-temporal reasoning in computer vision. Vision Computing, 6(4):247\u2013254, 1988.","journal-title":"Vision Computing"},{"key":"6_CR7","unstructured":"Y. Chen, Y. Rui, and T. Huang. JPDAF based HMM for real-time contour tracking. In Proc. Conference on Computer Vision and Pattern Recognition, 2001."},{"issue":"3","key":"6_CR8","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1145\/330534.330540","volume":"43","author":"J. Crowley","year":"2000","unstructured":"J. Crowley, J. Coutaz, and F. Berard. Things that see: Machine perception for human computer interaction. Communications of the ACM, 43(3):54\u201364, 2000.","journal-title":"Communications of the ACM"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"J. Crowley, J. Coutaz, G. Rey, and P. Reignier. Perceptual components for context aware computing. In Proc. Ubicomp 2002, 2002.","DOI":"10.1007\/3-540-45809-3_9"},{"issue":"1\u20132","key":"6_CR10","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/0165-1684(93)90034-8","volume":"32","author":"J. Crowley","year":"1993","unstructured":"J. Crowley and Y. Demazeau. Principles and techniques for sensor data fusion. Signal Processing, 32(1\u20132):5\u201327, 1993.","journal-title":"Signal Processing"},{"key":"6_CR11","unstructured":"T. Darrell, G. Gordon, M. Harville, and J. Woodfill. Integrated person tracking using stereo, color, and pattern detection. In Proc. Conference on Computer Vision and Pattern Recognition, 1998."},{"key":"6_CR12","unstructured":"D. C. Dennett. Minds, machines, and evolution, chapter Cognitive Wheels: The Frame Problem of AI, pages 129\u2013151. Cambridge University Press, 1984."},{"key":"6_CR13","series-title":"Lect Notes Comput Sci","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1007\/3-540-48222-9_17","volume-title":"Adapting object recognition across domains: A demonstration","author":"B. Draper","year":"2001","unstructured":"B. Draper, U. Ahlrichs, and D. Paulus. Adapting object recognition across domains: A demonstration. Lecture Notes in Computer Science, 2095:256\u2013270, 2001."},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"P. Duygulu, K. Barnard, J.F.H. De Freitas, and D.A. Forsyth. Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary. In Proc. European Conference on Computer Vision, 2002.","DOI":"10.1007\/3-540-47979-1_7"},{"key":"6_CR15","unstructured":"J. Glicksman. A cooperative scheme for image understanding using multiple sources of information. Technical Report TR-82-13, University of British Columbia, Department of Computer Science, 1982."},{"key":"6_CR16","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1016\/0167-2789(90)90087-6","volume":"42","author":"S. Harnad","year":"1990","unstructured":"S. Harnad. The symbol grounding problem. Physica D, 42:335\u2013346, 1990.","journal-title":"Physica D"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"A. Harter, A. Hopper, P. Steggles, A. Ward, and P. Webster. The anatomy of a context-aware application. In Mobile Computing and Networking, pages 59\u201368, 1999.","DOI":"10.1145\/313451.313476"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"G. Herzog and K. Rohr. Integrating vision and language: Towards automatic description of human movements. In I. Wachsmuth, C.-R. Rollinger, and W. Brauer, editors, KI-95: Advances in Artificial Intelligence. 19th Annual German Conference on Artificial Intelligence, pages 257\u2013268. Springer, 1995.","DOI":"10.1007\/3-540-60343-3_42"},{"key":"6_CR19","unstructured":"S. Intille and A. Bobick. Representation and visual recognition of complex, multiagent actions using belief networks. In IEEE Workshop on the Interpretation of Visual Motion, 1998."},{"key":"6_CR20","series-title":"Lect Notes Comput Sci","first-page":"1406","volume-title":"ICONDENSATION: Unifying low-level and high-level tracking in a stochastic framework","author":"M. Isard","year":"1998","unstructured":"M. Isard and A. Blake. ICONDENSATION: Unifying low-level and high-level tracking in a stochastic framework. Lecture Notes in Computer Science, 1406, 1998."},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Y. Ivanov and A. Bobick. Recognition of visual activities and interactions by stochastic parsing. IEEE Trans. on Pattern Analysis and Machine Intell., 22(8), 2000.","DOI":"10.1109\/34.868686"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"A. Jaimes and S. Chang. A conceptual framework for indexing visual information at multiple levels. In IS&T SPIE Internet Imaging, 2000.","DOI":"10.1117\/12.373443"},{"key":"6_CR23","unstructured":"F.V. Jensen. An Introduction to Bayesian Networks. Springer Verlag, 1996."},{"key":"6_CR24","unstructured":"A. Kojima, T. Tamura, and K. Fukunaga. Natural language description of human activities from video images based on concept hierarchy of actions. Int. Journal of Computer Vision (to appear), 2002."