{"id":"https://openalex.org/W2912423076","doi":"https://doi.org/10.1109/tmm.2019.2894964","title":"Attend and Imagine: Multi-Label Image Classification With Visual Attention and Recurrent Neural Networks","display_name":"Attend and Imagine: Multi-Label Image Classification With Visual Attention and Recurrent Neural Networks","publication_year":2019,"publication_date":"2019-01-24","ids":{"openalex":"https://openalex.org/W2912423076","doi":"https://doi.org/10.1109/tmm.2019.2894964","mag":"2912423076"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2019.2894964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2894964","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5101573269","display_name":"Fan Lyu","orcid":"https://orcid.org/0000-0002-0878-5485"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Lyu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-0878-5485","affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060958969","display_name":"Qi Wu","orcid":"https://orcid.org/0000-0003-3631-256X"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Qi Wu","raw_affiliation_strings":["Australian Centre for Visual Technologies, School of Computer Science, The University of Adelaide, Adelaide, SA, Australia","School of Software Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3631-256X","affiliations":[{"raw_affiliation_string":"Australian Centre for Visual Technologies, School of Computer Science, The University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I5681781"]},{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086390256","display_name":"Fuyuan Hu","orcid":"https://orcid.org/0000-0002-6818-2221"},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuyuan Hu","raw_affiliation_strings":["School of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6818-2221","affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou, China","institution_ids":["https://openalex.org/I308837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023130798","display_name":"Qingyao Wu","orcid":"https://orcid.org/0000-0002-6771-3932"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Qingyao Wu","raw_affiliation_strings":["Australian Centre for Visual Technologies, School of Computer Science, The University of Adelaide, Adelaide, SA, Australia","School of Software Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6771-3932","affiliations":[{"raw_affiliation_string":"Australian Centre for Visual Technologies, School of Computer Science, The University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I5681781"]},{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032352025","display_name":"Mingkui Tan","orcid":"https://orcid.org/0000-0001-8856-756X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingkui Tan","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8856-756X","affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.7771,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.973485,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"21","issue":"8","first_page":"1971","last_page":"1981"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9976999759674072,"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":0.9973999857902527,"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":0.8580197095870972},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.697959840297699},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.6768220663070679},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5881990790367126},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5852682590484619},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5264288187026978},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4976518452167511},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.4792459011077881},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45882654190063477},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42983412742614746},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4163625240325928},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3817024827003479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8580197095870972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.697959840297699},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.6768220663070679},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5881990790367126},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5852682590484619},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5264288187026978},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4976518452167511},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.4792459011077881},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45882654190063477},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42983412742614746},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4163625240325928},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3817024827003479},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2019.2894964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2894964","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1352119025","display_name":null,"funder_award_id":"61602185","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2758043104","display_name":null,"funder_award_id":"61876121","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5431340920","display_name":"\u8f66\u8f7d\u5168\u666f\u5e8f\u5217\u56fe\u50cf\u7684\u7279\u5f81\u5339\u914d\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61472267","