{"id":"https://openalex.org/W2953016680","doi":"https://doi.org/10.1109/tpami.2018.2890628","title":"Focal Visual-Text Attention for Memex Question Answering","display_name":"Focal Visual-Text Attention for Memex Question Answering","publication_year":2019,"publication_date":"2019-01-09","ids":{"openalex":"https://openalex.org/W2953016680","doi":"https://doi.org/10.1109/tpami.2018.2890628","mag":"2953016680","pmid":"https://pubmed.ncbi.nlm.nih.gov/30624212"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2018.2890628","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2018.2890628","pdf_url":"https://ieeexplore.ieee.org/ielx7/34/8752185/08603827.pdf","source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/34/8752185/08603827.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059207044","display_name":"Junwei Liang","orcid":"https://orcid.org/0000-0003-2219-5569"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Junwei Liang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090730336","display_name":"Lu Jiang","orcid":"https://orcid.org/0000-0003-0286-8439"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu Jiang","raw_affiliation_strings":["Google AI, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google AI, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103187717","display_name":"Liangliang Cao","orcid":"https://orcid.org/0000-0003-0900-1512"},"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":"Liangliang Cao","raw_affiliation_strings":["University of Massachusetts, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042126127","display_name":"Yannis Kalantidis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yannis Kalantidis","raw_affiliation_strings":["Facebook Research, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Research, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009049500","display_name":"Li-Jia Li","orcid":"https://orcid.org/0000-0001-5850-7013"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li-Jia Li","raw_affiliation_strings":["Google AI, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google AI, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107836252","display_name":"Alexander G. Hauptmann","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander G. Hauptmann","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5059207044"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":5.2104,"has_fulltext":true,"cited_by_count":75,"citation_normalized_percentile":{"value":0.96446869,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"41","issue":"8","first_page":"1893","last_page":"1908"},"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":0.9955000281333923,"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/question-answering","display_name":"Question answering","score":0.9453444480895996},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8199265599250793},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7594899535179138},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6019587516784668},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5649877190589905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4752618670463562},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44269460439682007},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3425794839859009},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.23794305324554443}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.9453444480895996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8199265599250793},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7594899535179138},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6019587516784668},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5649877190589905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4752618670463562},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44269460439682007},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3425794839859009},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23794305324554443},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2018.2890628","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2018.2890628","pdf_url":"https://ieeexplore.ieee.org/ielx7/34/8752185/08603827.pdf","source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:30624212","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30624212","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:1806.01873","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.01873","pdf_url":"https://arxiv.org/pdf/1806.01873","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"doi:10.1109/tpami.2018.2890628","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2018.2890628","pdf_url":"https://ieeexplore.ieee.org/ielx7/34/8752185/08603827.pdf","source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1732624909","display_name":null,"funder_award_id":"D17PC00340","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"},{"id":"https://openalex.org/G4723519231","display_name":null,"funder_award_id":"60NANB17D156","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"},{"id":"https://openalex.org/G6256855654","display_name":null,"funder_award_id":"60NANB17D156","funder_id":"https://openalex.org/F4320332178","funder_display_name":"National Institute of Standards and Technology"},{"id":"https://openalex.org/G6657070506","display_name":null,"funder_award_id":"60NANB17D156","funder_id":"https://openalex.org/F4320306111","funder_display_name":"U.S. Department of Commerce"}],"funders":[{"id":"https://openalex.org/F4320306111","display_name":"U.S. Department of Commerce","ror":"https://ror.org/04chq2495"},{"id":"https://openalex.org/F4320308380","display_name":"Yale University","ror":"https://ror.org/03v76x132"},{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320333452","display_name":"Interior