{"id":"https://openalex.org/W4412945007","doi":"https://doi.org/10.18653/v1/2025.acl-long.935","title":"MegaPairs: Massive Data Synthesis for Universal Multimodal Retrieval","display_name":"MegaPairs: Massive Data Synthesis for Universal Multimodal Retrieval","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945007","doi":"https://doi.org/10.18653/v1/2025.acl-long.935"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.935","doi":"https://doi.org/10.18653/v1/2025.acl-long.935","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.935","pdf_url":"https://aclanthology.org/2025.acl-long.935.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2025.acl-long.935.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100758508","display_name":"Junjie Zhou","orcid":"https://orcid.org/0000-0002-1323-053X","observed_orcids":["https://orcid.org/0000-0002-1323-053X"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":"CN","type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Zhou","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence","State Key Laboratory of Networking and Switching Technology , Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology , Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101879433","display_name":"Yongping Xiong","orcid":"https://orcid.org/0000-0001-8670-3898","observed_orcids":["https://orcid.org/0000-0001-8670-3898","https://orcid.org/0000-0001-5333-204X"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":"CN","type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongping Xiong","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology , Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology , Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100423656","display_name":"Zheng Liu","orcid":"https://orcid.org/0000-0001-7765-8466","observed_orcids":["https://orcid.org/0000-0001-7765-8466","https://orcid.org/0009-0006-1277-0493","https://orcid.org/0000-0003-3437-2630"]},"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/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zheng Liu","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence","The Hong Kong Polytechnic University","University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ze Liu","orcid":null,"observed_orcids":[]},"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/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Ze Liu","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence","The Hong Kong Polytechnic University","University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044147794","display_name":"Shitao Xiao","orcid":"https://orcid.org/0000-0003-2567-6843","observed_orcids":["https://orcid.org/0000-0003-2567-6843"]},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shitao Xiao","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yueze Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueze Wang","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019447016","display_name":"Bo Zhao","orcid":"https://orcid.org/0000-0001-7877-7934","observed_orcids":["https://orcid.org/0000-0001-7877-7934"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University ,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374113","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0002-3306-9317","observed_orcids":["https://orcid.org/0000-0002-3306-9317"]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chen Jason Zhang","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085254654","display_name":"Defu Lian","orcid":"https://orcid.org/0000-0002-3507-9607","observed_orcids":["https://orcid.org/0000-0002-3507-9607"]},"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":"Defu Lian","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.464,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.97618544,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"19076","last_page":"19095"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7440999746322632,"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":0.7440999746322632,"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":0.1851000040769577,"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":0.05139999836683273,"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/multimodal-retrieval","display_name":"multimodal retrieval","score":0.9330000281333923},{"id":"https://openalex.org/keywords/data-synthesis","display_name":"data synthesis","score":0.7990000247955322},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.6119999885559082},{"id":"https://openalex.org/keywords/large-scale-data","display_name":"large-scale data","score":0.3479999899864197},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.6019999980926514},{"id":"https://openalex.org/keywords/multimodal-data","display_name":"multimodal data","score":0.33399999141693115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7477445602416992},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5025975704193115}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.935","doi":"https://doi.org/10.18653/v1/2025.acl-long.935","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.935","pdf_url":"https://aclanthology.org/2025.acl-long.935.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.14475","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.14475","pdf_url":"https://arxiv.org/pdf/2412.14475","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.14475","doi":"https://doi.org/10.48550/arxiv.2412.14475","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.14475","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.935","doi":"https://doi.org/10.18653/v1/2025.acl-long.935","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.935","pdf_url":"https://aclanthology.org/2025.acl-long.935.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.4099999964237213,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G8877833081","display_name":null,"funder_award_id":"62306046","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/F4320327557","display_name":"National Office for Philosophy and Social Sciences","ror":"https://ror.org/04m0ms912"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945007.pdf","grobid_xml":"https://content.openalex.org/works/W4412945007.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4405766600","https://openalex.org/W4413146941","https://openalex.org/W4416031498","https://openalex.org/W3132042721","https://openalex.org/W4206736799","https://openalex.org/W6891782444","https://openalex.org/W7131107355","https://openalex.org/W4413157159","https://openalex.org/W4415539179","https://openalex.org/W4404781497"],"abstract_inverted_index":{"Despite":[0],"the":[1,59,65,134,139],"rapidly":[2],"growing":[3],"demand":[4],"for":[5],"multimodal":[6,60],"retrieval,":[7],"progress":[8],"in":[9,96],"this":[10,21,48,99,117],"field":[11],"remains":[12],"severely":[13],"constrained":[14],"by":[15,143],"a":[16,26,42],"lack":[17],"of":[18,113],"training":[19,107],"data.In":[20],"paper,":[22],"we":[23,101],"introduce":[24],"MegaPairs,":[25],"novel":[27],"data":[28,72],"synthesis":[29],"method":[30],"that":[31,53],"leverages":[32],"vision":[33],"language":[34],"models":[35,112,120,159],"(VLMs)":[36],"and":[37,84,109,133,157],"open-domain":[38],"images,":[39],"together":[40],"with":[41,150],"massive":[43],"synthetic":[44],"dataset":[45],"generated":[46],"from":[47,73],"method.Our":[49],"empirical":[50],"analysis":[51],"shows":[52],"MegaPairs":[54,77],"generates":[55],"high-quality":[56],"data,":[57],"enabling":[58,93],"retriever":[61],"to":[62],"significantly":[63],"outperform":[64],"baseline":[66],"model":[67],"trained":[68,110],"on":[69,80,138],"70\u00d7":[70],"more":[71,103],"existing":[74],"datasets.Moreover,":[75],"since":[76],"solely":[78],"relies":[79],"general":[81],"image":[82,129],"corpora":[83],"open-source":[85],"VLMs,":[86],"it":[87],"can":[88],"be":[89],"easily":[90],"scaled":[91],"up,":[92],"continuous":[94],"improvements":[95,149],"retrieval":[97,130],"performance.In":[98],"stage,":[100],"produced":[102],"than":[104],"26":[105],"million":[106],"instances":[108],"several":[111],"varying":[114],"sizes":[115],"using":[116],"data.These":[118],"new":[119],"achieve":[121],"state-of-the-art":[122],"zero-shot":[123],"performance":[124,137,148],"across":[125],"4":[126],"popular":[127],"composed":[128],"(CIR)":[131],"benchmarks":[132],"highest":[135],"overall":[136],"36":[140],"datasets":[141],"provided":[142],"MMEB.They":[144],"also":[145],"demonstrate":[146],"notable":[147],"additional":[151],"downstream":[152],"fine-tuning.Our":[153],"code,":[154],"synthesized":[155],"dataset,":[156],"pre-trained":[158],"are":[160],"publicly":[161],"available":[162],"at":[163],"https://github.com/":[164],"VectorSpaceLab/MegaPairs.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2025-10-10T00:00:00"}
