{"id":"https://openalex.org/W3000576683","doi":"https://doi.org/10.1109/wacv45572.2020.9093373","title":"Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual Features","display_name":"Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual Features","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3000576683","doi":"https://doi.org/10.1109/wacv45572.2020.9093373","mag":"3000576683"},"language":"en","primary_location":{"id":"doi:10.1109/wacv45572.2020.9093373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.04732","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079250783","display_name":"Andr\u00e9s Mafla","orcid":"https://orcid.org/0000-0003-2575-6093"},"institutions":[{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":null,"type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Andres Mafla","raw_affiliation_strings":["Computer Vision Center, UAB, Spain","Computer Vision Center, UAB,Spain"],"affiliations":[{"raw_affiliation_string":"Computer Vision Center, UAB, Spain","institution_ids":["https://openalex.org/I4387153096"]},{"raw_affiliation_string":"Computer Vision Center, UAB,Spain","institution_ids":["https://openalex.org/I4387153096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047256071","display_name":"Sounak Dey","orcid":"https://orcid.org/0000-0001-6704-6810"},"institutions":[{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":null,"type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Sounak Dey","raw_affiliation_strings":["Computer Vision Center, UAB, Spain","Computer Vision Center, UAB,Spain"],"affiliations":[{"raw_affiliation_string":"Computer Vision Center, UAB, Spain","institution_ids":["https://openalex.org/I4387153096"]},{"raw_affiliation_string":"Computer Vision Center, UAB,Spain","institution_ids":["https://openalex.org/I4387153096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019081944","display_name":"Ali Furkan Biten","orcid":"https://orcid.org/0000-0003-2099-5554"},"institutions":[{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":null,"type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ali Furkan Biten","raw_affiliation_strings":["Computer Vision Center, UAB, Spain","Computer Vision Center, UAB,Spain"],"affiliations":[{"raw_affiliation_string":"Computer Vision Center, UAB, Spain","institution_ids":["https://openalex.org/I4387153096"]},{"raw_affiliation_string":"Computer Vision Center, UAB,Spain","institution_ids":["https://openalex.org/I4387153096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008562740","display_name":"Llu\u00eds G\u00f3mez","orcid":"https://orcid.org/0000-0003-1408-9803"},"institutions":[{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":null,"type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Lluis Gomez","raw_affiliation_strings":["Computer Vision Center, UAB, Spain","Computer Vision Center, UAB,Spain"],"affiliations":[{"raw_affiliation_string":"Computer Vision Center, UAB, Spain","institution_ids":["https://openalex.org/I4387153096"]},{"raw_affiliation_string":"Computer Vision Center, UAB,Spain","institution_ids":["https://openalex.org/I4387153096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029375723","display_name":"D\u00ecmosthenis Karatzas","orcid":"https://orcid.org/0000-0001-8762-4454"},"institutions":[{"id":"https://openalex.org/I123044942","display_name":"Universitat Aut\u00f2noma de Barcelona","ror":"https://ror.org/052g8jq94","country_code":"ES","type":"education","lineage":["https://openalex.org/I123044942"]},{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":null,"type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Dimosthenis Karatzas","raw_affiliation_strings":["Computer Vision Center, UAB, Spain","Autonomous University of Barcelona"],"affiliations":[{"raw_affiliation_string":"Computer Vision Center, UAB, Spain","institution_ids":["https://openalex.org/I4387153096"]},{"raw_affiliation_string":"Autonomous University of Barcelona","institution_ids":["https://openalex.org/I123044942"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5079250783"],"corresponding_institution_ids":["https://openalex.org/I4387153096"],"apc_list":null,"apc_paid":null,"fwci":0.3925,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.60100389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2939","last_page":"2948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7922676801681519},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.6129594445228577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.612361490726471},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5841879844665527},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5786160826683044},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5724954605102539},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.5694446563720703},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5654815435409546},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5443605184555054},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5218926072120667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4910740852355957},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4740975797176361},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33996906876564026}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922676801681519},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.6129594445228577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.612361490726471},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5841879844665527},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5786160826683044},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5724954605102539},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.5694446563720703},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5654815435409546},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5443605184555054},