Business Center","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2953016680.pdf","grobid_xml":"https://content.openalex.org/works/W2953016680.grobid-xml"},"referenced_works_count":96,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1500258577","https://openalex.org/W1544827683","https://openalex.org/W1575833922","https://openalex.org/W1832693441","https://openalex.org/W1933349210","https://openalex.org/W1986414721","https://openalex.org/W1999970330","https://openalex.org/W2015720094","https://openalex.org/W2018506599","https://openalex.org/W2062230193","https://openalex.org/W2063222491","https://openalex.org/W2137569015","https://openalex.org/W2141080726","https://openalex.org/W2142192571","https://openalex.org/W2145033823","https://openalex.org/W2155162820","https://openalex.org/W2189070436","https://openalex.org/W2202226326","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2288052783","https://openalex.org/W2293453011","https://openalex.org/W2463565445","https://openalex.org/W2474097899","https://openalex.org/W2516930406","https://openalex.org/W2521709538","https://openalex.org/W2546696630","https://openalex.org/W2551396370","https://openalex.org/W2556553881","https://openalex.org/W2558681897","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2585370664","https://openalex.org/W2597425697","https://openalex.org/W2606982687","https://openalex.org/W2735159761","https://openalex.org/W2743109345","https://openalex.org/W2745461083","https://openalex.org/W2765716052","https://openalex.org/W2774005037","https://openalex.org/W2796207103","https://openalex.org/W2798786641","https://openalex.org/W2949615363","https://openalex.org/W2950697717","https://openalex.org/W2950761309","https://openalex.org/W2951528484","https://openalex.org/W2951619830","https://openalex.org/W2962684798","https://openalex.org/W2962749469","https://openalex.org/W2962884579","https://openalex.org/W2962910007","https://openalex.org/W2963051286","https://openalex.org/W2963080779","https://openalex.org/W2963143606","https://openalex.org/W2963176022","https://openalex.org/W2963191264","https://openalex.org/W2963383024","https://openalex.org/W2963420691","https://openalex.org/W2963466731","https://openalex.org/W2963579811","https://openalex.org/W2963622213","https://openalex.org/W2963644680","https://openalex.org/W2963656855","https://openalex.org/W2963668159","https://openalex.org/W2963717374","https://openalex.org/W2963748441","https://openalex.org/W2963781647","https://openalex.org/W2963890755","https://openalex.org/W2963954913","https://openalex.org/W2964118342","https://openalex.org/W2964138017","https://openalex.org/W2964303913","https://openalex.org/W2964350391","https://openalex.org/W3023993913","https://openalex.org/W3087871082","https://openalex.org/W4298392976","https://openalex.org/W6600284362","https://openalex.org/W6630085304","https://openalex.org/W6632455782","https://openalex.org/W6634232107","https://openalex.org/W6637623960","https://openalex.org/W6680303927","https://openalex.org/W6682086655","https://openalex.org/W6686883664","https://openalex.org/W6692004142","https://openalex.org/W6694260854","https://openalex.org/W6697449767","https://openalex.org/W6718553084","https://openalex.org/W6719057275","https://openalex.org/W6726253136","https://openalex.org/W6729654139","https://openalex.org/W6730073950","https://openalex.org/W6742232253","https://openalex.org/W6746518932","https://openalex.org/W6750041603"],"related_works":["https://openalex.org/W2058118494","https://openalex.org/W2392768766","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2010935248","https://openalex.org/W2768810474"],"abstract_inverted_index":{"Recent":[0],"insights":[1],"on":[2,26,158,169,187],"language":[3],"and":[4,153,180],"vision":[5],"with":[6,41],"neural":[7],"networks":[8],"have":[9,35],"been":[10],"successfully":[11],"applied":[12],"to":[13,20,36,64,83,94,148,156,163],"simple":[14],"single-image":[15],"visual":[16],"question":[17,23,126],"answering.":[18],"However,":[19],"tackle":[21],"real-life":[22],"answering":[24,127],"problems":[25],"multimedia":[27],"collections":[28,40],"such":[29],"as":[30,103],"personal":[31,132],"photo":[32,133],"albums,":[33],"we":[34,115],"look":[37],"at":[38],"whole":[39],"sequences":[42],"of":[43,56,130,144],"photos.":[44,80],"This":[45],"paper":[46],"proposes":[47],"a":[48,54,59,84,87,145],"new":[49],"multimodal":[50,125],"MemexQA":[51,119,171],"task:":[52],"given":[53,93],"sequence":[55],"photos":[57,90,100,186],"from":[58],"user,":[60],"the":[61,96,109,113,118,121,160,165,170,182],"goal":[62],"is":[63],"automatically":[65],"answer":[66,164],"questions":[67],"that":[68,141,174],"help":[69,105],"users":[70,106],"recover":[71],"their":[72],"memory":[73],"about":[74],"an":[75,137],"event":[76],"captured":[77],"in":[78,159],"these":[79],"In":[81],"addition":[82],"text":[85],"answer,":[86],"few":[88],"grounding":[89,99,185],"are":[91,101],"also":[92],"justify":[95],"answer.":[97,110],"The":[98],"necessary":[102],"they":[104],"quickly":[107],"verifying":[108],"Towards":[111],"solving":[112],"task,":[114],"1)":[116],"present":[117],"dataset,":[120],"first":[122],"publicly":[123],"available":[124],"dataset":[128,172],"consisting":[129],"real":[131],"albums;":[134],"2)":[135],"propose":[136],"end-to-end":[138],"trainable":[139],"network":[140],"makes":[142],"use":[143],"hierarchical":[146],"process":[147],"dynamically":[149],"determine":[150],"what":[151,154],"media":[152],"time":[155],"focus":[157],"sequential":[161],"data":[162],"question.":[166],"Experimental":[167],"results":[168],"demonstrate":[173],"our":[175],"model":[176],"outperforms":[177],"strong":[178],"baselines":[179],"yields":[181],"most":[183],"relevant":[184],"this":[188],"challenging":[189],"task.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}