{"id":"https://openalex.org/W2577311815","doi":"https://doi.org/10.1109/vcip.2016.7805494","title":"Image classification with CNN-based Fisher vector coding","display_name":"Image classification with CNN-based Fisher vector coding","publication_year":2016,"publication_date":"2016-11-01","ids":{"openalex":"https://openalex.org/W2577311815","doi":"https://doi.org/10.1109/vcip.2016.7805494","mag":"2577311815"},"language":"en","primary_location":{"id":"doi:10.1109/vcip.2016.7805494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip.2016.7805494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Visual Communications and Image Processing (VCIP)","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/A5100381758","display_name":"Yan Song","orcid":"https://orcid.org/0000-0002-5668-9068"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yan Song","raw_affiliation_strings":["Department of EEIS, University of of Sci. and Tech. of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Department of EEIS, University of of Sci. and Tech. of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049723287","display_name":"Xinhai Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhai Hong","raw_affiliation_strings":["Department of EEIS, University of of Sci. and Tech. of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Department of EEIS, University of of Sci. and Tech. of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["Department of EEIS, University of of Sci. and Tech. of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Department of EEIS, University of of Sci. and Tech. of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I20581793","display_name":"University of Kent","ror":"https://ror.org/00xkeyj56","country_code":"GB","type":"education","lineage":["https://openalex.org/I20581793"]},{"id":"https://openalex.org/I167056439","display_name":"Medway School of Pharmacy","ror":"https://ror.org/00fa9v295","country_code":"GB","type":"education","lineage":["https://openalex.org/I167056439"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lirong Dai","raw_affiliation_strings":["School of computing, University of Kent, Medway, UK"],"affiliations":[{"raw_affiliation_string":"School of computing, University of Kent, Medway, UK","institution_ids":["https://openalex.org/I167056439","https://openalex.org/I20581793"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100381758"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.501,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.74343397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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":0.9998000264167786,"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":0.9998000264167786,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9987000226974487,"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":0.9969000220298767,"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/fisher-kernel","display_name":"Fisher kernel","score":0.7507537603378296},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.723698616027832},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.7205482125282288},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7125807404518127},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6776098608970642},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6613173484802246},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.48753592371940613},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4596301019191742},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.44781234860420227},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4271913468837738},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.41920045018196106},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.41392314434051514},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.41354700922966003},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.31186509132385254},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19171664118766785},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.1268807351589203},{"id":"https://openalex.org/keywords/kernel-fisher-discriminant-analysis","display_name":"Kernel Fisher discriminant analysis","score":0.11299729347229004},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09326794743537903}],"concepts":[{"id":"https://openalex.org/C207798031","wikidata":"https://www.wikidata.org/wiki/Q8563425","display_name":"Fisher kernel","level":5,"score":0.7507537603378296},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.723698616027832},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7205482125282288},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7125807404518127},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6776098608970642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6613173484802246},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.48753592371940613},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4596301019191742},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.44781234860420227},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4271913468837738},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.41920045018196106},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.41392314434051514},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.41354700922966003},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.31186509132385254},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19171664118766785},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.1268807351589203},{"id":"https://openalex.org/C181367576","wikidata":"https://www.wikidata.org/wiki/Q6394184","display_name":"Kernel