{"id":"https://openalex.org/W2954721224","doi":"https://doi.org/10.1109/tmm.2019.2924511","title":"<i>Deep0Tag</i>: Deep Multiple Instance Learning for Zero-Shot Image Tagging","display_name":"<i>Deep0Tag</i>: Deep Multiple Instance Learning for Zero-Shot Image Tagging","publication_year":2019,"publication_date":"2019-06-25","ids":{"openalex":"https://openalex.org/W2954721224","doi":"https://doi.org/10.1109/tmm.2019.2924511","mag":"2954721224"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2019.2924511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2924511","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/A5007895165","display_name":"Shafin Rahman","orcid":"https://orcid.org/0000-0001-7169-0318"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I4210101388","display_name":"Health Sciences and Nutrition","ror":"https://ror.org/0152bt112","country_code":"AU","type":"facility","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4210101388","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shafin Rahman","raw_affiliation_strings":["Data61, Commonwealth Scientific and Industrial Research Organization, Canberra, Australia","Research School of Engineering, The Australian National University, Canberra, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7169-0318","affiliations":[{"raw_affiliation_string":"Data61, Commonwealth Scientific and Industrial Research Organization, Canberra, Australia","institution_ids":["https://openalex.org/I4210101388","https://openalex.org/I42894916"]},{"raw_affiliation_string":"Research School of Engineering, The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000300751","display_name":"Salman Khan","orcid":"https://orcid.org/0000-0002-9502-1749"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I4210116052","display_name":"Inception Institute of Artificial Intelligence","ror":"https://ror.org/02664zk40","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210116052"]}],"countries":["AE","AU"],"is_corresponding":false,"raw_author_name":"Salman Khan","raw_affiliation_strings":["Inception Institute of Artificial Intelligence, Abu Dhabi, United Arab Emirates","Research School of Engineering, The Australian National University, Canberra, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9502-1749","affiliations":[{"raw_affiliation_string":"Inception Institute of Artificial Intelligence, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210116052"]},{"raw_affiliation_string":"Research School of Engineering, The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072837153","display_name":"Nick Barnes","orcid":"https://orcid.org/0000-0002-9343-9535"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I4210101388","display_name":"Health Sciences and Nutrition","ror":"https://ror.org/0152bt112","country_code":"AU","type":"facility","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4210101388","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Nick Barnes","raw_affiliation_strings":["Data61, Commonwealth Scientific and Industrial Research Organization, Canberra, Australia","Research School of Engineering, The Australian National University, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data61, Commonwealth Scientific and Industrial Research Organization, Canberra, Australia","institution_ids":["https://openalex.org/I4210101388","https://openalex.org/I42894916"]},{"raw_affiliation_string":"Research School of Engineering, The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1836,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.90455831,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"22","issue":"1","first_page":"242","last_page":"255"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991999864578247,"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":0.9988999962806702,"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":0.8210941553115845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7566298246383667},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5739109516143799},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5625457167625427},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5290619134902954},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4830787479877472},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47693175077438354},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46286046504974365},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4512259066104889},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.4346354007720947},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.42787009477615356},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4103904962539673},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.3992195427417755},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3823062777519226},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36279305815696716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8210941553115845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7566298246383667},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5739109516143799},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5625457167625427},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5290619134902954},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4830787479877472},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47693175077438354},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46286046504974365},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4512259066104889},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.4346354007720947},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.42787009477615356},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4103904962539673},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.3992195427417755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3823062777519226},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36279305815696716},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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":2,"locations":[{"id":"doi:10.1109/tmm.2019.2924511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2924511","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"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/294632","is_oa":false,"landing_page_url":"http://hdl.handle.net/1885/294632","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"Journal