{"id":"https://openalex.org/W4412377189","doi":"https://doi.org/10.1145/3726302.3729902","title":"Beyond General Alignment: Fine-Grained Entity-Centric Image-Text Matching with Multimodal Attentive Experts","display_name":"Beyond General Alignment: Fine-Grained Entity-Centric Image-Text Matching with Multimodal Attentive Experts","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412377189","doi":"https://doi.org/10.1145/3726302.3729902"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3729902","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729902","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729902","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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729902","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101651167","display_name":"Yaxiong Wang","orcid":"https://orcid.org/0000-0001-6596-8117"},"institutions":[{"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":"Yaxiong Wang","raw_affiliation_strings":["Hefei University of Technology, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-6596-8117","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076603720","display_name":"Lianwei Wu","orcid":"https://orcid.org/0000-0003-1451-9295"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianwei Wu","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, Sha'xi Province, China"],"raw_orcid":"https://orcid.org/0000-0003-1451-9295","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, Sha'xi Province, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060524512","display_name":"Lechao Cheng","orcid":"https://orcid.org/0000-0002-7546-9052"},"institutions":[{"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":"Lechao Cheng","raw_affiliation_strings":["Hefei University of Technology, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-7546-9052","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065328976","display_name":"Zhun Zhong","orcid":"https://orcid.org/0000-0002-8202-0544"},"institutions":[{"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":"Zhun Zhong","raw_affiliation_strings":["Hefei University of Technology, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-8202-0544","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032565150","display_name":"Yujiao Wu","orcid":"https://orcid.org/0000-0001-6366-9834"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yujiao Wu","raw_affiliation_strings":["CSIRO, Hobart, Australia"],"raw_orcid":"https://orcid.org/0000-0001-6366-9834","affiliations":[{"raw_affiliation_string":"CSIRO, Hobart, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100377147","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-3094-7735"},"institutions":[{"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":"Meng Wang","raw_affiliation_strings":["Hefei University of Technology, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-3094-7735","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"792","last_page":"802"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983000159263611,"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/T10028","display_name":"Topic Modeling","score":0.9976000189781189,"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":0.7537827491760254},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5945048332214355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5306436419487},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5007295608520508},{"id":"https://openalex.org/keywords/image-matching","display_name":"Image matching","score":0.48426005244255066},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4520731270313263},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4438125193119049},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3370104432106018},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07861906290054321}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537827491760254},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5945048332214355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5306436419487},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5007295608520508},{"id":"https://openalex.org/C2986492983","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image matching","level":3,"score":0.48426005244255066},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4520731270313263},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4438125193119049},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3370104432106018},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07861906290054321},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3729902","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729902","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729902","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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3729902","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729902","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729902","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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3364597423","display_name":null,"funder_award_id":"62472139","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8198022395","display_name":null,"funder_award_id":"62302140","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G8480155402","display_name":null,"funder_award_id":"72188101","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/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320326536","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64"},{"id":"https://openalex.org/F4320328099","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412377189.pdf","grobid_xml":"https://content.openalex.org/works/W4412377189.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2609731892","https://openalex.org/W2883311563","https://openalex.org/W2962964995","https://openalex.org/W2965848243","https://openalex.org/W2982573303","https://openalex.org/W3034151018","https://openalex.org/W3088460296","https://openalex.org/W3211405508","https://openalex.org/W4313655813","https://openalex.org/W4322718191","https://openalex.org/W4362655923","https://openalex.org/W4384918448","https://openalex.org/W4387969466","https://openalex.org/W4389518749","https://openalex.org/W4389520191","https://openalex.org/W4389665280","https://openalex.org/W4393729321","https://openalex.org/W4396821554"],"related_works":["https://openalex.org/W2384918310","https://openalex.org/W2383808867","https://openalex.org/W2372581239","https://openalex.org/W2391245565","https://openalex.org/W2107893065","https://openalex.org/W2617958085","https://openalex.org/W1509862229","https://openalex.org/W1974208548","https://openalex.org/W2050706403","https://openalex.org/W1973922169"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,56,59,68,77],"aligning":[3],"images":[4,48],"with":[5,25,147],"texts":[6,46,69,124],"has":[7,216],"achieved":[8],"remarkable":[9],"results,":[10],"however,":[11],"existing":[12],"models":[13],"tend":[14],"to":[15,102,121,140,162,198,209],"serve":[16],"general":[17,78],"queries":[18],"and":[19,47,70,93,151,228],"often":[20],"fall":[21],"short":[22],"when":[23],"dealing":[24],"detailed":[26],"query":[27],"requirements.":[28],"In":[29,133],"this":[30,84],"paper,":[31],"we":[32,86,135,180],"work":[33],"towards":[34],"Entity-centric":[35],"Image-Text":[36],"Matching":[37,189],"(EITM),":[38],"a":[39,95,168],"finer-grained":[40],"image-text":[41,79,206],"matching":[42,80,207],"task":[43],"that":[44,234],"aligns":[45],"centered":[49],"around":[50],"specific":[51],"entities.":[52],"The":[53,230],"main":[54],"challenge":[55],"EITM":[57,109],"lies":[58],"bridging":[60,131],"the":[61,112,148,164,173,211],"substantial":[62],"semantic":[63,165,170],"gap":[64,166],"between":[65],"entity-related":[66],"information":[67],"images,":[71],"which":[72],"is":[73,120,153,243],"more":[74],"pronounced":[75],"than":[76],"problems.":[81],"To":[82],"address":[83],"challenge,":[85],"adopt":[87],"CLIP":[88,104],"as":[89,130],"our":[90,115,157,235],"foundational":[91],"model":[92],"devise":[94],"Multimodal":[96,158],"Attentive":[97,159],"Experts":[98,160],"(MMAE)-based":[99],"contrastive":[100],"learning":[101,119],"adapt":[103],"into":[105,156],"an":[106,184,194],"expert":[107],"for":[108],"problem.":[110],"Particularly,":[111],"core":[113],"of":[114],"multimodal":[116],"attentive":[117],"experts":[118],"generate":[122,141],"explanation":[123],"by":[125,178,204],"Large":[126],"Language":[127],"Models":[128],"(LLMs)":[129],"clues.":[132],"specific,":[134],"first":[136],"employ":[137],"off-the-shelf":[138],"LLMs":[139],"explanatory":[142],"text.":[143],"This":[144],"text,":[145,152],"along":[146],"original":[149],"image":[150],"then":[154],"fed":[155],"module":[161],"narrow":[163],"within":[167],"unified":[169],"space.":[171],"Upon":[172],"enriched":[174],"feature":[175],"representations":[176],"generated":[177],"MMAE,":[179,202],"have":[181],"further":[182],"developed":[183],"effective":[185],"Gated":[186],"Integrative":[187],"Image-text":[188],"(GI-ITM)":[190],"strategy.":[191],"GI-ITM":[192],"utilizes":[193],"adaptive":[195],"gating":[196],"mechanism":[197],"combine":[199],"features":[200],"from":[201],"followed":[203],"applying":[205],"constraints":[208],"enhance":[210],"alignment":[212],"precision.":[213],"Our":[214,241],"method":[215],"been":[217],"extensively":[218],"evaluated":[219],"on":[220],"three":[221],"social":[222],"media":[223],"news":[224],"benchmarks:":[225],"N24News,":[226],"VisualNews,":[227],"GoodNews.":[229],"experimental":[231],"results":[232],"demonstrate":[233],"approach":[236],"significantly":[237],"outperforms":[238],"competing":[239],"methods.":[240],"code":[242],"available":[244],"at:":[245],"https://github.com/wangyxxjtu/ETE.":[246]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}