Fisher discriminant analysis","level":4,"score":0.11299729347229004},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09326794743537903},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/vcip.2016.7805494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip.2016.7805494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:kar.kent.ac.uk:57115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/VCIP.2016.7805494>)","pdf_url":null,"source":{"id":"https://openalex.org/S4377196264","display_name":"Kent Academic Repository (University of Kent)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20581793","host_organization_name":"University of Kent","host_organization_lineage":["https://openalex.org/I20581793"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1524680991","https://openalex.org/W1551774182","https://openalex.org/W1601795611","https://openalex.org/W1665214252","https://openalex.org/W1686810756","https://openalex.org/W1903029394","https://openalex.org/W1924160326","https://openalex.org/W1963882359","https://openalex.org/W1966385142","https://openalex.org/W2012592962","https://openalex.org/W2017814585","https://openalex.org/W2062118960","https://openalex.org/W2066941820","https://openalex.org/W2108598243","https://openalex.org/W2115628259","https://openalex.org/W2129326773","https://openalex.org/W2149933564","https://openalex.org/W2151103935","https://openalex.org/W2152161678","https://openalex.org/W2153635508","https://openalex.org/W2155541015","https://openalex.org/W2161969291","https://openalex.org/W2163605009","https://openalex.org/W2166473218","https://openalex.org/W2962835968","https://openalex.org/W4294375521","https://openalex.org/W4299518610","https://openalex.org/W6631498818","https://openalex.org/W6633090903","https://openalex.org/W6637242042","https://openalex.org/W6676297131","https://openalex.org/W6677322961","https://openalex.org/W6679431263","https://openalex.org/W6682132143","https://openalex.org/W6682778277","https://openalex.org/W6684116732","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W1597090307","https://openalex.org/W2744946191","https://openalex.org/W1992295166","https://openalex.org/W2143508933","https://openalex.org/W4287823873","https://openalex.org/W3089463411","https://openalex.org/W3013788394","https://openalex.org/W2163006912","https://openalex.org/W2096858107","https://openalex.org/W2129389418"],"abstract_inverted_index":{"Fisher":[0,22,116,143],"vector":[1,23,117,144],"coding":[2,24,118,145],"methods":[3,25,43],"have":[4,26,169],"been":[5,170],"demonstrated":[6],"to":[7,52,64,91,134,157,162,181,213,221,225],"be":[8,92],"effective":[9],"for":[10,142],"image":[11],"classification.":[12],"With":[13],"the":[14,32,54,66,85,107,125,136,150,154,164,183,186,198,209],"help":[15],"of":[16,34,57,69,77,87,124,185,191],"convolutional":[17,160],"neural":[18],"networks":[19],"(CNN),":[20],"several":[21],"shown":[27],"state-of-the-art":[28,206],"performance":[29,224],"by":[30,80],"adopting":[31],"activations":[33,123],"a":[35,46,74,103,113,158,217],"single":[36],"fully-connected":[37,127],"layer":[38],"as":[39,106],"region":[40,58,165],"features.":[41,59,166],"These":[42],"generally":[44],"exploit":[45],"diagonal":[47],"Gaussian":[48],"mixture":[49],"model":[50,65],"(GMM)":[51],"describe":[53],"generative":[55],"process":[56],"However,":[60],"it":[61],"is":[62,211],"difficult":[63],"complex":[67],"distribution":[68],"high-dimensional":[70],"feature":[71],"space":[72],"with":[73],"limited":[75],"number":[76,86],"Gaussians":[78,88],"obtained":[79],"unsupervised":[81],"learning.":[82],"Simply":[83],"increasing":[84],"turns":[89],"out":[90],"inefficient":[93],"and":[94,111,128,139,179,193,200,227],"computationally":[95],"impractical.":[96],"To":[97,147],"address":[98],"this":[99],"issue,":[100],"we":[101,152],"re-interpret":[102],"pre-trained":[104,155],"CNN":[105,114,156],"probabilistic":[108],"discriminative":[109],"model,":[110],"present":[112],"based":[115],"method,":[119],"termed":[120],"CNN-FVC.":[121],"Specifically,":[122],"intermediate":[126],"output":[129],"soft-max":[130],"layers":[131],"are":[132,195],"exploited":[133],"derive":[135],"posteriors,":[137],"mean":[138],"covariance":[140],"parameters":[141],"implicitly.":[146],"further":[148,222],"improve":[149,223],"efficiency,":[151],"convert":[153],"fully":[159],"one":[161],"extract":[163],"Extensive":[167],"experiments":[168],"conducted":[171],"on":[172,197],"two":[173],"standard":[174],"scene":[175],"benchmarks":[176,202],"(i.e.":[177],"SUN397":[178,199],"MIT67)":[180],"evaluate":[182],"effectiveness":[184],"proposed":[187],"method.":[188],"Classification":[189],"accuracies":[190],"60.7%":[192],"82.1%":[194],"achieved":[196],"MIT67":[201],"respectively,":[203],"outperforming":[204],"previous":[205],"approaches.":[207],"Furthermore,":[208],"method":[210],"complementary":[212],"GMM-FVC":[214],"methods,":[215],"allowing":[216],"simple":[218],"fusion":[219],"scheme":[220],"61.1%":[226],"83.1%":[228],"respectively.":[229]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}