{"id":"https://openalex.org/W7156073746","doi":"https://doi.org/10.1145/3774904.3792154","title":"Dual-Branch Multi-Granularity Network with Structured Contrastive Ranking for Cross-Modal Retrieval","display_name":"Dual-Branch Multi-Granularity Network with Structured Contrastive Ranking for Cross-Modal Retrieval","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7156073746","doi":"https://doi.org/10.1145/3774904.3792154"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792154","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792154","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134721430","display_name":"Zihao Chen","orcid":"https://orcid.org/0009-0001-0218-2827"},"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"]},{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]},{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Chen","raw_affiliation_strings":["The Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China), Hefei University of Technology, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0001-0218-2827","affiliations":[{"raw_affiliation_string":"The Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China), Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422","https://openalex.org/I143868143","https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062592193","display_name":"Chenyang Bu","orcid":"https://orcid.org/0000-0001-8203-0956"},"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"]},{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]},{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Bu","raw_affiliation_strings":["The Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China), Hefei University of Technology, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-8203-0956","affiliations":[{"raw_affiliation_string":"The Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China), Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422","https://openalex.org/I143868143","https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039946566","display_name":"Shengwei Ji","orcid":"https://orcid.org/0000-0003-4942-9767"},"institutions":[{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengwei Ji","raw_affiliation_strings":["School of Artificial Intelligence and Big Data, Hefei University, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-4942-9767","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Big Data, Hefei University, Hefei, Anhui, China","institution_ids":["https://openalex.org/I39774598"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134677274","display_name":"Xindong Wu","orcid":"https://orcid.org/0000-0003-2396-1704"},"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"]},{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]},{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xindong Wu","raw_affiliation_strings":["The Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China), Hefei University of Technology, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-2396-1704","affiliations":[{"raw_affiliation_string":"The Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China), Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422","https://openalex.org/I143868143","https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64156548,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1959","last_page":"1970"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6929000020027161,"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":0.6929000020027161,"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":0.2524000108242035,"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":0.014399999752640724,"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/discriminative-model","display_name":"Discriminative model","score":0.6484000086784363},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6355000138282776},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6043000221252441},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5698000192642212},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5532000064849854},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41609999537467957},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.3127000033855438},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.3091000020503998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8044999837875366},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6484000086784363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6480000019073486},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6355000138282776},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6043000221252441},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5698000192642212},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5532000064849854},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.476500004529953},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41609999537467957},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37709999084472656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3165000081062317},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.3091000020503998},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792154","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792154","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792154","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7406327128410339,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2007972815","https://openalex.org/W2106277773","https://openalex.org/W2137434377","https://openalex.org/W2945210081","https://openalex.org/W2964081303","https://openalex.org/W2967957126","https://openalex.org/W3022592147","https://openalex.org/W3130796238","https://openalex.org/W3168433561","https://openalex.org/W3187176672","https://openalex.org/W4206430846","https://openalex.org/W4213303451","https://openalex.org/W4285221285","https://openalex.org/W4304083193","https://openalex.org/W4312877428","https://openalex.org/W4312924260","https://openalex.org/W4313178921","https://openalex.org/W4313181088","https://openalex.org/W4386072138","https://openalex.org/W4386075677","https://openalex.org/W4389675233","https://openalex.org/W4393159265","https://openalex.org/W4393160894","https://openalex.org/W4399527522","https://openalex.org/W4403792420","https://openalex.org/W4406387563","https://openalex.org/W4406857712","https://openalex.org/W4408358227","https://openalex.org/W4409670741","https://openalex.org/W4410737652","https://openalex.org/W4412887939","https://openalex.org/W4413145070","https://openalex.org/W4414359625","https://openalex.org/W4414359834","https://openalex.org/W4415241163","https://openalex.org/W4417051941"],"related_works":[],"abstract_inverted_index":{"Cross-modal":[0],"retrieval":[1,58],"(CMR)":[2],"has":[3],"advanced":[4],"considerably":[5],"by":[6,84],"mapping":[7],"image":[8],"and":[9,44,105,108,124],"text":[10],"features":[11],"into":[12],"a":[13,86,99,113,149],"shared":[14],"embedding":[15],"space;":[16],"however,":[17],"these":[18,67],"approaches":[19],"still":[20],"face":[21],"two":[22],"persistent":[23],"challenges:":[24],"(1)":[25],"semantic":[26,49],"sparsity,":[27],"where":[28,51],"discriminative":[29],"cues":[30,97],"are":[31],"confined":[32],"to":[33,39,54,91],"localized":[34],"regions,":[35],"making":[36],"it":[37],"difficult":[38],"identify":[40],"implicit":[41],"visual":[42,82],"evidence;":[43],"(2)":[45],"ranking":[46,110],"uncertainty":[47],"under":[48],"ambiguity,":[50],"models":[52],"struggle":[53],"maintain":[55],"the":[56,71],"correct":[57],"order":[59],"when":[60],"candidates":[61],"share":[62],"similar":[63],"contexts.":[64],"To":[65],"address":[66],"issues,":[68],"we":[69],"propose":[70],"Dual-Branch":[72],"Multi-Granularity":[73],"Network":[74],"(DBMG)":[75],"with":[76],"Structured":[77],"Contrastive":[78],"Ranking,":[79],"which":[80],"enriches":[81],"semantics":[83],"leveraging":[85],"multimodal":[87],"large":[88],"language":[89],"model":[90],"generate":[92],"auxiliary":[93],"descriptions,":[94],"aligns":[95],"sparse":[96],"through":[98],"dual-branch":[100],"architecture":[101],"capturing":[102],"both":[103],"global":[104],"local":[106],"interactions,":[107],"enforces":[109],"consistency":[111],"via":[112],"three-stage":[114],"contrastive":[115],"objective":[116],"that":[117,135],"progressively":[118],"optimizes":[119],"category":[120],"clustering,":[121],"instance":[122],"alignment,":[123],"margin-based":[125],"ranking.":[126],"Extensive":[127],"experiments":[128],"on":[129],"four":[130],"standard":[131],"CMR":[132],"benchmarks":[133],"demonstrate":[134],"DBMG":[136],"outperforms":[137],"12":[138],"strong":[139],"baselines,":[140],"achieving":[141],"an":[142],"average":[143],"15.91%":[144],"improvement":[145],"in":[146],"mAP,":[147],"establishing":[148],"new":[150],"state-of-the-art.":[151],"The":[152],"code":[153],"is":[154],"available":[155],"at":[156],"https://github.com/DMiC-Lab-HFUT/DBMG.":[157]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-28T00:00:00"}