{"id":"https://openalex.org/W3206384369","doi":"https://doi.org/10.1145/3474085.3481540","title":"Unifying Multimodal Transformer for Bi-directional Image and Text Generation","display_name":"Unifying Multimodal Transformer for Bi-directional Image and Text Generation","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206384369","doi":"https://doi.org/10.1145/3474085.3481540","mag":"3206384369"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3481540","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3481540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.09753","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067298679","display_name":"Yupan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yupan Huang","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110819662","display_name":"Hongwei Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwei Xue","raw_affiliation_strings":["University of Science and Technology of China, Feihe, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Feihe, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378248","display_name":"Bei Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bei Liu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101633465","display_name":"Yutong Lu","orcid":"https://orcid.org/0000-0001-5315-3375"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Lu","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1138","last_page":"1147"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9965999722480774,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9886000156402588,"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":0.7811493873596191},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7683387398719788},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5827906727790833},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5142157077789307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46224120259284973},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4238909184932709},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40554094314575195},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33999305963516235},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.1080751121044159},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1005505919456482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7811493873596191},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7683387398719788},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5827906727790833},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5142157077789307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46224120259284973},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4238909184932709},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40554094314575195},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33999305963516235},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.1080751121044159},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1005505919456482},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3474085.3481540","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3481540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2110.09753","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.09753","pdf_url":"https://arxiv.org/pdf/2110.09753","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.09753","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.09753","pdf_url":"https://arxiv.org/pdf/2110.09753","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W1959608418","https://openalex.org/W2099471712","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2176263492","https://openalex.org/W2183341477","https://openalex.org/W2277195237","https://openalex.org/W2331128040","https://openalex.org/W2405756170","https://openalex.org/W2423557781","https://openalex.org/W2432004435","https://openalex.org/W2506483933","https://openalex.org/W2547875792","https://openalex.org/W2557449848","https://openalex.org/W2563399268","https://openalex.org/W2564591810","https://openalex.org/W2600463316","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2782980316","https://openalex.org/W2795151422","https://openalex.org/W2803775694","https://openalex.org/W2890531016","https://openalex.org/W2892181857","https://openalex.org/W2896457183","https://openalex.org/W2921737854","https://openalex.org/W2931831966","https://openalex.org/W2949999304","https://openalex.org/W2950761309","https://openalex.org/W2951140085","https://openalex.org/W2952342379","https://openalex.org/W2953106684","https://openalex.org/W2962845008","https://openalex.org/W2962968665","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963248296","https://openalex.org/W2963373786","https://openalex.org/W2963403868","https://openalex.org/W2963966654","https://openalex.org/W2963981733","https://openalex.org/W2964024144","https://openalex.org/W2964121744","https://openalex.org/W2965597639","https://openalex.org/W2966715458","https://openalex.org/W2966792645","https://openalex.org/W2968549119","https://openalex.org/W2969862959","https://openalex.org/W2970231061","https://openalex.org/W2970608575","https://openalex.org/W2982450728","https://openalex.org/W2986670728","https://openalex.org/W2988975212","https://openalex.org/W2990069284","https://openalex.org/W2990818246","https://openalex.org/W2997591391","https://openalex.org/W3000433013","https://openalex.org/W3014611590","https://openalex.org/W3016923549","https://openalex.org/W3034655362","https://openalex.org/W3035497460","https://openalex.org/W3089089004","https://openalex.org/W3091588028","https://openalex.org/W3103651098","https://openalex.org/W3104152799","https://openalex.org/W3129576130","https://openalex.org/W3135367836","https://openalex.org/W3153469116","https://openalex.org/W3165647589","https://openalex.org/W3166396011","https://openalex.org/W3184784418","https://openalex.org/W4289542422","https://openalex.org/W4296979096","https://openalex.org/W4301206121","https://openalex.org/W4320013936","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W936373746","https://openalex.org/W2975817033","https://openalex.org/W4382701072","https://openalex.org/W4256502920"],"abstract_inverted_index":{"We":[0,53,96],"study":[1,49],"the":[2,50,88,108,147],"joint":[3],"learning":[4],"of":[5,85],"image-to-text":[6,144],"and":[7,64,80,87,103,134],"text-to-image":[8,132],"generations,":[9],"which":[10,26],"are":[11],"naturally":[12],"bi-directional":[13,51],"tasks.":[14,52],"Typical":[15],"existing":[16],"works":[17],"design":[18,29],"two":[19],"separate":[20],"task-specific":[21],"models":[22],"for":[23,60,131,142],"each":[24],"task,":[25],"impose":[27],"expensive":[28],"efforts.":[30],"In":[31],"this":[32],"work,":[33],"we":[34,68,77],"propose":[35,98],"a":[36,43],"unified":[37,58,83,110],"image-and-text":[38],"generative":[39],"framework":[40],"based":[41],"on":[42,146],"single":[44],"multimodal":[45,91],"model":[46,121],"to":[47,93,106,126,140],"jointly":[48],"adopt":[54],"Transformer":[55,89],"as":[56,72,82],"our":[57,115],"architecture":[59],"its":[61],"strong":[62],"performance":[63],"task-agnostic":[65],"design.":[66],"Specifically,":[67],"formulate":[69],"both":[70],"tasks":[71],"sequence":[73],"generation":[74,145],"tasks,":[75],"where":[76],"represent":[78],"images":[79],"text":[81],"sequences":[84],"tokens,":[86],"learns":[90],"interactions":[92],"generate":[94],"sequences.":[95],"further":[97],"two-level":[99],"granularity":[100],"feature":[101],"representations":[102],"sequence-level":[104],"training":[105],"improve":[107],"Transformer-based":[109,120],"framework.":[111],"Experiments":[112],"show":[113],"that":[114],"approach":[116],"significantly":[117],"improves":[118,135],"previous":[119],"X-LXMERT's":[122],"FID":[123],"from":[124,138],"37.0":[125],"29.9":[127],"(lower":[128],"is":[129,152],"better)":[130],"generation,":[133],"CIDEr-D":[136],"score":[137],"100.9%":[139],"122.6%":[141],"fine-tuned":[143],"MS-COCO":[148],"dataset.":[149],"Our":[150],"code":[151],"available":[153],"online.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-10-25T00:00:00"}