{"id":"https://openalex.org/W2079238516","doi":"https://doi.org/10.1109/cvpr.2012.6247926","title":"Image categorization using Fisher kernels of non-iid image models","display_name":"Image categorization using Fisher kernels of non-iid image models","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2079238516","doi":"https://doi.org/10.1109/cvpr.2012.6247926","mag":"2079238516"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2012.6247926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2012.6247926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-00685943","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051499142","display_name":"Ramazan G\u00f6kberk Cinbi\u015f","orcid":"https://orcid.org/0000-0003-0962-7101"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210149092","display_name":"Laboratoire Jean Kuntzmann","ror":"https://ror.org/04ett5b41","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210149092","https://openalex.org/I899635006","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"R. G. Cinbis","raw_affiliation_strings":["LEAR, Laboratoire Jean Kuntzmann, INRIA Grenoble, France","LEAR, INRIA Grenoble, France#TAB#"],"affiliations":[{"raw_affiliation_string":"LEAR, Laboratoire Jean Kuntzmann, INRIA Grenoble, France","institution_ids":["https://openalex.org/I4210149092","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"LEAR, INRIA Grenoble, France#TAB#","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040312210","display_name":"Jakob Verbeek","orcid":"https://orcid.org/0000-0003-1419-1816"},"institutions":[{"id":"https://openalex.org/I4210149092","display_name":"Laboratoire Jean Kuntzmann","ror":"https://ror.org/04ett5b41","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210149092","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"J. Verbeek","raw_affiliation_strings":["LEAR, Laboratoire Jean Kuntzmann, INRIA Grenoble, France","LEAR, INRIA Grenoble, France#TAB#"],"affiliations":[{"raw_affiliation_string":"LEAR, Laboratoire Jean Kuntzmann, INRIA Grenoble, France","institution_ids":["https://openalex.org/I4210149092","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"LEAR, INRIA Grenoble, France#TAB#","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110279104","display_name":"C. Schmid","orcid":null},"institutions":[{"id":"https://openalex.org/I4210149092","display_name":"Laboratoire Jean Kuntzmann","ror":"https://ror.org/04ett5b41","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210149092","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"C. Schmid","raw_affiliation_strings":["LEAR, Laboratoire Jean Kuntzmann, INRIA Grenoble, France","LEAR, INRIA Grenoble, France#TAB#"],"affiliations":[{"raw_affiliation_string":"LEAR, Laboratoire Jean Kuntzmann, INRIA Grenoble, France","institution_ids":["https://openalex.org/I4210149092","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"LEAR, INRIA Grenoble, France#TAB#","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051499142"],"corresponding_institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210149092"],"apc_list":null,"apc_paid":null,"fwci":8.6329,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.98211827,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2184","last_page":"2191"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9994000196456909,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fisher-kernel","display_name":"Fisher kernel","score":0.6474983096122742},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5801081657409668},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5534492135047913},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.552479088306427},{"id":"https://openalex.org/keywords/independent-and-identically-distributed-random-variables","display_name":"Independent and identically distributed random variables","score":0.5265538692474365},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5205529928207397},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.47926923632621765},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4593951404094696},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.44132286310195923},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.429074227809906},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4182332158088684},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34571897983551025},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.21393460035324097},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1615557074546814},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.15395838022232056},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.09930276870727539},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.09834098815917969}],"concepts":[{"id":"https://openalex.org/C207798031","wikidata":"https://www.wikidata.org/wiki/Q8563425","display_name":"Fisher