{"id":"https://openalex.org/W3155855665","doi":"https://doi.org/10.1145/3404835.3462987","title":"Passage Retrieval for Outside-Knowledge Visual Question Answering","display_name":"Passage Retrieval for Outside-Knowledge Visual Question Answering","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3155855665","doi":"https://doi.org/10.1145/3404835.3462987","mag":"3155855665"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3462987","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3462987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.03938","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chen Qu","orcid":null},"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":"Chen Qu","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hamed Zamani","orcid":null},"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":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liu Yang","orcid":null},"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":"Liu Yang","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":null,"display_name":"W. Bruce Croft","orcid":null},"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":"W. Bruce Croft","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":null,"display_name":"Erik Learned-Miller","orcid":null},"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":"Erik Learned-Miller","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":null,"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":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1753","last_page":"1757"},"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":0.9965999722480774,"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":0.9962999820709229,"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":0.7955999970436096},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6489999890327454},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6026999950408936},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5870000123977661},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.545199990272522},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.44040000438690186},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4250999987125397},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.39579999446868896}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7955999970436096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7935000061988831},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6489999890327454},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6466000080108643},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6026999950408936},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5870000123977661},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.545199990272522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5404999852180481},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.44040000438690186},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.414000004529953},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.39579999446868896},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2992999851703644},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3404835.3462987","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3462987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.03938","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.03938","pdf_url":"https://arxiv.org/pdf/2105.03938","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,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.03938","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.03938","pdf_url":"https://arxiv.org/pdf/2105.03938","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,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337800","display_name":"Center for Intelligent Information Retrieval, University of Massachusetts Amherst","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2060494110","https://openalex.org/W2142192571","https://openalex.org/W2148972377","https://openalex.org/W2151498684","https://openalex.org/W2202226326","https://openalex.org/W2277195237","https://openalex.org/W2293453011","https://openalex.org/W2463565445","https://openalex.org/W2560730294","https://openalex.org/W2563399268","https://openalex.org/W2745461083","https://openalex.org/W2772833636","https://openalex.org/W2775221064","https://openalex.org/W2889792105","https://openalex.org/W2891394954","https://openalex.org/W2896457183","https://openalex.org/W2947312908","https://openalex.org/W2951434086","https://openalex.org/W2962749469","https://openalex.org/W2962808855","https://openalex.org/W2962985038","https://openalex.org/W2963383024","https://openalex.org/W2963398599","https://openalex.org/W2963477107","https://openalex.org/W2963748441","https://openalex.org/W2964303913","https://openalex.org/W2970231061","https://openalex.org/W3007672467","https://openalex.org/W3012707646","https://openalex.org/W3021282678","https://openalex.org/W3034303366","https://openalex.org/W3034654340","https://openalex.org/W3035454069","https://openalex.org/W3044175177","https://openalex.org/W3099700870","https://openalex.org/W3101703188","https://openalex.org/W3143415700","https://openalex.org/W3154189934","https://openalex.org/W6635985794","https://openalex.org/W6669996083","https://openalex.org/W6739901393","https://openalex.org/W6752083267"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,35],"address":[4],"multi-modal":[5,98],"information":[6],"needs":[7],"that":[8,64,104,111,124],"contain":[9],"text":[10],"questions":[11],"and":[12,51,59,71],"images":[13],"by":[14],"focusing":[15],"on":[16],"passage":[17,42],"retrieval":[18,48,106,110,117,123],"for":[19],"outside-knowledge":[20],"visual":[21,65],"question":[22,55],"answering.":[23],"This":[24],"task":[25],"requires":[26],"access":[27],"to":[28,37,74],"outside":[29],"knowledge,":[30],"which":[31],"in":[32,81],"our":[33],"case":[34],"define":[36],"be":[38,75],"a":[39,87,97],"large":[40],"unstructured":[41],"collection.":[43],"We":[44,62,84,101],"first":[45],"conduct":[46],"sparse":[47,82,109,122],"with":[49,56,91],"BM25":[50],"study":[52],"expanding":[53],"the":[54,92,119],"object":[57,79,113],"names":[58,80],"image":[60],"captions.":[61,127],"verify":[63],"clues":[66],"play":[67],"an":[68],"important":[69],"role":[70],"captions":[72],"tend":[73],"more":[76],"informative":[77],"than":[78],"retrieval.":[83],"then":[85],"construct":[86],"dual-encoder":[88],"dense":[89,105,116],"retriever,":[90],"query":[93],"encoder":[94],"being":[95],"LXMERT,":[96],"pre-trained":[99],"transformer.":[100],"further":[102],"show":[103],"significantly":[107],"outperforms":[108],"uses":[112],"expansion.":[114],"Moreover,":[115],"matches":[118],"performance":[120],"of":[121],"leverages":[125],"human-generated":[126]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2021-04-26T00:00:00"}