{"id":"https://openalex.org/W2808193342","doi":"https://doi.org/10.1145/3206025.3206054","title":"Visual Question Answering With a Hybrid Convolution Recurrent Model","display_name":"Visual Question Answering With a Hybrid Convolution Recurrent Model","publication_year":2018,"publication_date":"2018-06-05","ids":{"openalex":"https://openalex.org/W2808193342","doi":"https://doi.org/10.1145/3206025.3206054","mag":"2808193342"},"language":"en","primary_location":{"id":"doi:10.1145/3206025.3206054","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3206025.3206054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/61104/icmr2018.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072670235","display_name":"Philipp Harzig","orcid":null},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Harzig","raw_affiliation_strings":["University of Augsburg, Augsburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Augsburg, Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007553837","display_name":"Christian Eggert","orcid":null},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Eggert","raw_affiliation_strings":["University of Augsburg, Augsburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Augsburg, Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009744749","display_name":"Rainer Lienhart","orcid":"https://orcid.org/0000-0003-4007-6889"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rainer Lienhart","raw_affiliation_strings":["University of Augsburg, Augsburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Augsburg, Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I179225836"],"apc_list":null,"apc_paid":null,"fwci":0.318,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61742107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"318","last_page":"325"},"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":0.9984999895095825,"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":0.9966999888420105,"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":0.9335861206054688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7778422236442566},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6842652559280396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.662026584148407},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6605610251426697},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5967597365379333},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5652661323547363},{"id":"https://openalex.org/keywords/questions-and-answers","display_name":"Questions and answers","score":0.4551023542881012},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.43604832887649536},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42952680587768555},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.41870689392089844},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.39248690009117126},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.364322692155838},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34189724922180176}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.9335861206054688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778422236442566},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6842652559280396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.662026584148407},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6605610251426697},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5967597365379333},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5652661323547363},{"id":"https://openalex.org/C3019144022","wikidata":"https://www.wikidata.org/wiki/Q4124998","display_name":"Questions and answers","level":2,"score":0.4551023542881012},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.43604832887649536},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42952680587768555},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.41870689392089844},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39248690009117126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.364322692155838},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34189724922180176},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3206025.3206054","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3206025.3206054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:61104","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-611041","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/61104/icmr2018.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":{"id":"pmh:oai:uni-augsburg.opus-bayern.de:61104","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-611041","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/61104/icmr2018.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2808193342.pdf","grobid_xml":"https://content.openalex.org/works/W2808193342.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1687846465","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W1934863104","https://openalex.org/W2064675550","https://openalex.org/W2117539524","https://openalex.org/W2183341477","https://openalex.org/W2190656909","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2302255633","https://openalex.org/W2402144811","https://openalex.org/W2463955103","https://openalex.org/W2525778437","https://openalex.org/W2560730294","https://openalex.org/W2567070169","https://openalex.org/W2613718673","https://openalex.org/W2613904329","https://openalex.org/W2745132836","https://openalex.org/W2963150162","https://openalex.org/W2963383024","https://openalex.org/W2963758027"],"related_works":["https://openalex.org/W2964954556","https://openalex.org/W3019910406","https://openalex.org/W2118632115","https://openalex.org/W2555213299","https://openalex.org/W2576107865","https://openalex.org/W3215363805","https://openalex.org/W1846393350","https://openalex.org/W4307481286","https://openalex.org/W4226441484","https://openalex.org/W2577658701"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"is":[4],"a":[5,21,40,67,80,98,119],"relatively":[6],"new":[7],"task,":[8],"which":[9,110,141],"tries":[10],"to":[11,89,113,118,135],"infer":[12,75],"answer":[13,38,76,115],"sentences":[14,77],"for":[15,93],"an":[16,104,125],"input":[17,121],"image":[18,122],"coupled":[19],"with":[20,152],"corresponding":[22],"question.":[23],"Instead":[24],"of":[25,43,53,64,100,155,161],"dynamically":[26,90,114],"generating":[27],"answers,":[28,57,140],"they":[29],"are":[30,133,142],"usually":[31],"inferred":[32],"by":[33,78,123,145],"finding":[34,54],"the":[35,51,61,153],"most":[36],"probable":[37],"from":[39],"fixed":[41],"set":[42],"possible":[44,56],"answers.":[45],"Previous":[46],"work":[47],"did":[48],"not":[49,143],"address":[50],"problem":[52],"all":[55],"but":[58],"only":[59],"modeled":[60],"answering":[62],"part":[63],"VQA":[65],"as":[66],"classification":[68,146],"task.":[69],"To":[70],"tackle":[71],"this":[72,130],"problem,":[73],"we":[74,102,132],"using":[79,124],"Long":[81],"Short-Term":[82],"Memory":[83],"(LSTM)":[84],"network":[85],"that":[86,159],"allows":[87,111],"us":[88,112],"generate":[91,136],"answers":[92,151,158],"(image,":[94],"question)":[95],"pairs.":[96],"In":[97],"series":[99],"experiments,":[101],"discover":[103],"end-to-end":[105],"Deep":[106],"Neural":[107],"Network":[108],"structure,":[109],"questions":[116],"referring":[117],"given":[120],"LSTM":[126],"decoder":[127],"network.":[128],"With":[129],"approach,":[131],"able":[134],"both":[137],"less":[138],"common":[139],"considered":[144],"models,":[147],"and":[148],"more":[149,162],"complex":[150],"appearance":[154],"datasets":[156],"containing":[157],"consist":[160],"than":[163],"three":[164],"words.":[165]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}