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7230160030","display_name":null,"funder_award_id":"D2172480","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7367589139","display_name":null,"funder_award_id":"61877038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W1514027499","https://openalex.org/W1514535095","https://openalex.org/W1524416683","https://openalex.org/W1567302070","https://openalex.org/W1581407678","https://openalex.org/W1606858007","https://openalex.org/W1686810756","https://openalex.org/W1753402186","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1900086069","https://openalex.org/W1905051261","https://openalex.org/W1953606363","https://openalex.org/W1990702921","https://openalex.org/W1991367009","https://openalex.org/W1992851697","https://openalex.org/W1998839399","https://openalex.org/W1999954155","https://openalex.org/W2010181071","https://openalex.org/W2031489346","https://openalex.org/W2052684427","https://openalex.org/W2062118960","https://openalex.org/W2064675550","https://openalex.org/W2066624635","https://openalex.org/W2108598243","https://openalex.org/W2114315281","https://openalex.org/W2116750654","https://openalex.org/W2118712128","https://openalex.org/W2130942839","https://openalex.org/W2131101925","https://openalex.org/W2133564696","https://openalex.org/W2138290126","https://openalex.org/W2156935079","https://openalex.org/W2157331557","https://openalex.org/W2159243025","https://openalex.org/W2161381512","https://openalex.org/W2163605009","https://openalex.org/W2166912588","https://openalex.org/W2194775991","https://openalex.org/W2295744208","https://openalex.org/W2302086703","https://openalex.org/W2401353841","https://openalex.org/W2534457893","https://openalex.org/W2549365021","https://openalex.org/W2560096627","https://openalex.org/W2560920409","https://openalex.org/W2577763257","https://openalex.org/W2592165076","https://openalex.org/W2618530766","https://openalex.org/W2625940279","https://openalex.org/W2787911558","https://openalex.org/W2799787995","https://openalex.org/W2911189325","https://openalex.org/W2917837129","https://openalex.org/W2962835968","https://openalex.org/W2963020325","https://openalex.org/W2963094099","https://openalex.org/W2963346784","https://openalex.org/W2963705779","https://openalex.org/W2963745697","https://openalex.org/W2963786816","https://openalex.org/W2963875806","https://openalex.org/W2964049455","https://openalex.org/W2964308564","https://openalex.org/W2964350391","https://openalex.org/W4232706428","https://openalex.org/W6630792627","https://openalex.org/W6630875275","https://openalex.org/W6634906388","https://openalex.org/W6637373629","https://openalex.org/W6677758222","https://openalex.org/W6679384483","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6683512859","https://openalex.org/W6694260854","https://openalex.org/W6720932270","https://openalex.org/W6729046916","https://openalex.org/W6729487027","https://openalex.org/W6748708600","https://openalex.org/W6755034786","https://openalex.org/W6759955056","https://openalex.org/W6891831295"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2378211422","https://openalex.org/W2988126442","https://openalex.org/W2745001401","https://openalex.org/W4205999209","https://openalex.org/W2735080633","https://openalex.org/W4387801808"],"abstract_inverted_index":{"Real":[0],"images":[1],"often":[2],"have":[3,77],"multiple":[4,12,35,71],"labels,":[5],"i.e.,":[6],"each":[7,169],"image":[8,19,51,62,75,83],"is":[9,25,52],"associated":[10],"with":[11],"objects":[13,36],"or":[14],"attributes.":[15],"Compared":[16],"to":[17,30,81,94,109,125,129,149,171],"single-label":[18],"classification,":[20],"the":[21,41,44,55,96,101,111,127,137,151,173],"multilabel":[22,61],"classification":[23],"problem":[24],"much":[26],"more":[27],"challenging":[28],"due":[29,80],"several":[31,185],"issues.":[32],"At":[33],"first,":[34],"can":[37,63,76],"be":[38,64],"anywhere":[39],"in":[40,49,59,89,136,168],"image.":[42,138],"Second,":[43],"importance":[45],"of":[46,57,73,134,153,175],"different":[47,66],"regions":[48,56,133],"an":[50,74],"different,":[53],"and":[54,145],"interest":[58,135],"a":[60,116,121,159],"very":[65],"from":[67],"another":[68],"one.":[69],"Finally,":[70],"labels":[72,97,167],"label":[78,112],"dependencies":[79],"complex":[82],"structures.":[84],"To":[85],"address":[86],"these":[87],"challenges,":[88],"this":[90],"paper,":[91],"we":[92,119,157],"propose":[93],"predict":[95],"sequentially":[98],"by":[99],"applying":[100],"recurrent":[102],"neural":[103],"networks":[104],"(RNNs),":[105],"which":[106,162],"are":[107,147],"used":[108],"encode":[110],"dependencies.":[113],"When":[114],"predicting":[115,189],"specific":[117],"label,":[118],"introduce":[120],"dynamic":[122],"attention":[123],"mechanism":[124],"enable":[126],"model":[128],"focus":[130],"on":[131],"only":[132],"Two":[139],"benchmark":[140],"datasets":[141],"(i.e.,":[142],"Pascal":[143],"VOC":[144],"MS-COCO)":[146],"adopted":[148],"demonstrate":[150],"effectiveness":[152,174],"our":[154,176,182],"work.":[155],"Moreover,":[156],"construct":[158],"new":[160],"dataset,":[161],"includes":[163],"many":[164],"semantic":[165,191],"dependent":[166],"image,":[170],"verify":[172],"model.":[177],"Experimental":[178],"results":[179],"show":[180],"that":[181],"method":[183],"outperforms":[184],"state-of-the-arts,":[186],"especially":[187],"when":[188],"some":[190],"relative":[192],"labels.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}