{"id":"https://openalex.org/W4327808595","doi":"https://doi.org/10.1109/tmm.2023.3254205","title":"Bilaterally Slimmable Transformer for Elastic and Efficient Visual Question Answering","display_name":"Bilaterally Slimmable Transformer for Elastic and Efficient Visual Question Answering","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4327808595","doi":"https://doi.org/10.1109/tmm.2023.3254205"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3254205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3254205","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-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/A5061025828","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0001-8407-1137"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Yu","raw_affiliation_strings":["School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8407-1137","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031451585","display_name":"Zitian Jin","orcid":"https://orcid.org/0009-0004-7419-049X"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zitian Jin","raw_affiliation_strings":["HDU-ITMO Joint Institute, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-7419-049X","affiliations":[{"raw_affiliation_string":"HDU-ITMO Joint Institute, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050817770","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0003-1922-7283"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1922-7283","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081346568","display_name":"Mingliang Xu","orcid":"https://orcid.org/0000-0002-6885-3451"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingliang Xu","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6885-3451","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395737","display_name":"Hongbo Wang","orcid":"https://orcid.org/0000-0001-5003-3124"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbo Wang","raw_affiliation_strings":["School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5003-3124","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100728569","display_name":"Jianping Fan","orcid":"https://orcid.org/0000-0003-2290-1785"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianping Fan","raw_affiliation_strings":["AI Lab at Lenovo Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2290-1785","affiliations":[{"raw_affiliation_string":"AI Lab at Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.4749,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.57717906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"25","issue":null,"first_page":"9543","last_page":"9556"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.989799976348877,"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":0.9887999892234802,"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/transformer","display_name":"Transformer","score":0.6829321384429932},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6570496559143066},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.6024706959724426},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5866671800613403},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.5718319416046143},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.4669526517391205},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4489190876483917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4034835398197174},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39341893792152405},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.33756130933761597},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2061673402786255},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.17774003744125366},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.13542145490646362},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09040254354476929}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6829321384429932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6570496559143066},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.6024706959724426},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5866671800613403},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.5718319416046143},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.4669526517391205},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4489190876483917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4034835398197174},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39341893792152405},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.33756130933761597},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2061673402786255},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.17774003744125366},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.13542145490646362},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09040254354476929},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3254205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3254205","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6151690139","display_name":null,"funder_award_id":"62020106007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6570941292","display_name":null,"funder_award_id":"62125201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7336325476","display_name":"\u5916\u90e8\u201c\u6570\u636e-\u77e5\u8bc6\u201d\u8054\u5408\u589e\u5f3a\u7684\u89c6\u89c9\u95ee\u7b54\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62072147","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7528510259","display_name":"\u57fa\u4e8e\u5927\u89c4\u6a21\u8de8\u5a92\u4f53\u77e5\u8bc6\u7f51\u7edc\u7684\u590d\u6742\u89