{"id":"https://openalex.org/W4405440281","doi":"https://doi.org/10.1109/tpami.2024.3519112","title":"Cross-Modal Guided Visual Representation Learning for Social Image Retrieval","display_name":"Cross-Modal Guided Visual Representation Learning for Social Image Retrieval","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4405440281","doi":"https://doi.org/10.1109/tpami.2024.3519112","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030605"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3519112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3519112","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/A5065194313","display_name":"Ziyu Guan","orcid":"https://orcid.org/0000-0003-2413-4698"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyu Guan","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-2413-4698","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066572238","display_name":"Wanqing Zhao","orcid":"https://orcid.org/0000-0001-7622-0665"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanqing Zhao","raw_affiliation_strings":["School of Information Science and Technology, Northwest University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0001-7622-0665","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Northwest University, Xi’an, China","institution_ids":["https://openalex.org/I37802460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100710109","display_name":"Hongmin Liu","orcid":"https://orcid.org/0000-0001-9834-4087"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongmin Liu","raw_affiliation_strings":["School of Intelligence Science and Technology and the Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9834-4087","affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology and the Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065649079","display_name":"Yuta Nakashima","orcid":"https://orcid.org/0000-0001-8000-3567"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuta Nakashima","raw_affiliation_strings":["Institute for Datability Science, Osaka University, Osaka, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8000-3567","affiliations":[{"raw_affiliation_string":"Institute for Datability Science, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068454170","display_name":"Noboru Babaguchi","orcid":"https://orcid.org/0000-0003-3320-896X"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Noboru Babaguchi","raw_affiliation_strings":["Institute for Datability Science, Osaka University, Osaka, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3320-896X","affiliations":[{"raw_affiliation_string":"Institute for Datability Science, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102013345","display_name":"Xiaofei He","orcid":"https://orcid.org/0009-0001-9107-2354"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei He","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-9107-2354","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2262,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8105603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"47","issue":"3","first_page":"2186","last_page":"2198"},"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":1.0,"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":1.0,"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":0.9998999834060669,"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":0.9980000257492065,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7224260568618774},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7210147976875305},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5616179704666138},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5385978817939758},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5318676233291626},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4574408531188965},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45059096813201904},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43159353733062744}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7224260568618774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7210147976875305},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5616179704666138},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5385978817939758},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5318676233291626},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4574408531188965},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45059096813201904},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43159353733062744},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3519112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3519112","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:40030605","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030605","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":[{"display_name":"Reduced inequalities","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G2930858977","display_name":null,"funder_award_id":"62103314","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4230411568","display_name":null,"funder_award_id":"62273275","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5655994340","display_name":null,"funder_award_id":"62303366","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7071169373","display_name":null,"funder_award_id":"61936006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8269017458","display_name":null,"funder_award_id":"2020ZDLGY04-07","funder_id":"https://openalex.org/F4320336350","funder_display_name":"Key