{"id":"https://openalex.org/W3015246548","doi":"https://doi.org/10.1109/icassp40776.2020.9053595","title":"Multi-Layer Content Interaction Through Quaternion Product for Visual Question Answering","display_name":"Multi-Layer Content Interaction Through Quaternion Product for Visual Question Answering","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015246548","doi":"https://doi.org/10.1109/icassp40776.2020.9053595","mag":"3015246548"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5052255801","display_name":"Lei Shi","orcid":"https://orcid.org/0000-0002-5570-7818"},"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lei Shi","raw_affiliation_strings":["Beijing University of Posts and Telecomminications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecomminications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080973846","display_name":"Shijie Geng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Shijie Geng","raw_affiliation_strings":["Rutgers University"],"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012633404","display_name":"Kai Shuang","orcid":"https://orcid.org/0000-0003-0917-3541"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Shuang","raw_affiliation_strings":["Beijing University of Posts and Telecomminications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecomminications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001601327","display_name":"Chiori Hori","orcid":"https://orcid.org/0000-0002-4201-7578"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chiori Hori","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL)"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL)","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102778496","display_name":"Songxiang Liu","orcid":"https://orcid.org/0000-0002-0943-2446"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Songxiang Liu","raw_affiliation_strings":["CUHK"],"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028272399","display_name":"Peng Gao","orcid":"https://orcid.org/0000-0003-2230-3937"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Peng Gao","raw_affiliation_strings":["CUHK"],"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036865453","display_name":"Sen Su","orcid":"https://orcid.org/0000-0003-4266-7527"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sen Su","raw_affiliation_strings":["Beijing University of Posts and Telecomminications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecomminications","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5052255801"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":1.2701,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.82089803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4412","last_page":"4416"},"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":0.9987999796867371,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9965000152587891,"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/computer-science","display_name":"Computer science","score":0.7719966173171997},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.7100602388381958},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5827171206474304},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5316216349601746},{"id":"https://openalex.org/keywords/quaternion","display_name":"Quaternion","score":0.520744800567627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5112855434417725},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5054426193237305},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4969210922718048},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.48428839445114136},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4610620439052582},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4228706955909729},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1121968924999237},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0747271180152893}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7719966173171997},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.7100602388381958},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5827171206474304},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5316216349601746},{"id":"https://openalex.org/C200127275","wikidata":"https://www.wikidata.org/wiki/Q173853","display_name":"Quaternion","level":2,"score":0.520744800567627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5112855434417725},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5054426193237305},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4969210922718048},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.48428839445114136},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4610620439052582},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4228706955909729},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1121968924999237},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0747271180152893},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1486649854","https://openalex.org/W1686810756","https://openalex.org/W1933349210","https://openalex.org/W2133564696","https://openalex.org/W2147527908","https://openalex.org/W2153579005","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2560730294","https://openalex.org/W2584992898","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2752782242","https://openalex.org/W2803747201","https://openalex.org/W2810643877","https://openalex.org/W2885156408","https://openalex.org/W2896457183","https://openalex.org/W2951527505","https://openalex.org/W2952383053","https://openalex.org/W2962739339","https://openalex.org/W2962835968","https://openalex.org/W2962916650","https://openalex.org/W2963176022","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963420686","https://openalex.org/W2963446712","https://openalex.org/W2963521239","https://openalex.org/W2963719423","https://openalex.org/W2964067226","https://openalex.org/W2964308564","https://openalex.org/W2966683369","https://openalex.org/W2966715458","https://openalex.org/W2970608575","https://openalex.org/W3002557610","https://openalex.org/W4294170691","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6629028937","https://openalex.org/W6637373629","https://openalex.org/W6679434410","https://openalex.org/W6682137061","https://openalex.org/W6682691769","https://openalex.org/W6739901393","https://openalex.org/W6742999658","https://openalex.org/W6750243331","https://openalex.org/W6752083267","https://openalex.org/W6752114883","https://openalex.org/W6755207826","https://openalex.org/W6766645339","https://openalex.org/W6766904570"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Multi-modality":[0],"fusion":[1,39],"technologies":[2],"have":[3],"greatly":[4],"improved":[5],"the":[6,24,32,42,49,52,69,85,91,97,126,133,153],"performance":[7,127],"of":[8,35,44,93,155],"neural":[9],"network-based":[10],"Video":[11],"Description/Caption,":[12],"Visual":[13,19],"Question":[14],"Answering":[15],"(VQA)":[16],"and":[17,116],"Audio":[18],"Scene-aware":[20],"Dialog":[21],"(AVSD)":[22],"over":[23],"recent":[25],"years.":[26],"Most":[27],"previous":[28],"approaches":[29],"only":[30,67],"explore":[31],"last":[33,70],"layers":[34,77,109,112],"multiple":[36],"layer":[37,71],"feature":[38],"while":[40],"omitting":[41],"importance":[43],"intermediate":[45,53,76],"layers.":[46],"To":[47],"solve":[48],"issue":[50],"for":[51,68,74,113],"layers,":[54],"we":[55,83],"propose":[56],"an":[57],"efficient":[58],"Quaternion":[59],"Block":[60],"Network":[61],"(QBN)":[62],"to":[63,89,110,151],"learn":[64],"interaction":[65],"not":[66],"but":[72],"also":[73],"all":[75],"simultaneously.":[78],"In":[79,96],"our":[80,123],"proposed":[81,157],"QBN,":[82],"use":[84],"holistic":[86],"text":[87,117],"features":[88],"guide":[90],"update":[92],"visual":[94,115,140],"features.":[95],"meantime,":[98],"Hamilton":[99],"quaternion":[100],"products":[101],"can":[102],"efficiently":[103],"perform":[104],"information":[105],"flow":[106],"from":[107],"higher":[108],"lower":[111],"both":[114],"modalities.":[118],"The":[119],"evaluation":[120],"results":[121],"show":[122],"QBN":[124],"improve":[125],"on":[128],"VQA":[129],"2.0,":[130],"furthermore":[131],"surpasses":[132],"approach":[134],"using":[135],"large":[136],"scale":[137],"BERT":[138,141],"or":[139],"pre-trained":[142],"models.":[143],"Extensive":[144],"ablation":[145],"study":[146],"has":[147],"been":[148],"carried":[149],"out":[150],"examine":[152],"influence":[154],"each":[156],"module":[158],"in":[159],"this":[160],"study.":[161]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}