{"id":"https://openalex.org/W4293524578","doi":"https://doi.org/10.1109/icme52920.2022.9859639","title":"Multi-Head Attention Fusion Network for Visual Question Answering","display_name":"Multi-Head Attention Fusion Network for Visual Question Answering","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293524578","doi":"https://doi.org/10.1109/icme52920.2022.9859639"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859639","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100392409","display_name":"Haiyang Zhang","orcid":"https://orcid.org/0000-0002-3025-9609"},"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":"Haiyang Zhang","raw_affiliation_strings":["School of computer science, Beijing University of Posts and Telecommunications,Beijing,China","School of computer science, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of computer science, Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of computer science, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100713350","display_name":"Ruoyu Li","orcid":"https://orcid.org/0000-0003-0754-2817"},"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":"Ruoyu Li","raw_affiliation_strings":["School of computer science, Beijing University of Posts and Telecommunications,Beijing,China","School of computer science, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of computer science, Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of computer science, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100322368","display_name":"Liang Liu","orcid":"https://orcid.org/0000-0002-5040-2468"},"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":"Liang Liu","raw_affiliation_strings":["School of computer science, Beijing University of Posts and Telecommunications,Beijing,China","School of computer science, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of computer science, Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of computer science, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.5548,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75462555,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9979000091552734,"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":0.9976000189781189,"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":0.834458589553833},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8183281421661377},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7253282070159912},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6710810661315918},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6705530881881714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6367784738540649},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6273047924041748},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5370003581047058},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5312478542327881},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4621264636516571},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4548436403274536},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41418272256851196},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34478336572647095},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.05845370888710022}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.834458589553833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8183281421661377},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7253282070159912},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6710810661315918},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6705530881881714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6367784738540649},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6273047924041748},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5370003581047058},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5312478542327881},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4621264636516571},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4548436403274536},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41418272256851196},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34478336572647095},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.05845370888710022},{"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},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859639","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8125674608","display_name":null,"funder_award_id":"62061146002,61921003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1933349210","https://openalex.org/W2053101950","https://openalex.org/W2194775991","https://openalex.org/W2463565445","https://openalex.org/W2546696630","https://openalex.org/W2553418567","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2949197413","https://openalex.org/W2953106684","https://openalex.org/W2963150162","https://openalex.org/W2963176022","https://openalex.org/W2963191264","https://openalex.org/W2963383024","https://openalex.org/W2963521239","https://openalex.org/W2963954913","https://openalex.org/W2964067226","https://openalex.org/W2966683369","https://openalex.org/W2970972665","https://openalex.org/W3009971095","https://openalex.org/W3035497460","https://openalex.org/W3199396412","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6630875275","https://openalex.org/W6719057275","https://openalex.org/W6728881024","https://openalex.org/W6729948091","https://openalex.org/W6739901393","https://openalex.org/W6742823334","https://openalex.org/W6750243331","https://openalex.org/W6752083267","https://openalex.org/W6767287485"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W2387743295","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W2086519370"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"is":[4],"a":[5,67],"challenging":[6],"task":[7],"to":[8,13,23,46,52,57,82,112,122],"answer":[9],"questions":[10],"with":[11,79],"respect":[12],"the":[14,29,35,38,55,63,84,90,98,124,129],"image.":[15],"Most":[16],"approaches":[17],"concentrate":[18],"on":[19,25,128],"utilizing":[20],"attention":[21,39,69,108],"networks":[22],"focus":[24],"crucial":[26],"objects":[27],"of":[28,34,41,54,92,100,131],"image":[30],"and":[31,86,97,116],"key":[32],"words":[33],"question.":[36],"However,":[37],"distribution":[40,109],"these":[42],"prior":[43],"attempts":[44],"tends":[45],"lo-cate":[47],"similar":[48],"regions,":[49],"which":[50,73],"leads":[51],"lack":[53],"ability":[56],"derive":[58],"important":[59],"entities.":[60],"To":[61],"address":[62],"issue,":[64],"we":[65],"propose":[66],"multi-head":[68],"fusion":[70,78],"network":[71],"(MHAFN),":[72],"can":[74,104],"achieve":[75],"hierarchical":[76],"multimodal":[77],"various":[80],"branches":[81],"capture":[83,106],"fine-grained":[85],"intricate":[87],"relationship":[88],"in":[89],"perspective":[91],"multiple":[93,113],"levels:":[94],"word,":[95],"region":[96],"interaction":[99],"them.":[101],"Furthermore,":[102],"it":[103],"also":[105],"distinct":[107],"for":[110],"attending":[111],"different":[114],"visual":[115],"textual":[117],"components":[118],"that":[119,135],"are":[120],"vital":[121],"infer":[123],"answer.":[125],"Extensive":[126],"ex-periments":[127],"benchmark":[130],"VQA-v2":[132],"dataset":[133],"demonstrate":[134],"MHAFN":[136],"significantly":[137],"outperforms":[138],"previous":[139],"methods.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}