{"id":"https://openalex.org/W3160728318","doi":"https://doi.org/10.1109/icassp39728.2021.9414074","title":"Adaptive Re-Balancing Network with Gate Mechanism for Long-Tailed Visual Question Answering","display_name":"Adaptive Re-Balancing Network with Gate Mechanism for Long-Tailed Visual Question Answering","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160728318","doi":"https://doi.org/10.1109/icassp39728.2021.9414074","mag":"3160728318"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5115601817","display_name":"Hongyu Chen","orcid":"https://orcid.org/0000-0003-4888-0441"},"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":"Hongyu Chen","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023135578","display_name":"Ruifang Liu","orcid":"https://orcid.org/0000-0003-1801-6759"},"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":"Ruifang Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032465074","display_name":"Han Fang","orcid":"https://orcid.org/0000-0001-9635-9859"},"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":"Han Fang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101692351","display_name":"Ximing Zhang","orcid":"https://orcid.org/0000-0002-6400-6984"},"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":"Ximing Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5115601817"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.2882,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53898693,"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":"3605","last_page":"3609"},"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":0.9988999962806702,"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":0.9976999759674072,"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":0.8149967789649963},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.8112679719924927},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6423908472061157},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5912667512893677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.580525279045105},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5577890872955322},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4494679272174835},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4344802796840668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8149967789649963},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8112679719924927},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6423908472061157},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5912667512893677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.580525279045105},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5577890872955322},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4494679272174835},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4344802796840668},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1933349210","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2412393473","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2787119853","https://openalex.org/W2807935099","https://openalex.org/W2894842749","https://openalex.org/W2962731754","https://openalex.org/W2963383024","https://openalex.org/W2963403868","https://openalex.org/W2963938081","https://openalex.org/W2964072591","https://openalex.org/W2964345214","https://openalex.org/W2964760297","https://openalex.org/W2971183306","https://openalex.org/W2984814708","https://openalex.org/W2997531716","https://openalex.org/W3035651653","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6694395031","https://openalex.org/W6715144786","https://openalex.org/W6730531838","https://openalex.org/W6739901393","https://openalex.org/W6743068658","https://openalex.org/W6743157954","https://openalex.org/W6748581942","https://openalex.org/W6756259377","https://openalex.org/W6767988601"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W2354233396"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"is":[4,122,132],"a":[5,10,62,136],"challenging":[6],"task":[7],"which":[8,96],"requires":[9],"fine-grained":[11],"semantic":[12],"understanding":[13],"of":[14,71,160,166],"visual":[15,127],"and":[16,76,102],"textual":[17],"contents.":[18],"Existing":[19],"works":[20],"focus":[21],"on":[22,150],"better":[23],"modality":[24],"representations.":[25],"However,":[26],"these":[27],"methods":[28],"give":[29,141],"little":[30],"consideration":[31],"to":[32,48,68,90,140,144],"the":[33,98,105,110,120,158,167],"long-tailed":[34],"data":[35,107],"distribution":[36],"in":[37,51,56,73,119],"common":[38,151],"VQA":[39],"datasets.":[40],"The":[41,147],"extreme":[42],"class":[43],"imbalance":[44],"causes":[45],"training":[46,86],"bias":[47],"behave":[49],"well":[50],"head":[52,75],"class,":[53],"but":[54],"fail":[55],"tail":[57,77,106],"class.":[58],"Therefore,":[59],"we":[60],"propose":[61],"unified":[63],"Adaptive":[64],"Re-balancing":[65],"Network":[66],"(ARN)":[67],"take":[69],"care":[70],"classification":[72],"both":[74],"classes,":[78],"exhaustively":[79],"improving":[80],"performance":[81],"for":[82,124],"VQA.":[83],"Specifically,":[84],"two":[85],"branches":[87],"are":[88],"introduced":[89],"per-form":[91],"their":[92],"own":[93],"duty":[94],"iteratively,":[95],"learn":[97],"universal":[99],"representations":[100],"first":[101],"then":[103],"emphasize":[104],"progressively":[108],"by":[109],"re-balancing":[111],"branch":[112],"with":[113,135,164],"adaptive":[114],"learning.":[115],"Meanwhile,":[116],"contextual":[117,145],"information":[118],"question":[121],"vital":[123],"guiding":[125],"accurate":[126],"attention.":[128],"Thus":[129],"our":[130,161],"network":[131],"further":[133],"equipped":[134],"novel":[137],"gate":[138],"mechanism":[139],"higher":[142],"weight":[143],"information.":[146],"Experimental":[148],"results":[149],"benchmarks":[152],"such":[153],"as":[154],"VQA-v2":[155],"have":[156],"demonstrated":[157],"superiority":[159],"method":[162],"compared":[163],"state":[165],"art.":[168]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}