kernel","level":5,"score":0.6474983096122742},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5801081657409668},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5534492135047913},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.552479088306427},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.5265538692474365},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5205529928207397},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.47926923632621765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4593951404094696},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.44132286310195923},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.429074227809906},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4182332158088684},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34571897983551025},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.21393460035324097},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1615557074546814},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.15395838022232056},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.09930276870727539},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.09834098815917969},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C181367576","wikidata":"https://www.wikidata.org/wiki/Q6394184","display_name":"Kernel Fisher discriminant analysis","level":4,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cvpr.2012.6247926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2012.6247926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00685943v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00685943","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CVPR 2012 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2012, Providence, United States. pp.2184-2191, ⟨10.1109/CVPR.2012.6247926⟩","raw_type":"Conference papers"},{"id":"pmh:oai:open.metu.edu.tr:11511/56688","is_oa":false,"landing_page_url":"https://hdl.handle.net/11511/56688","pdf_url":null,"source":{"id":"https://openalex.org/S4306402495","display_name":"OpenMETU (Middle East Technical University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I201799495","host_organization_name":"Middle East Technical University","host_organization_lineage":["https://openalex.org/I201799495"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00685943v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00685943","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CVPR 2012 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2012, Providence, United States. pp.2184-2191, ⟨10.1109/CVPR.2012.6247926⟩","raw_type":"Conference papers"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.75,"display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1516111018","https://openalex.org/W1606858007","https://openalex.org/W1625255723","https://openalex.org/W1880262756","https://openalex.org/W1976921161","https://openalex.org/W1984309565","https://openalex.org/W2020733616","https://openalex.org/W2038597090","https://openalex.org/W2058537326","https://openalex.org/W2068143350","https://openalex.org/W2097271781","https://openalex.org/W2107137555","https://openalex.org/W2112020727","https://openalex.org/W2126152463","https://openalex.org/W2131846894","https://openalex.org/W2134731454","https://openalex.org/W2135631383","https://openalex.org/W2141303268","https://openalex.org/W2147238549","https://openalex.org/W2154301842","https://openalex.org/W2162915993","https://openalex.org/W2166473218","https://openalex.org/W4212788824","https://openalex.org/W4237791300","https://openalex.org/W6636412649","https://openalex.org/W6636494156","https://openalex.org/W6684116732"],"related_works":["https://openalex.org/W2580650124","https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W2125598731","https://openalex.org/W2107028936","https://openalex.org/W2132005946","https://openalex.org/W1600099814","https://openalex.org/W2142835450","https://openalex.org/W2079825755","https://openalex.org/W2135267219"],"abstract_inverted_index":{"The":[0],"bag-of-words":[1],"(BoW)":[2],"model":[3,85,114],"treats":[4],"images":[5],"as":[6,51,151],"an":[7,69,98],"unordered":[8],"set":[9],"of":[10,48,74,100,131,154,161],"local":[11,60,120],"regions":[12,21,61],"and":[13,27,122],"represents":[14],"them":[15],"by":[16,44,71],"visual":[17,132],"word":[18],"histograms.":[19],"Implicitly,":[20],"are":[22,55],"assumed":[23],"to":[24,94,115,126],"be":[25],"identically":[26],"independently":[28],"distributed":[29],"(iid),":[30],"which":[31,54],"is":[32],"a":[33,37],"poor":[34],"assumption":[35],"from":[36],"modeling":[38],"perspective.":[39],"We":[40],"introduce":[41],"non-iid":[42],"models":[43,50,125,138],"treating":[45],"the":[46,64,72,75,84,112,128],"parameters":[47],"BoW":[49],"latent":[52,123],"variables":[53],"integrated":[56],"out,":[57],"rendering":[58],"all":[59],"dependent.":[62],"Using":[63,107],"Fisher":[65],"kernel":[66],"we":[67,110],"encode":[68],"image":[70],"gradient":[73],"data":[76],"log-likelihood":[77],"w.r.t.":[78],"hyper-parameters":[79],"that":[80],"control":[81],"priors":[82],"on":[83],"parameters.":[86],"Our":[87,137],"representation":[88],"naturally":[89],"involves":[90],"discounting":[91],"transformations":[92,103,149],"similar":[93],"taking":[95,152],"square-roots,":[96],"providing":[97],"explanation":[99],"why":[101],"such":[102,150],"have":[104],"proven":[105],"successful.":[106],"variational":[108],"inference":[109],"extend":[111],"basic":[113],"include":[116],"Gaussian":[117],"mixtures":[118],"over":[119],"descriptors,":[121],"topic":[124],"capture":[127],"co-occurrence":[129],"structure":[130],"words,":[133],"both":[134],"improving":[135],"performance.":[136],"yield":[139],"state-of-the-art":[140],"categorization":[141],"performance":[142],"using":[143,147,157],"linear":[144],"classifiers;":[145],"without":[146],"non-linear":[148,162],"square-roots":[153],"features,":[155],"or":[156],"(approximate)":[158],"explicit":[159],"embeddings":[160],"kernels.":[163]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}