{"id":"https://openalex.org/W4409310662","doi":"https://doi.org/10.26599/cvm.2025.9450377","title":"Text to Image Generation with Bidirectional Multiway Transformers","display_name":"Text to Image Generation with Bidirectional Multiway Transformers","publication_year":2025,"publication_date":"2025-04-01","ids":{"openalex":"https://openalex.org/W4409310662","doi":"https://doi.org/10.26599/cvm.2025.9450377"},"language":"en","primary_location":{"id":"doi:10.26599/cvm.2025.9450377","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450377","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.26599/cvm.2025.9450377","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053932343","display_name":"Hangbo Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangbo Bao","raw_affiliation_strings":["Harbin Institute of Technology,Department of Computer Science and Technology,Harbin,China,150001","Department of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Department of Computer Science and Technology,Harbin,China,150001","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100771361","display_name":"Li Dong","orcid":"https://orcid.org/0000-0003-2002-8249"},"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":"Li Dong","raw_affiliation_strings":["Microsoft Research Asia,Beijing,China,100080","Microsoft Research Asia, Beijing 100080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,Beijing,China,100080","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101775106","display_name":"Songhao Piao","orcid":"https://orcid.org/0000-0003-4351-9112"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songhao Piao","raw_affiliation_strings":["Harbin Institute of Technology,Department of Computer Science and Technology,Harbin,China,150001","Department of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Department of Computer Science and Technology,Harbin,China,150001","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014662947","display_name":"Furu Wei","orcid":"https://orcid.org/0000-0002-7810-5852"},"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":"Furu Wei","raw_affiliation_strings":["Microsoft Research Asia,Beijing,China,100080","Microsoft Research Asia, Beijing 100080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,Beijing,China,100080","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing 100080, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6475,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89732021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"11","issue":"2","first_page":"405","last_page":"422"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14320","display_name":"Optics and Image Analysis","score":0.5250999927520752,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T14320","display_name":"Optics and Image Analysis","score":0.5250999927520752,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5714802742004395},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5479779243469238},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5246567726135254},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics","score":0.523963451385498},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42408332228660583},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37966540455818176},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3378889262676239},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1856352686882019},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13779577612876892}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5714802742004395},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5479779243469238},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5246567726135254},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.523963451385498},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42408332228660583},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37966540455818176},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3378889262676239},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1856352686882019},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13779577612876892},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.26599/cvm.2025.9450377","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450377","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f7dd10ac457945a29854f3077559eebe","is_oa":true,"landing_page_url":"https://doaj.org/article/f7dd10ac457945a29854f3077559eebe","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Visual Media, Vol 11, Iss 2, Pp 405-422 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.26599/cvm.2025.9450377","is_oa":true,"landing_page_url":"https://doi.org/10.26599/cvm.2025.9450377","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307764","display_name":"Microsoft","ror":"https://ror.org/00d0nc645"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1538131130","https://openalex.org/W1861492603","https://openalex.org/W2095705004","https://openalex.org/W2117539524","https://openalex.org/W2331143823","https://openalex.org/W2507296351","https://openalex.org/W2560730294","https://openalex.org/W2752796333","https://openalex.org/W2886641317","https://openalex.org/W2923014074","https://openalex.org/W2950689937","https://openalex.org/W2962770929","https://openalex.org/W2962784628","https://openalex.org/W2962785568","https://openalex.org/W2963073614","https://openalex.org/W2963250244","https://openalex.org/W2963530300","https://openalex.org/W2963748441","https://openalex.org/W2963966654","https://openalex.org/W2988975212","https://openalex.org/W3034255912","https://openalex.org/W3096831136","https://openalex.org/W3138516171","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3174525637","https://openalex.org/W3175515048","https://openalex.org/W3180355996","https://openalex.org/W3212386989","https://openalex.org/W4312312750","https://openalex.org/W4312438583","https://openalex.org/W4312804044","https://openalex.org/W4312911498","https://openalex.org/W4312933868","https://openalex.org/W4312974539","https://openalex.org/W4313021454","https://openalex.org/W4313156423","https://openalex.org/W4313158203","https://openalex.org/W4385245566","https://openalex.org/W4386065765","https://openalex.org/W4386071687","https://openalex.org/W4386076509","https://openalex.org/W6679436768","https://openalex.org/W6718379498","https://openalex.org/W6762931180","https://openalex.org/W6765779288","https://openalex.org/W6779879114","https://openalex.org/W6789753369","https://openalex.org/W6790019176","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W2319989118","https://openalex.org/W1503820821","https://openalex.org/W2285491073","https://openalex.org/W1991998366","https://openalex.org/W3112751614","https://openalex.org/W1995979513","https://openalex.org/W4403759101","https://openalex.org/W4249185555","https://openalex.org/W1999937205","https://openalex.org/W4409132263"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3,47,138],"explore":[4],"the":[5,26,39,54,60,65,80,83,92,119,125],"potential":[6],"of":[7,82,94,147],"Multiway":[8,50,69],"Transformers":[9,51,70],"for":[10,37,129],"text-to-image":[11,120],"generation":[12,121],"to":[13,52,103],"achieve":[14,139],"performance":[15],"improvements":[16],"through":[17],"a":[18,35,143],"concise":[19],"and":[20,25,78,96,117],"efficient":[21],"decoupled":[22],"model":[23,105,134],"design":[24],"inference":[27],"efficiency":[28],"provided":[29],"by":[30],"bidirectional":[31,49,100],"encoding.":[32],"We":[33],"propose":[34],"method":[36],"improving":[38],"image":[40,114],"tokenizer":[41,110],"using":[42],"pretrained":[43],"Vision":[44],"Transformers.":[45],"Next,":[46],"employ":[48],"restore":[53],"masked":[55],"visual":[56,95],"tokens":[57,98],"combined":[58],"with":[59,135,142],"unmasked":[61],"text":[62,97],"tokens.":[63],"On":[64],"MS-COCO":[66],"benchmark,":[67],"our":[68,108,133],"outperform":[71],"vanilla":[72],"Transformers,":[73],"achieving":[74],"superior":[75],"FID":[76,145],"scores":[77],"confirming":[79],"efficacy":[81],"modality-specific":[84],"parameter":[85],"computation":[86],"design.":[87],"Ablation":[88],"studies":[89],"reveal":[90],"that":[91],"fusion":[93],"in":[99,113],"encoding":[101],"contributes":[102],"improved":[104],"performance.":[106],"Additionally,":[107],"proposed":[109],"outperforms":[111],"VQGAN":[112],"reconstruction":[115],"quality":[116],"enhances":[118],"results.":[122],"By":[123],"incorporating":[124],"additional":[126],"CC-3M":[127],"dataset":[128],"intermediate":[130],"finetuning":[131],"on":[132,149],"688M":[136],"parameters,":[137],"competitive":[140],"results":[141],"finetuned":[144],"score":[146],"4.98":[148],"MS-COCO.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2025-10-10T00:00:00"}
