{"id":"https://openalex.org/W4408358227","doi":"https://doi.org/10.1109/tpami.2025.3550526","title":"Active Supervised Cross-Modal Retrieval","display_name":"Active Supervised Cross-Modal Retrieval","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408358227","doi":"https://doi.org/10.1109/tpami.2025.3550526","pmid":"https://pubmed.ncbi.nlm.nih.gov/40072859"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3550526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3550526","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5000417495","display_name":"Huaiwen Zhang","orcid":"https://orcid.org/0000-0002-3183-9218"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaiwen Zhang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0000-0002-3183-9218","affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397772","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0003-2690-7180"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0000-0003-2690-7180","affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034515569","display_name":"Fan Qi","orcid":"https://orcid.org/0000-0003-1461-7100"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Qi","raw_affiliation_strings":["College of Computer Science, Tianjin University of Technology, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-1461-7100","affiliations":[{"raw_affiliation_string":"College of Computer Science, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073601707","display_name":"Shengsheng Qian","orcid":"https://orcid.org/0000-0001-9488-2208"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengsheng Qian","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9488-2208","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8343-9665","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7398,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.92652707,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"47","issue":"6","first_page":"5112","last_page":"5126"},"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":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.687953770160675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6550115346908569},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5642609596252441},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40557196736335754},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34141308069229126},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3346223831176758}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.687953770160675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6550115346908569},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5642609596252441},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40557196736335754},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34141308069229126},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3346223831176758},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3550526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3550526","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40072859","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40072859","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1383338027","display_name":null,"funder_award_id":"62206137","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1406082945","display_name":null,"funder_award_id":"62206200","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1498893086","display_name":null,"funder_award_id":"62036012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2280626339","display_name":null,"funder_award_id":"62276257","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1970855969","https://openalex.org/W2007972815","https://openalex.org/W2011674654","https://openalex.org/W2100235303","https://openalex.org/W2108598243","https://openalex.org/W2128518360","https://openalex.org/W2149197198","https://openalex.org/W2155803963","https://openalex.org/W2748386424","https://openalex.org/W2765440071","https://openalex.org/W2788686132","https://openalex.org/W2802572676","https://openalex.org/W2842511635","https://openalex.org/W2888796042","https://openalex.org/W2898952346","https://openalex.org/W2933775054","https://openalex.org/W2956018683","https://openalex.org/W2964002344","https://openalex.org/W2967957126","https://openalex.org/W2969471275","https://openalex.org/W2979306407","https://openalex.org/W2984303785","https://openalex.org/W2986514296","https://openalex.org/W3014249243","https://openalex.org/W3037466839","https://openalex.org/W3049254243","https://openalex.org/W3080353943","https://openalex.org/W3094172275","https://openalex.org/W3095809828","https://openalex.org/W3107927687","https://openalex.org/W3127668069","https://openalex.org/W3164803610","https://openalex.org/W3168433561","https://