{"id":"https://openalex.org/W4413979509","doi":"https://doi.org/10.1109/tcsvt.2025.3605958","title":"Beyond One and Two Tower: Cross-Modal Consensus Learning for Image-Text Retrieval","display_name":"Beyond One and Two Tower: Cross-Modal Consensus Learning for Image-Text Retrieval","publication_year":2025,"publication_date":"2025-09-04","ids":{"openalex":"https://openalex.org/W4413979509","doi":"https://doi.org/10.1109/tcsvt.2025.3605958"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3605958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3605958","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5000130041","display_name":"Zhangxiang Shi","orcid":"https://orcid.org/0000-0002-7442-3407"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhangxiang Shi","raw_affiliation_strings":["School of Information Science, University of Science and Technology of China, Hefei, China","school of information science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-7442-3407","affiliations":[{"raw_affiliation_string":"School of Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"school of information science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044692080","display_name":"Yunlai Ding","orcid":"https://orcid.org/0009-0000-7253-7614"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunlai Ding","raw_affiliation_strings":["Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China","faculty of information science and engineering, Ocean University of China, Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]},{"raw_affiliation_string":"faculty of information science and engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029633264","display_name":"Junyu Dong","orcid":"https://orcid.org/0000-0001-7012-2087"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyu Dong","raw_affiliation_strings":["Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China","faculty of information science and engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-7012-2087","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]},{"raw_affiliation_string":"faculty of information science and engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100648981","display_name":"Tianzhu Zhang","orcid":"https://orcid.org/0000-0003-1856-9564"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianzhu Zhang","raw_affiliation_strings":["School of Information Science, University of Science and Technology of China, Hefei, China","school of information science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1856-9564","affiliations":[{"raw_affiliation_string":"School of Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"school of information science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5588,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67633078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"36","issue":"2","first_page":"2581","last_page":"2593"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9959999918937683,"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":0.9918000102043152,"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":0.6330468058586121},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5565544366836548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5052350163459778},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.48890724778175354},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3922950029373169},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3425803482532501},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3371095359325409}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6330468058586121},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5565544366836548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5052350163459778},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.48890724778175354},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3922950029373169},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3425803482532501},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3371095359325409},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3605958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3605958","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2745461083","https://openalex.org/W2949461431","https://openalex.org/W2956018683","https://openalex.org/W2962964995","https://openalex.org/W2981586349","https://openalex.org/W2988823324","https://openalex.org/W2998356391","https://openalex.org/W3034305926","https://openalex.org/W3035588244","https://openalex.org/W3035605030","https://openalex.org/W3092820619","https://openalex.org/W3094172275","https://openalex.org/W3099614098","https://openalex.org/W3110042533","https://openalex.org/W3118694826","https://openalex.org/W3168433561","https://openalex.org/W3171668871","https://openalex.org/W3174873881","https://openalex.org/W3175888430","https://openalex.org/W3188008942","https://openalex.org/W3189718596","https://openalex.org/W3195680250","https://openalex.org/W3202436960","https://openalex.org/W3215742971","https://openalex.org/W4205219932","https://openalex.org/W4206314411","https://openalex.org/W4221142658","https://openalex.org/W4224952037","https://openalex.org/W4282931980","https://openalex.org/W4283805294","https://openalex.org/W4285118104","https://openalex.org/W4285186657","https://openalex.org/W4285283873","https://openalex.org/W4285606530","https://openalex.org/W4292258164","https://openalex.org/W4292787334","https://openalex.org/W4302307036","https://openalex.org/W4312460555","https://openalex.org/W4312761738","https://openalex.org/W4312934263","https://openalex.org/W4313030099","https://openalex.org/W4360897523","https://openalex.org/W4366851068","https://openalex.org/W4367060669","https://openalex.org/W4377235294","https://openalex.org/W4382998936","https://openalex.org/W4386071498","https://openalex.org/W4386071757","https://openalex.org/W4386071847","https://openalex.org/W4386075677","https://openalex.org/W4387968136","https://openalex.org/W4393147915","https://openalex.org/W4393154020","https://openalex.org/W4395056490","https://openalex.org/W4395447490","https://openalex.org/W4402715976","https://openalex.org/W4402716469","https://openalex.org/W4402727895","https://openalex.org/W4402753983","https://openalex.org/W4413145100"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W1986902711","https://openalex.org/W2396760013","https://openalex.org/W2148433556","https://openalex.org/W2171776552","https://openalex.org/W98391849","https://openalex.org/W1600907701","https://openalex.org/W2726741344"],"abstract_inverted_index":{"Existing":[0],"image-text":[1],"retrieval":[2],"methods":[3,82],"mainly":[4],"rely":[5],"on":[6,121,147],"region":[7],"and":[8,23,36,62,77,155,161],"word":[9],"features":[10],"to":[11,32,41,65,90,124],"measure":[12],"cross-modal":[13,17,38,67,106],"similarities.":[14],"Thus,":[15],"dense":[16],"semantic":[18,85,102,107],"alignment":[19,44,108],"which":[20,105],"matches":[21],"regions":[22,76],"words":[24,78],"becomes":[25],"crucial.":[26],"However,":[27],"this":[28,43,49],"is":[29,45,109],"non-trivial":[30],"due":[31],"the":[33,37,59,95,126,158],"heterogeneity":[34],"gap":[35],"attention":[39],"used":[40],"achieve":[42],"inefficient.":[46],"Towards":[47],"solving":[48],"problem,":[50],"we":[51,113,142],"propose":[52],"a":[53,88,115],"novel":[54,116],"framework":[55,72],"that":[56],"goes":[57],"beyond":[58],"previous":[60],"one-tower":[61],"two-tower":[63],"frameworks":[64],"learn":[66],"consensus":[68],"efficiently.":[69],"The":[70],"proposed":[71],"does":[73],"not":[74],"align":[75],"directly":[79],"like":[80],"existing":[81,133],"but":[83],"uses":[84],"prototypes":[86],"as":[87],"bridge":[89],"attend":[91],"specific":[92],"contents":[93],"with":[94],"same":[96],"semantics":[97],"among":[98],"different":[99],"modalities":[100],"through":[101,104],"decoders,":[103],"naturally":[110],"achieved.":[111],"Furthermore,":[112],"design":[114],"plug-and-play":[117],"self-correction":[118],"method":[119],"based":[120],"optimal":[122],"transport":[123],"alleviate":[125],"drawbacks":[127],"of":[128,138,163],"incomplete":[129],"pairwise":[130],"labels":[131],"in":[132],"multimodal":[134],"datasets.":[135],"On":[136],"top":[137],"various":[139],"base":[140],"backbones,":[141],"carry":[143],"out":[144],"extensive":[145],"experiments":[146],"two":[148],"benchmark":[149],"datasets,":[150],"<italic":[151],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[152],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">i.e</i>.,":[153],"Flickr30K":[154],"MS-COCO,":[156],"demonstrating":[157],"effectiveness,":[159],"superiority":[160],"generalization":[162],"our":[164],"method.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}