Research and Development Projects of Shaanxi Province"},{"id":"https://openalex.org/G8746616028","display_name":null,"funder_award_id":"62133012","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/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320336350","display_name":"Key Research and Development Projects of Shaanxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1913628733","https://openalex.org/W1933349210","https://openalex.org/W1974647172","https://openalex.org/W2007972815","https://openalex.org/W2012833704","https://openalex.org/W2123229215","https://openalex.org/W2155803963","https://openalex.org/W2163922914","https://openalex.org/W2194775991","https://openalex.org/W2340690086","https://openalex.org/W2461086877","https://openalex.org/W2544587078","https://openalex.org/W2618530766","https://openalex.org/W2808604000","https://openalex.org/W2889212689","https://openalex.org/W2962786441","https://openalex.org/W2962964995","https://openalex.org/W2966683369","https://openalex.org/W2981138049","https://openalex.org/W3025665229","https://openalex.org/W3034924978","https://openalex.org/W3035552787","https://openalex.org/W3093116134","https://openalex.org/W3133524129","https://openalex.org/W3171007011","https://openalex.org/W3173220247","https://openalex.org/W3176085205","https://openalex.org/W3195929246","https://openalex.org/W4221155360","https://openalex.org/W4312648273","https://openalex.org/W4312761738","https://openalex.org/W4312784228","https://openalex.org/W4362722892","https://openalex.org/W4377711491","https://openalex.org/W4380433178","https://openalex.org/W4382457317","https://openalex.org/W4383752469","https://openalex.org/W4385245566","https://openalex.org/W4385567711","https://openalex.org/W4386065512","https://openalex.org/W4386065811","https://openalex.org/W4386076409","https://openalex.org/W4387968544","https://openalex.org/W6636510571","https://openalex.org/W6697214482","https://openalex.org/W6730529904","https://openalex.org/W6738279954","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6853754985"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2795079307","https://openalex.org/W2714992399","https://openalex.org/W2793058541"],"abstract_inverted_index":{"Social":[0],"images":[1,156],"are":[2,69,103],"often":[3],"associated":[4],"with":[5,80],"rich":[6],"but":[7],"noisy":[8,158],"tags":[9,15,102,159,189],"from":[10,157],"community":[11],"contributions.":[12],"Although":[13],"social":[14,73,123,221],"can":[16,89,225],"potentially":[17],"provide":[18],"valuable":[19],"semantic":[20,153],"training":[21,172],"information":[22],"for":[23,72,96,121,139,193,231],"image":[24,40,60,74,124,222,233],"retrieval,":[25],"existing":[26],"studies":[27],"all":[28],"fail":[29],"to":[30,54,135,164],"effectively":[31],"filter":[32,180],"noises":[33],"by":[34,93,168],"exploiting":[35],"the":[36,55,59,85,101,129,215,232],"cross-modal":[37,46,97,133],"correlation":[38],"between":[39,87],"content":[41],"and":[42,61,105,115,160,179,198,208],"tags.":[43],"The":[44,142,236],"current":[45],"vision-and-language":[47],"representation":[48],"learning":[49],"methods,":[50],"which":[51],"selectively":[52],"attend":[53],"relevant":[56],"parts":[57],"of":[58,131,155,196],"text,":[62],"show":[63,202],"a":[64,169,184,228],"promising":[65],"direction.":[66],"However,":[67],"they":[68,78,108],"not":[70],"suitable":[71],"retrieval":[75,234],"since:":[76],"(1)":[77],"deal":[79],"natural":[81],"text":[82],"sequences":[83],"where":[84],"relationships":[86],"words":[88],"be":[90,118],"easily":[91],"captured":[92],"language":[94],"models":[95],"relevance":[98],"estimation,":[99],"while":[100],"isolated":[104],"noisy;":[106],"(2)":[107],"take":[109],"(image,":[110],"text)":[111],"pair":[112],"as":[113,227],"input,":[114],"consequently":[116],"cannot":[117],"employed":[119],"directly":[120],"unimodal":[122,140],"retrieval.":[125,141],"This":[126],"paper":[127],"tackles":[128],"challenge":[130],"utilizing":[132],"interactions":[134],"learn":[136],"precise":[137],"representations":[138,154],"proposed":[143],"framework,":[144],"dubbed":[145],"CGVR":[146,204,224],"(Cross-modal":[147],"Guided":[148],"Visual":[149],"Representation),":[150],"extracts":[151],"accurate":[152],"transfers":[161],"this":[162],"ability":[163],"image-only":[165],"hashing":[166],"subnetwork":[167],"carefully":[170],"designed":[171],"scheme.":[173],"To":[174],"well":[175],"capture":[176],"correlated":[177],"semantics":[178],"noises,":[181],"it":[182],"embeds":[183],"priori":[185],"common-sense":[186],"relationship":[187],"among":[188],"into":[190],"attention":[191],"computation":[192],"joint":[194],"awareness":[195],"textual":[197],"visual":[199],"context.":[200],"Experiments":[201],"that":[203],"achieves":[205],"approximately":[206],"8.82":[207],"5.45":[209],"points":[210],"improvement":[211],"in":[212],"MAP":[213],"over":[214],"state-of-the-art":[216],"on":[217],"two":[218],"widely":[219],"used":[220],"benchmarks.":[223],"serve":[226],"new":[229],"baseline":[230],"community.":[235],"code":[237],"is":[238],"provided":[239],"at":[240],"https://github.com/zhaowanqing/CGVR.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}