openalex.org/W3174702694","https://openalex.org/W3174894125","https://openalex.org/W3176349206","https://openalex.org/W3184557372","https://openalex.org/W3185219364","https://openalex.org/W3187176672","https://openalex.org/W3205626500","https://openalex.org/W3207005171","https://openalex.org/W3216480618","https://openalex.org/W3217016149","https://openalex.org/W4200631738","https://openalex.org/W4221138649","https://openalex.org/W4226107105","https://openalex.org/W4230649179","https://openalex.org/W4283837671","https://openalex.org/W4284679506","https://openalex.org/W4284896388","https://openalex.org/W4297808394","https://openalex.org/W4304480715","https://openalex.org/W4310465416","https://openalex.org/W4312677475","https://openalex.org/W4386065435","https://openalex.org/W4386065563","https://openalex.org/W4386075926","https://openalex.org/W4386076030","https://openalex.org/W4386076294","https://openalex.org/W4386076514","https://openalex.org/W4398250170","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6686207219","https://openalex.org/W6735374517","https://openalex.org/W6747231328","https://openalex.org/W6748034479","https://openalex.org/W6763607942","https://openalex.org/W6790019176","https://openalex.org/W6804095316","https://openalex.org/W6809741598"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Supervised":[0,166],"Cross-Modal":[1,167],"Retrieval":[2,168],"(SCMR)":[3],"achieves":[4],"significant":[5],"performance":[6,49,156,279],"with":[7,141,230],"the":[8,19,27,56,69,88,94,98,107,136,154,194,220,226,258,275],"supervision":[9],"provided":[10],"by":[11,280],"substantial":[12],"label":[13],"annotations":[14],"of":[15,29,109,135,157,199,224,228,265,274],"multi-modal":[16,24,148,175,188,200],"data.":[17],"However,":[18],"requirement":[20],"for":[21,63,73,290],"large":[22],"annotated":[23],"datasets":[25],"restricts":[26],"use":[28],"supervised":[30,74,277],"cross-modal":[31,75],"retrieval":[32,76,155],"in":[33,50,54,132,255],"many":[34],"practical":[35],"scenarios.":[36],"Active":[37,165],"Learning":[38],"(AL)":[39],"has":[40],"been":[41],"proposed":[42,238],"to":[43,115],"reduce":[44],"labeling":[45,64],"costs":[46],"while":[47,261],"improving":[48],"various":[51],"label-dependent":[52],"tasks,":[53],"which":[55,171],"most":[57],"informative":[58,174],"unlabeled":[59],"samples":[60,122,176,289],"are":[61,129,240],"selected":[62,121,288],"and":[65,128,151,177,196,250,285,293],"training.":[66],"Directly":[67],"exploiting":[68],"existing":[70,102],"AL":[71],"methods":[72,103,239],"may":[77],"not":[78],"be":[79],"a":[80,116,133,186,203,213,231],"good":[81],"idea":[82],"since":[83],"they":[84],"only":[85,281],"focus":[86,104],"on":[87,106,242],"uncertainty":[89,198],"within":[90,97,202],"each":[91],"modality,":[92],"ignoring":[93],"inter-modality":[95,197],"relationship":[96],"text-image":[99],"pairs.":[100],"Furthermore,":[101],"exclusively":[105],"informativeness":[108,189,227],"data":[110,144],"during":[111],"sample":[112,180,209],"selection,":[113,210],"leading":[114],"biased,":[117],"homogenized":[118],"set":[119],"where":[120],"often":[123],"contain":[124],"nearly":[125],"identical":[126],"semantics":[127],"densely":[130],"distributed":[131],"region":[134],"feature":[137],"space.":[138],"Persistent":[139],"training":[140],"such":[142],"biased":[143],"selections":[145],"can":[146],"disturb":[147],"representation":[149],"learning":[150,222,267],"substantially":[152],"degrade":[153],"SCMR.":[158],"In":[159,182],"this":[160],"work,":[161],"we":[162,184,211],"propose":[163,185],"an":[164],"(ASCMR)":[169],"framework,":[170],"effectively":[172],"identifies":[173],"generates":[178],"unbiased":[179,208],"selections.":[181],"particular,":[183],"probabilistic":[187],"estimation":[190],"that":[191,218],"captures":[192],"both":[193],"intra-modality":[195],"pairs":[201],"unified":[204],"representation.":[205],"To":[206],"ensure":[207],"introduce":[212],"density-aware":[214],"budget":[215],"allocation":[216],"strategy":[217],"constrains":[219],"active":[221,266,287],"objective":[223],"maximizing":[225],"selection":[229],"novel":[232],"semantic":[233],"density":[234],"regularization":[235],"term.":[236],"The":[237],"evaluated":[241],"three":[243],"widely":[244],"used":[245],"benchmark":[246],"datasets,":[247],"MS-COCO,":[248,291],"NUS-WIDE,":[249,292],"MIRFlickr,":[251,294],"demonstrating":[252],"our":[253],"effectiveness":[254],"significantly":[256],"reducing":[257],"annotation":[259],"cost":[260],"outperforming":[262],"other":[263],"baselines":[264],"strategies.":[268],"We":[269],"could":[270],"achieve":[271],"over":[272],"95%":[273],"fully":[276],"model's":[278],"utilizing":[282],"6%,":[283],"3%,":[284],"4%":[286],"respectively.":[295]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}