article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W21006490","https://openalex.org/W24402856","https://openalex.org/W93016980","https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1536680647","https://openalex.org/W1567302070","https://openalex.org/W1686810756","https://openalex.org/W1797268635","https://openalex.org/W1861492603","https://openalex.org/W1938425378","https://openalex.org/W1945608308","https://openalex.org/W1950117310","https://openalex.org/W1972306304","https://openalex.org/W1999818274","https://openalex.org/W2007972815","https://openalex.org/W2010181071","https://openalex.org/W2044913453","https://openalex.org/W2081580037","https://openalex.org/W2088049833","https://openalex.org/W2097117768","https://openalex.org/W2150399170","https://openalex.org/W2194775991","https://openalex.org/W2220111505","https://openalex.org/W2250539671","https://openalex.org/W2293561010","https://openalex.org/W2328434568","https://openalex.org/W2334493732","https://openalex.org/W2413850928","https://openalex.org/W2536305071","https://openalex.org/W2552383788","https://openalex.org/W2560609797","https://openalex.org/W2563764042","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2571156573","https://openalex.org/W2596142952","https://openalex.org/W2597015119","https://openalex.org/W2601051138","https://openalex.org/W2605572715","https://openalex.org/W2605805765","https://openalex.org/W2610510511","https://openalex.org/W2611632661","https://openalex.org/W2724492314","https://openalex.org/W2735810033","https://openalex.org/W2738853914","https://openalex.org/W2746797088","https://openalex.org/W2785934082","https://openalex.org/W2900868354","https://openalex.org/W2950800384","https://openalex.org/W2962870798","https://openalex.org/W2963052338","https://openalex.org/W2963093690","https://openalex.org/W2963097641","https://openalex.org/W2963346784","https://openalex.org/W2963351448","https://openalex.org/W2963465381","https://openalex.org/W2963854535","https://openalex.org/W2963936013","https://openalex.org/W2964275819","https://openalex.org/W2964350399","https://openalex.org/W3099554308","https://openalex.org/W3104069527","https://openalex.org/W4294170691","https://openalex.org/W6600827882","https://openalex.org/W6600987510","https://openalex.org/W6603820874","https://openalex.org/W6606917465","https://openalex.org/W6630792627","https://openalex.org/W6630875275","https://openalex.org/W6637373629","https://openalex.org/W6638319203","https://openalex.org/W6639102338","https://openalex.org/W6682691769","https://openalex.org/W6714138976","https://openalex.org/W6731892127","https://openalex.org/W6744580074","https://openalex.org/W6747701563","https://openalex.org/W6756159146","https://openalex.org/W6763422710"],"related_works":["https://openalex.org/W3192357901","https://openalex.org/W3036286480","https://openalex.org/W2387360586","https://openalex.org/W4287027631","https://openalex.org/W4237171675","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W3177930984","https://openalex.org/W2052697133"],"abstract_inverted_index":{"Zero-shot":[0],"learning":[1,16],"aims":[2],"to":[3,52,76,82,98,116,167,174],"perform":[4,162],"visual":[5],"reasoning":[6],"about":[7],"unseen":[8,42,56,216],"objects.":[9],"In-line":[10],"with":[11,245],"the":[12,32,64,96,126,133,140,148,169,178,246],"success":[13],"of":[14,67,91,135,215],"deep":[15,23,144,188],"on":[17,63],"object":[18],"recognition":[19,27],"problems,":[20],"several":[21,155,182],"end-to-end":[22,142],"models":[24,35],"for":[25,147,157,203,239],"zero-shot":[26,68,150,261],"have":[28],"been":[29],"proposed":[30,179],"in":[31,38],"literature.":[33],"These":[34],"are":[36,58,74],"successful":[37],"predicting":[39],"a":[40,235],"single":[41],"label":[43],"given":[44,218],"an":[45,77,113,163],"input":[46],"image":[47,69,109,119,123],"but":[48],"do":[49],"not":[50,193],"scale":[51],"cases":[53],"where":[54,71],"multiple":[55,72],"objects":[57],"present.":[59],"Here,":[60],"we":[61,111,138],"focus":[62],"challenging":[65],"problem":[66],"tagging,":[70],"labels":[73,217,228],"assigned":[75],"image,":[78],"that":[79],"may":[80],"relate":[81],"objects,":[83],"attributes,":[84],"actions,":[85],"events,":[86],"and":[87,121,161,249,252,259],"scene":[88,93],"type.":[89],"Discovery":[90],"these":[92],"concepts":[94],"requires":[95],"ability":[97],"process":[99,212],"multi-scale":[100],"information.":[101],"To":[102,132],"encompass":[103],"global":[104],"as":[105,107,229],"well":[106],"local":[108],"details,":[110],"propose":[112,139],"automatic":[114],"approach":[115],"locate":[117],"relevant":[118],"patches":[120],"model":[122],"tagging":[124,151,262],"within":[125],"Multiple":[127],"Instance":[128],"Learning":[129],"(MIL)":[130],"framework.":[131],"best":[134],"our":[136],"knowledge,":[137],"first":[141],"trainable":[143],"MIL":[145,189],"framework":[146,180],"multi-label":[149],"problem.":[152],"We":[153,243],"explore":[154],"alternatives":[156],"instance-level":[158],"evidence":[159],"aggregation":[160],"extensive":[164],"ablation":[165],"study":[166],"identify":[168],"optimal":[170],"pooling":[171],"strategy.":[172],"Due":[173],"its":[175],"novel":[176],"design,":[177],"has":[181],"interesting":[183],"features:":[184],"1)":[185],"unlike":[186],"previous":[187],"models,":[190],"it":[191,210,232],"does":[192],"use":[194],"any":[195,213],"off-line":[196],"procedure":[197],"(e.g.,":[198],"Selective":[199],"Search":[200],"or":[201],"EdgeBoxes)":[202],"bag":[204],"generation.":[205],"2)":[206],"During":[207],"test":[208],"time,":[209],"can":[211,233],"number":[214],"their":[219],"semantic":[220],"embedding":[221],"vectors.":[222],"3)":[223],"Using":[224],"only":[225],"image-level":[226],"seen":[227],"weak":[230],"annotation,":[231],"produce":[234],"localized":[236],"bounding":[237],"box":[238],"each":[240],"predicted":[241],"label.":[242],"experiment":[244],"large-scale":[247],"NUS-WIDE":[248],"MS-COCO":[250],"datasets":[251],"achieve":[253],"superior":[254],"performance":[255],"across":[256],"conventional,":[257],"zero-shot,":[258],"generalized":[260],"tasks.":[263]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}