{"id":"https://openalex.org/W2154422044","doi":"https://doi.org/10.1109/cvpr.2003.1211479","title":"Object class recognition by unsupervised scale-invariant learning","display_name":"Object class recognition by unsupervised scale-invariant learning","publication_year":2003,"publication_date":"2003-11-21","ids":{"openalex":"https://openalex.org/W2154422044","doi":"https://doi.org/10.1109/cvpr.2003.1211479","mag":"2154422044"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2003.1211479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2003.1211479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089960673","display_name":"Rob Fergus","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"R. Fergus","raw_affiliation_strings":["Department of Engineering Science, University of Oxford, Oxford, UK"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Science, University of Oxford, Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026825380","display_name":"Pietro Perona","orcid":"https://orcid.org/0000-0002-7583-5809"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Perona","raw_affiliation_strings":["Department of Electrical Engineering, California Institute of Technology, Pasadena, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, California Institute of Technology, Pasadena, CA, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057678172","display_name":"Andrew Zisserman","orcid":"https://orcid.org/0000-0002-8945-8573"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"A. Zisserman","raw_affiliation_strings":["Department of Engineering Science, University of Oxford, Oxford, UK"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Science, University of Oxford, Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5089960673"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":113.8629,"has_fulltext":false,"cited_by_count":2045,"citation_normalized_percentile":{"value":0.99992824,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"2","issue":null,"first_page":"II","last_page":"264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7925795316696167},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.7681847810745239},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.6219890117645264},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.56163489818573},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.5408945083618164},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5227739214897156},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5128102898597717},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4831761419773102},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4674229323863983},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.46051111817359924},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4247046113014221},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41185569763183594},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4117637574672699},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.41166117787361145},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.35804831981658936},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34748196601867676},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1709393858909607},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08013466000556946}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7925795316696167},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7681847810745239},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.6219890117645264},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.56163489818573},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.5408945083618164},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5227739214897156},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5128102898597717},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4831761419773102},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4674229323863983},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.46051111817359924},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4247046113014221},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41185569763183594},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4117637574672699},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.41166117787361145},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.35804831981658936},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34748196601867676},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1709393858909607},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08013466000556946},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/cvpr.2003.1211479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2003.1211479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:authors.library.caltech.edu:27284","is_oa":false,"landing_page_url":"https://resolver.caltech.edu/CaltechAUTHORS:20111018-135127518","pdf_url":null,"source":{"id":"https://openalex.org/S4306402161","display_name":"CaltechAUTHORS (California Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122411786","host_organization_name":"California Institute of Technology","host_organization_lineage":["https://openalex.org/I122411786"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Book Section"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.114.7863","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.114.7863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.stat.ucla.edu/~yuille/courses/Stat238-Fall07/fergus03object.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.115.2508","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.115.2508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.fias.uni-frankfurt.de/~triesch/courses/260object/papers/FergusEtAl2003.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.115.7747","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.115.7747","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~misc-read/talks-2003/fergus-cvpr-2003.pdf","raw_type":"text"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:9e3e6d2f-3989-4d6c-bfed-e892ad3d3602","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1513966746","https://openalex.org/W1699734612","https://openalex.org/W1758770588","https://openalex.org/W1949116567","https://openalex.org/W1958762911","https://openalex.org/W2049633694","https://openalex.org/W2078602589","https://openalex.org/W2103497972","https://openalex.org/W2109200236","https://openalex.org/W2119747362","https://openalex.org/W2124722975","https://openalex.org/W2152942156","https://openalex.org/W2154791445","https://openalex.org/W2155511848","https://openalex.org/W2159686933","https://openalex.org/W2160225842","https://openalex.org/W2164598857","https://openalex.org/W2167828171","https://openalex.org/W2217896605","https://openalex.org/W4293052488","https://openalex.org/W6637860379","https://openalex.org/W6640791922","https://openalex.org/W6641096339","https://openalex.org/W6683732952","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W1563898036","https://openalex.org/W1978153144","https://openalex.org/W1573889165","https://openalex.org/W2147030611","https://openalex.org/W102848802","https://openalex.org/W2982058819","https://openalex.org/W2130734797","https://openalex.org/W2172249169","https://openalex.org/W3176361882","https://openalex.org/W3100038748"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,18,79,89,107],"method":[3],"to":[4,53,92],"learn":[5],"and":[6,13,44,56,118],"recognize":[7],"object":[8,69],"class":[9],"models":[10],"from":[11],"unlabeled":[12],"unsegmented":[14],"cluttered":[15],"scenes":[16],"in":[17,78,88],"scale":[19,58],"invariant":[20],"manner.":[21],"Objects":[22],"are":[23,71],"modeled":[24],"as":[25,122],"flexible":[26,96,119],"constellations":[27],"of":[28,38,66,98,109],"parts.":[29],"A":[30],"probabilistic":[31],"representation":[32],"is":[33,51,74,86,101],"used":[34,52,87],"for":[35],"all":[36],"aspects":[37],"the":[39,60,64,67,99],"object:":[40],"shape,":[41],"appearance,":[42],"occlusion":[43],"relative":[45],"scale.":[46],"An":[47],"entropy-based":[48],"feature":[49],"detector":[50],"select":[54],"regions":[55],"their":[57],"within":[59],"image.":[61],"In":[62,82],"learning":[63],"parameters":[65],"scale-invariant":[68],"model":[70,85,100],"estimated.":[72],"This":[73],"done":[75],"using":[76],"expectation-maximization":[77],"maximum-likelihood":[80],"setting.":[81],"recognition,":[83],"this":[84],"Bayesian":[90],"manner":[91],"classify":[93],"images.":[94],"The":[95],"nature":[97],"demonstrated":[102],"by":[103],"excellent":[104],"results":[105],"over":[106],"range":[108],"datasets":[110],"including":[111],"geometrically":[112],"constrained":[113],"classes":[114],"(e.g.":[115],"faces,":[116],"cars)":[117],"objects":[120],"(such":[121],"animals).":[123]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":33},{"year":2018,"cited_by_count":36},{"year":2017,"cited_by_count":51},{"year":2016,"cited_by_count":54},{"year":2015,"cited_by_count":98},{"year":2014,"cited_by_count":102},{"year":2013,"cited_by_count":126},{"year":2012,"cited_by_count":148}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}