{"id":"https://openalex.org/W4321480073","doi":"https://doi.org/10.1145/3539597.3570481","title":"AGREE: Aligning Cross-Modal Entities for Image-Text Retrieval Upon Vision-Language Pre-trained Models","display_name":"AGREE: Aligning Cross-Modal Entities for Image-Text Retrieval Upon Vision-Language Pre-trained Models","publication_year":2023,"publication_date":"2023-02-22","ids":{"openalex":"https://openalex.org/W4321480073","doi":"https://doi.org/10.1145/3539597.3570481"},"language":"en","primary_location":{"id":"doi:10.1145/3539597.3570481","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539597.3570481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5114594103","display_name":"Xiaodan Wang","orcid":"https://orcid.org/0000-0002-3721-3494"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Wang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3721-3494","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008585342","display_name":"Lei Li","orcid":"https://orcid.org/0000-0002-8891-1786"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Li","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8891-1786","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065529268","display_name":"Zhixu Li","orcid":"https://orcid.org/0000-0003-2355-288X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixu Li","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2355-288X","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068832926","display_name":"Xuwu Wang","orcid":"https://orcid.org/0000-0003-3363-570X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuwu Wang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3363-570X","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041560675","display_name":"Xiangru Zhu","orcid":"https://orcid.org/0000-0001-7308-3642"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangru Zhu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7308-3642","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373451","display_name":"Chengyu Wang","orcid":"https://orcid.org/0000-0003-1010-9678"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyu Wang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1010-9678","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054621636","display_name":"Jun Huang","orcid":"https://orcid.org/0000-0002-7706-7081"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Huang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7706-7081","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090455375","display_name":"Yanghua Xiao","orcid":"https://orcid.org/0000-0001-8403-9591"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanghua Xiao","raw_affiliation_strings":["Fudan University & Fudan-Aishu Cognitive Intelligence Joint Research Center, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8403-9591","affiliations":[{"raw_affiliation_string":"Fudan University & Fudan-Aishu Cognitive Intelligence Joint Research Center, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"456","last_page":"464"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9962000250816345,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9915000200271606,"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":0.8560168743133545},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.801241934299469},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7010666728019714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6086540222167969},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5954603552818298},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5741133093833923},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5107829570770264},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5066567063331604},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4805377125740051},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46682828664779663},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.42042481899261475},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37125593423843384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8560168743133545},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.801241934299469},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7010666728019714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6086540222167969},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5954603552818298},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5741133093833923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5107829570770264},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5066567063331604},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4805377125740051},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46682828664779663},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.42042481899261475},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37125593423843384},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539597.3570481","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539597.3570481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1926516915","https://openalex.org/W2185175083","https://openalex.org/W2277195237","https://openalex.org/W2749708282","https://openalex.org/W2765440071","https://openalex.org/W2795389793","https://openalex.org/W2903529742","https://openalex.org/W2962784628","https://openalex.org/W2962964995","https://openalex.org/W2963527096","https://openalex.org/W2964120214","https://openalex.org/W2970231061","https://openalex.org/W2988823324","https://openalex.org/W2998356391","https://openalex.org/W3035688398","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3102566412","https://openalex.org/W3110042533","https://openalex.org/W3118694826","https://openalex.org/W3139017368","https://openalex.org/W3166304536","https://openalex.org/W3168851777","https://openalex.org/W3173909648","https://openalex.org/W3174010726","https://openalex.org/W3177654849","https://openalex.org/W3184735396","https://openalex.org/W3184784418","https://openalex.org/W3207798279","https://openalex.org/W4283218507","https://openalex.org/W4285106586","https://openalex.org/W4312956471","https://openalex.org/W4313178921"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W2031260042","https://openalex.org/W2185469136","https://openalex.org/W2391445434","https://openalex.org/W4301143707","https://openalex.org/W2952745240"],"abstract_inverted_index":{"Image-text":[0],"retrieval":[1,30,46,98],"is":[2,67],"a":[3,87],"challenging":[4],"cross-modal":[5,51,94,124],"task":[6],"that":[7,48,162],"arouses":[8],"much":[9],"attention.":[10],"While":[11],"the":[12,18,38,63,76,104],"traditional":[13],"methods":[14,40],"cannot":[15,49],"break":[16],"down":[17],"barriers":[19],"between":[20],"different":[21],"modalities,":[22],"Vision-Language":[23],"Pre-trained":[24],"(VLP)":[25],"models":[26,101,154],"greatly":[27],"improve":[28],"image-text":[29,35,97,119],"performance":[31],"based":[32],"on":[33,155],"massive":[34],"pairs.":[36],"Nonetheless,":[37],"VLP-based":[39],"are":[41,140],"still":[42],"prone":[43],"to":[44,58,75,92,115],"produce":[45],"results":[47,167],"be":[50],"aligned":[52],"with":[53,151],"entities.":[54],"Recent":[55],"efforts":[56],"try":[57],"fix":[59],"this":[60,82],"problem":[61],"at":[62,103],"pre-training":[64],"stage,":[65],"which":[66],"not":[68],"only":[69,102],"expensive":[70],"but":[71],"also":[72],"unpractical":[73],"due":[74],"unavailable":[77],"of":[78],"full":[79],"datasets.":[80],"In":[81],"paper,":[83],"we":[84],"novelly":[85],"propose":[86],"lightweight":[88],"and":[89,106,113,121,130,158],"practical":[90],"approach":[91,164],"align":[93],"entities":[95],"for":[96,146],"upon":[99],"VLP":[100,153],"fine-tuning":[105],"re-ranking":[107,138],"stages.":[108],"We":[109],"employ":[110],"external":[111],"knowledge":[112],"tools":[114],"construct":[116],"extra":[117],"fine-grained":[118],"pairs,":[120],"then":[122],"emphasize":[123],"entity":[125],"alignment":[126],"through":[127],"contrastive":[128],"learning":[129],"entity-level":[131],"mask":[132],"modeling":[133],"in":[134,168],"fine-tuning.":[135],"Besides,":[136],"two":[137],"strategies":[139],"proposed,":[141],"including":[142],"one":[143],"specially":[144],"designed":[145],"zero-shot":[147],"scenarios.":[148],"Extensive":[149],"experiments":[150],"several":[152],"multiple":[156],"Chinese":[157],"English":[159],"datasets":[160],"show":[161],"our":[163],"achieves":[165],"state-of-the-art":[166],"nearly":[169],"all":[170],"settings.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}