{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/80778"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/80778","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Generative Models for Computer Vision","abstract":"In order to build robust computer vision algorithms, scene models are necessary that are capable of capturing various aspects of the data at the same time. These models should be fairly simple, but capable of adapting to the data. Flexible models, as defined in the machine learning community, are minimally structured probability models with a large number of parameters that can adapt so as to explain the input data. We describe one possible framework for designing and using flexible models for vision. The framework uses structured probability models to describe causes of variability in the data, exact or variational methods for inference, and an expectation-maximization algorithm for parameter estimation. We show that within this framework, we can perform various vision tasks jointly, such as tracking, recognition, occlusion detection, object stabilization, object removal, and filtering. In fact, in this dissertation we argue that dealing with these tasks jointly is easier than combining individually optimized modules in a typical engineering approach to signal processing.","abstract_html":"In order to build robust computer vision algorithms, scene models are necessary that are capable of capturing various aspects of the data at the same time. These models should be fairly simple, but capable of adapting to the data. Flexible models, as defined in the machine learning community, are minimally structured probability models with a large number of parameters that can adapt so as to explain the input data. We describe one possible framework for designing and using flexible models for vision. The framework uses structured probability models to describe causes of variability in the data, exact or variational methods for inference, and an expectation-maximization algorithm for parameter estimation. We show that within this framework, we can perform various vision tasks jointly, such as tracking, recognition, occlusion detection, object stabilization, object removal, and filtering. In fact, in this dissertation we argue that dealing with these tasks jointly is easier than combining individually optimized modules in a typical engineering approach to signal processing.","abstract_has_math":false,"creators":["Jojic, Nebojsa"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical Engineering","degree_department":null,"school":null,"contributors":["Huang, Thomas S.","Brendan J. Frey"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2015,"date_issued":"2015-09-25T20:08:07Z","date_published":"2015-09-25T20:08:07Z","updated_at":"2026-07-22T22:26:14Z","subjects":["Engineering, Electronics and Electrical"],"languages":["eng"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["(MiAaPQ)AAI3070010"],"render_values":[{"text":"(MiAaPQ)AAI3070010","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/2142/80778","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Huang, Thomas S.","Brendan J. Frey"]},{"key":"dc:creator","label":"Author","values":["Jojic, Nebojsa"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2015-09-25T20:08:07Z","10000-01-01","2002"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Engineering, Electronics and Electrical"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/80778","(MiAaPQ)AAI3070010"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["In order to build robust computer vision algorithms, scene models are necessary that are capable of capturing various aspects of the data at the same time. These models should be fairly simple, but capable of adapting to the data. Flexible models, as defined in the machine learning community, are minimally structured probability models with a large number of parameters that can adapt so as to explain the input data. We describe one possible framework for designing and using flexible models for vision. The framework uses structured probability models to describe causes of variability in the data, exact or variational methods for inference, and an expectation-maximization algorithm for parameter estimation. We show that within this framework, we can perform various vision tasks jointly, such as tracking, recognition, occlusion detection, object stabilization, object removal, and filtering. In fact, in this dissertation we argue that dealing with these tasks jointly is easier than combining individually optimized modules in a typical engineering approach to signal processing.","Made available in DSpace on 2015-09-25T20:08:07Z (GMT). No. of bitstreams: 2 license.txt: 4848 bytes, checksum: 96035ab3f5e1c23cc7138a224ce498bd (MD5) 3070010.pdf: 6352741 bytes, checksum: 73ec0aba85d4d10149490cbcef6517e5 (MD5) Previous issue date: 2002","Embargo set by: Seth Robbins for item 82060 Lift date: Forever Reason: Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","U of I Only","128 p.","Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2002."]},{"key":"dc:title","label":"Title","values":["Generative Models for Computer Vision"]}]}],"canonical_facts":{"dc:contributor":["Huang, Thomas S.","Brendan J. Frey"],"dc:creator":["Jojic, Nebojsa"],"dc:date":["2015-09-25T20:08:07Z","10000-01-01","2002"],"dc:description":["In order to build robust computer vision algorithms, scene models are necessary that are capable of capturing various aspects of the data at the same time. These models should be fairly simple, but capable of adapting to the data. Flexible models, as defined in the machine learning community, are minimally structured probability models with a large number of parameters that can adapt so as to explain the input data. We describe one possible framework for designing and using flexible models for vision. The framework uses structured probability models to describe causes of variability in the data, exact or variational methods for inference, and an expectation-maximization algorithm for parameter estimation. We show that within this framework, we can perform various vision tasks jointly, such as tracking, recognition, occlusion detection, object stabilization, object removal, and filtering. In fact, in this dissertation we argue that dealing with these tasks jointly is easier than combining individually optimized modules in a typical engineering approach to signal processing.","Made available in DSpace on 2015-09-25T20:08:07Z (GMT). No. of bitstreams: 2 license.txt: 4848 bytes, checksum: 96035ab3f5e1c23cc7138a224ce498bd (MD5) 3070010.pdf: 6352741 bytes, checksum: 73ec0aba85d4d10149490cbcef6517e5 (MD5) Previous issue date: 2002","Embargo set by: Seth Robbins for item 82060 Lift date: Forever Reason: Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","U of I Only","128 p.","Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2002."],"dc:identifier":["http://hdl.handle.net/2142/80778","(MiAaPQ)AAI3070010"],"dc:language":["eng"],"dc:subject":["Engineering, Electronics and Electrical"],"dc:title":["Generative Models for Computer Vision"],"dc:type":["text"],"thesis:degree_discipline":["Electrical Engineering"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:26:14Z"}