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5218926072120667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4910740852355957},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4740975797176361},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33996906876564026},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/wacv45572.2020.9093373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.04732","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.04732","pdf_url":"https://arxiv.org/pdf/2001.04732","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3000576683","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2001.04732","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2001.04732","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.04732","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.04732","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.04732","pdf_url":"https://arxiv.org/pdf/2001.04732","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3000576683.pdf","grobid_xml":"https://content.openalex.org/works/W3000576683.grobid-xml"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W654550266","https://openalex.org/W1846799578","https://openalex.org/W1922126009","https://openalex.org/W1928906481","https://openalex.org/W1944396096","https://openalex.org/W1966385142","https://openalex.org/W2046519698","https://openalex.org/W2053317383","https://openalex.org/W2089335071","https://openalex.org/W2091759811","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2127141656","https://openalex.org/W2144554289","https://openalex.org/W2147238549","https://openalex.org/W2153579005","https://openalex.org/W2164587673","https://openalex.org/W2169501191","https://openalex.org/W2187089797","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2253806798","https://openalex.org/W2302086703","https://openalex.org/W2343052201","https://openalex.org/W2493916176","https://openalex.org/W2515655118","https://openalex.org/W2563764042","https://openalex.org/W2565591417","https://openalex.org/W2605982830","https://openalex.org/W2727586675","https://openalex.org/W2747623286","https://openalex.org/W2773354261","https://openalex.org/W2784050770","https://openalex.org/W2808178187","https://openalex.org/W2888894220","https://openalex.org/W2891951760","https://openalex.org/W2919115771","https://openalex.org/W2947555604","https://openalex.org/W2949197413","https://openalex.org/W2962747232","https://openalex.org/W2962773189","https://openalex.org/W2962986948","https://openalex.org/W2963114696","https://openalex.org/W2963150162","https://openalex.org/W2963717374","https://openalex.org/W2964072591","https://openalex.org/W2964153283","https://openalex.org/W2979382951","https://openalex.org/W2994689640","https://openalex.org/W3101029400","https://openalex.org/W3106250896","https://openalex.org/W6606244218","https://openalex.org/W6638677478","https://openalex.org/W6640376812","https://openalex.org/W6682691769","https://openalex.org/W6684876274","https://openalex.org/W6691603626","https://openalex.org/W6726347659","https://openalex.org/W6728881024","https://openalex.org/W6729791593","https://openalex.org/W6748339197","https://openalex.org/W6766196973","https://openalex.org/W6767164110","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W3024152176","https://openalex.org/W3087664992","https://openalex.org/W3126044525","https://openalex.org/W2398118205","https://openalex.org/W2405589773","https://openalex.org/W1564115175","https://openalex.org/W2946481693","https://openalex.org/W1558393477","https://openalex.org/W3211256241","https://openalex.org/W1480369142","https://openalex.org/W1484195577","https://openalex.org/W3034556548","https://openalex.org/W2744926832","https://openalex.org/W2905544595","https://openalex.org/W2465870074","https://openalex.org/W974332475","https://openalex.org/W2000429972","https://openalex.org/W1970828142","https://openalex.org/W2343237272","https://openalex.org/W2182772297"],"abstract_inverted_index":{"Text":[0],"contained":[1],"in":[2],"an":[3],"image":[4,15,42,61,140],"carries":[5],"high-level":[6],"semantics":[7],"that":[8,28,108],"can":[9],"be":[10,30,148],"exploited":[11],"to":[12,32,71,95],"achieve":[13],"richer":[14],"understanding.":[16],"In":[17,50],"particular,":[18],"the":[19,55,73,78,84,89,110],"mere":[20],"presence":[21],"of":[22,36,57,83,88,91,99,112,144],"text":[23],"provides":[24,116],"strong":[25],"guiding":[26],"content":[27],"should":[29],"employed":[31],"tackle":[33],"a":[34,92,97,104,117],"diversity":[35],"computer":[37],"vision":[38],"tasks":[39],"such":[40],"as":[41,125],"retrieval,":[43],"fine-grained":[44,58,137],"classification,":[45],"and":[46,60,124,139],"visual":[47,69],"question":[48],"answering.":[49],"this":[51,122,145],"paper,":[52],"we":[53],"address":[54],"problem":[56],"classification":[59,138],"retrieval":[62],"by":[63],"leveraging":[64],"textual":[65,100],"information":[66],"along":[67,102],"with":[68,103],"cues":[70],"comprehend":[72],"existing":[74],"intrinsic":[75],"relation":[76],"between":[77],"two":[79,134],"modalities.":[80],"The":[81,142],"novelty":[82],"proposed":[85],"model":[86,146],"consists":[87],"usage":[90],"PHOC":[93],"descriptor":[94],"construct":[96],"bag":[98],"words":[101],"Fisher":[105],"Vector":[106],"Encoding":[107],"captures":[109],"morphology":[111],"text.":[113],"This":[114],"approach":[115],"stronger":[118],"multimodal":[119],"representation":[120],"for":[121],"task":[123],"our":[126],"experiments":[127],"demonstrate,":[128],"it":[129],"achieves":[130],"state-of-the-art":[131],"results":[132],"on":[133],"different":[135],"tasks,":[136],"retrieval.":[141],"code":[143],"will":[147],"publicly":[149],"available":[150],"at":[151],"<sup":[152],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[153],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[154],".":[155]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}