{"id":"https://openalex.org/W4385688545","doi":"https://doi.org/10.1145/3578337.3605137","title":"Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering","display_name":"Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering","publication_year":2023,"publication_date":"2023-08-09","ids":{"openalex":"https://openalex.org/W4385688545","doi":"https://doi.org/10.1145/3578337.3605137"},"language":"en","primary_location":{"id":"doi:10.1145/3578337.3605137","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3578337.3605137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM SIGIR International Conference on Theory of Information Retrieval","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/A5082594835","display_name":"Alireza Salemi","orcid":"https://orcid.org/0009-0006-1937-2615"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alireza Salemi","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":"https://orcid.org/0009-0006-1937-2615","affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101613387","display_name":"Mahta Rafiee","orcid":"https://orcid.org/0009-0007-1410-4897"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahta Rafiee","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":"https://orcid.org/0009-0007-1410-4897","affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457713","display_name":"Hamed Zamani","orcid":"https://orcid.org/0000-0002-0800-3340"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamed Zamani","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0800-3340","affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"169","last_page":"176"},"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":0.9993000030517578,"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":0.9961000084877014,"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/question-answering","display_name":"Question answering","score":0.8893612027168274},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8399906158447266},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7086329460144043},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5854002237319946},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5660915970802307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5348113775253296},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5191997289657593},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.48390254378318787},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4823581576347351},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3724963068962097},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07512614130973816}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8893612027168274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8399906158447266},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7086329460144043},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5854002237319946},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5660915970802307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5348113775253296},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5191997289657593},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48390254378318787},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4823581576347351},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3724963068962097},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07512614130973816},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3578337.3605137","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3578337.3605137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7699234984","display_name":"III: Medium: Collaborative Research: Athena:  Learning-oriented Search with Personalized Learning Flows","funder_award_id":"2106282","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2101105183","https://openalex.org/W2525579820","https://openalex.org/W2594029062","https://openalex.org/W2610935556","https://openalex.org/W2613589950","https://openalex.org/W2889757348","https://openalex.org/W2964121744","https://openalex.org/W2964303913","https://openalex.org/W2965373594","https://openalex.org/W2981852735","https://openalex.org/W2998536339","https://openalex.org/W2998702515","https://openalex.org/W3035313607","https://openalex.org/W3139224848","https://openalex.org/W3156082048","https://openalex.org/W4205480697","https://openalex.org/W4283777642","https://openalex.org/W4284669679","https://openalex.org/W4288089799","https://openalex.org/W4294534134","https://openalex.org/W4385573917"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W4288102755","https://openalex.org/W2103247590","https://openalex.org/W3159777597"],"abstract_inverted_index":{"This":[0,21],"paper":[1],"studies":[2],"a":[3,60,65,73,118],"category":[4,22],"of":[5,76],"visual":[6,26],"question":[7,27],"answering":[8,18,28],"tasks,":[9],"in":[10,33,121],"which":[11],"accessing":[12],"external":[13],"knowledge":[14],"is":[15,23,37],"necessary":[16],"for":[17,42,53,79,89,94],"the":[19,43,107,113],"questions.":[20],"called":[24],"outside-knowledge":[25],"(OK-VQA).":[29],"A":[30],"major":[31],"step":[32],"developing":[34],"OK-VQA":[35,95],"systems":[36],"to":[38,101,106],"retrieve":[39],"relevant":[40],"documents":[41],"given":[44],"multi-modal":[45,61],"query.":[46],"Current":[47],"state-of-the-art":[48,109],"asymmetric":[49,110],"dense":[50],"retrieval":[51,92,123],"model":[52],"this":[54],"task":[55],"uses":[56],"an":[57,70,84],"architecture":[58,71],"with":[59],"query":[62],"encoder":[63],"and":[64],"uni-modal":[66],"document":[67],"encoder.":[68],"Such":[69],"requires":[72],"large":[74],"amount":[75],"training":[77],"data":[78,86],"effective":[80],"performance.":[81],"We":[82],"propose":[83],"automatic":[85],"generation":[87],"pipeline":[88],"pre-training":[90,115],"passage":[91],"models":[93],"tasks.":[96],"The":[97],"proposed":[98,114],"approach":[99,116],"leads":[100],"26.9%":[102],"Precision@5":[103],"improvements":[104],"compared":[105],"current":[108],"architecture.":[111],"Additionally,":[112],"exhibits":[117],"good":[119],"ability":[120],"zero-shot":[122],"scenarios.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}