c6\u9891\u95ee\u7b54\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61836002","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":84,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2279098554","https://openalex.org/W2331143823","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2924902521","https://openalex.org/W2962851801","https://openalex.org/W2962944050","https://openalex.org/W2963125010","https://openalex.org/W2963150162","https://openalex.org/W2963176022","https://openalex.org/W2963215144","https://openalex.org/W2963383024","https://openalex.org/W2963518342","https://openalex.org/W2963954913","https://openalex.org/W2964067226","https://openalex.org/W2964345792","https://openalex.org/W2965373594","https://openalex.org/W2966683369","https://openalex.org/W2968543045","https://openalex.org/W2970106668","https://openalex.org/W2970231061","https://openalex.org/W2978017171","https://openalex.org/W2981165461","https://openalex.org/W2981698279","https://openalex.org/W3005881764","https://openalex.org/W3034457371","https://openalex.org/W3035030897","https://openalex.org/W3035251378","https://openalex.org/W3035265375","https://openalex.org/W3035281298","https://openalex.org/W3087975588","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3092767330","https://openalex.org/W3096609285","https://openalex.org/W3105232955","https://openalex.org/W3113709932","https://openalex.org/W3168640669","https://openalex.org/W3173909648","https://openalex.org/W3195963939","https://openalex.org/W3207798279","https://openalex.org/W4210820868","https://openalex.org/W4285200267","https://openalex.org/W4288089799","https://openalex.org/W4297775537","https://openalex.org/W4312784228","https://openalex.org/W6638523607","https://openalex.org/W6677580257","https://openalex.org/W6687239747","https://openalex.org/W6695314431","https://openalex.org/W6719057275","https://openalex.org/W6728881024","https://openalex.org/W6737664043","https://openalex.org/W6739901393","https://openalex.org/W6752083267","https://openalex.org/W6753640285","https://openalex.org/W6755207826","https://openalex.org/W6757036269","https://openalex.org/W6760732026","https://openalex.org/W6764409202","https://openalex.org/W6766673545","https://openalex.org/W6766904570","https://openalex.org/W6767064347","https://openalex.org/W6767211374","https://openalex.org/W6767494712","https://openalex.org/W6768021236","https://openalex.org/W6768080748","https://openalex.org/W6768851824","https://openalex.org/W6769627184","https://openalex.org/W6773815586","https://openalex.org/W6775706467","https://openalex.org/W6780226713","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6798350552","https://openalex.org/W6798805250","https://openalex.org/W6811013733","https://openalex.org/W6839015040"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W4381094582","https://openalex.org/W1978893398","https://openalex.org/W1977906818","https://openalex.org/W2201908702","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1522139108","https://openalex.org/W4381058564","https://openalex.org/W2964413124"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,163],"Transformer":[3,79],"architectures":[4],"[1]":[5],"have":[6],"brought":[7],"remarkable":[8],"improvements":[9],"to":[10,24,51,63,94,192],"visual":[11],"question":[12],"answering":[13],"(VQA).":[14],"Nevertheless,":[15],"Transformer-based":[16,91,128],"VQA":[17,55,92,129],"models":[18,93],"are":[19],"usually":[20],"deep":[21],"and":[22,37,100,108,114,136,139,166,184],"wide":[23],"guarantee":[25],"good":[26],"performance,":[27],"so":[28],"they":[29],"can":[30,85],"only":[31,180],"run":[32,39],"on":[33,40,143,157,195],"powerful":[34],"GPU":[35],"servers":[36],"cannot":[38],"capacity-restricted":[41],"platforms":[42],"such":[43],"as":[44],"mobile":[45,197],"phones.":[46],"Therefore,":[47],"it":[48,190,194],"is":[49],"desirable":[50],"learn":[52],"an":[53],"elastic":[54],"model":[56,98,164],"that":[57,84],"supports":[58],"adaptive":[59],"pruning":[60],"at":[61],"runtime":[62],"meet":[64],"the":[65,76,112,121,172],"efficiency":[66],"constraints":[67],"of":[68,105,116],"different":[69,106],"platforms.":[70],"To":[71,110],"this":[72,117],"end,":[73],"we":[74,119],"present":[75],"bilaterally":[77],"slimmable":[78],"(BST),":[80],"a":[81,96,196],"general":[82],"framework":[83,124],"be":[86],"seamlessly":[87],"integrated":[88],"into":[89],"arbitrary":[90],"train":[95],"single":[97],"once":[99],"obtain":[101],"various":[102],"slimmed":[103,151],"submodels":[104],"widths":[107],"depths.":[109],"verify":[111],"effectiveness":[113],"generality":[115],"method,":[118],"integrate":[120],"proposed":[122],"BST":[123],"with":[125,199],"three":[126],"typical":[127],"approaches,":[130],"namely":[131],"MCAN":[132,174],"[2],":[133],"UNITER":[134],"[3],":[135],"CLIP-ViL":[137],"[4],":[138],"conduct":[140],"extensive":[141],"experiments":[142],"two":[144],"commonly-used":[145],"benchmark":[146],"datasets.":[147],"In":[148],"particular,":[149],"one":[150],"MCAN$_\\mathsf":[152,178],"{BST}$submodel":[153,179],"achieves":[154],"comparable":[155],"accuracy":[156],"VQA-v2,":[158],"while":[159],"being":[160],"0.38\u00d7":[161],"smaller":[162],"size":[165],"having":[167],"0.27\u00d7":[168],"fewer":[169],"FLOPs":[170,186],"than":[171,201],"reference":[173],"model.":[175],"The":[176],"smallest":[177],"has":[181],"9M":[182],"parameters":[183],"0.16G":[185],"during":[187],"inference,":[188],"making":[189],"possible":[191],"deploy":[193],"device":[198],"less":[200],"60":[202],"ms":[203],"latency.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}