},{"key":"6_CR25","unstructured":"D. Moore and I. Essa. Recognizing multitasked activities using stochastic context-free grammar. In Proc. Workshop on Models vs Exemplars in Computer Vision, 2001."},{"issue":"8","key":"6_CR26","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1109\/34.868684","volume":"22","author":"N. Oliver","year":"2000","unstructured":"N. Oliver, B. Rosario, and A. Pentland. A bayesian computer vision system for modeling human interactions. IEEE Trans. on Pattern Analysis and Machine Intell., 22(8):831\u2013843, 2000.","journal-title":"IEEE Trans. on Pattern Analysis and Machine Intell."},{"key":"6_CR27","unstructured":"C. Pinhanez and A. Bobick. Approximate world models: Incorporating qualitative and linguistic information into vision systems. In AAAI\u201996, 1996."},{"key":"6_CR28","unstructured":"R. Rimey. Control of Selective Perception using Bayes Nets and Decision Theory. PhD thesis, University of Rochester Computer Science Department, 1993."},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"J. Sherrah and S. Gong. Tracking discontinuous motion using bayesian inference. In Proc. European Conference on Computer Vision, pages 150\u2013166, 2000.","DOI":"10.1007\/3-540-45053-X_10"},{"key":"6_CR30","unstructured":"J. Sherrah and S. Gong. Continuous global evidence-based bayesian modality fusion for simultaneous tracking of multiple objects. In Proc. International Conference on Computer Vision, 2001."},{"key":"6_CR31","unstructured":"P. Smith. Edge-based Motion Segmentation. PhD thesis, Cambridge University Engineering Department, 2001."},{"key":"6_CR32","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/S0004-3702(99)00075-2","volume":"114","author":"K. Sparck Jones","year":"1999","unstructured":"K. Sparck Jones. Information retrieval and artificial intelligence. Artificial Intelligence, 114: 257\u2013281, 1999.","journal-title":"Artificial Intelligence"},{"key":"6_CR33","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/3-540-48222-9_7","volume":"2095","author":"M. Spengler","year":"2001","unstructured":"M. Spengler and B. Schiele. Towards robust multi-cue integration for visual tracking. Lecture Notes in Computer Science, 2095:93\u2013106, 2001.","journal-title":"Lecture Notes in Computer Science"},{"key":"6_CR34","first-page":"349","volume":"8","author":"R. Srihari","year":"1995","unstructured":"R. Srihari. Computational models for integrating linguistic and visual information: A survey. Artificial Intelligence Review, special issue on Integrating Language and Vision, 8:349\u2013369, 1995.","journal-title":"Artificial Intelligence Review, special issue on Integrating Language and Vision"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"S. Stillman and I. Essa. Towards reliable multimodal sensing in aware environments. In Proc. Perceptual User Interfaces Workshop, ACM UIST 2001, 2001.","DOI":"10.1145\/971478.971499"},{"key":"6_CR36","unstructured":"M. Thonnat and N. Rota. Image understanding for visual surveillance applications. In Proc. of 3rd Int. Workshop on Cooperative Distributed Vision, 1999."},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"C.P. Town and D.A. Sinclair. Ontological query language for content based image retrieval. In Proc. IEEE Workshop on Content-based Access of Image and Video Libraries, pages 75\u201381, 2001.","DOI":"10.1109\/IVL.2001.990859"},{"key":"6_CR38","unstructured":"K. Toyama and E. Horvitz. Bayesian modality fusion: Probabilistic integration of multiple vision algorithms for head tracking. In Proc. Asian Conference on Computer Vision, 2000."},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"W. Tsai and K. Fu. Attributed grammars \u2014 a tool for combining syntactic and statistical approaches to pattern recognition. IEEE Transactions on Systems, Man and Cybernetics, SMC-10(12), 1980.","DOI":"10.1109\/TSMC.1980.4308414"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"J. Tsotsos, J. Mylopoulos, H. Covvey, and S. Zucker. A framework for visual motion understanding. IEEE Trans. on Pattern Analysis and Machine Intell., Special Issue on Computer Analysis of Time-Varying Imagery:563\u2013573, 1980.","DOI":"10.1109\/TPAMI.1980.6447704"},{"key":"6_CR41","unstructured":"Y. Wu and T. Huang. A co-inference approach to robust visual tracking. In Proc. International Conference on Computer Vision, 2001."}],"container-title":["Lecture Notes in Computer Science","Computer Vision Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-36592-3_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T04:00:59Z","timestamp":1737172859000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/3-540-36592-3_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003]]},"ISBN":["9783540009214","9783540365921"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/3-540-36592-3_6","relation":{},"ISSN":["0302-9743"],"issn-type":[{"type":"print","value":"0302-9743"}],"subject":[],"published":{"date-parts":[[2003]]},"assertion":[{"value":"14 March 2003","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}