{"id":"https://openalex.org/W4392910548","doi":"https://doi.org/10.1109/icassp48485.2024.10447092","title":"Bridging The Domain Gap Arising from Text Description Differences for Stable Text-To-Image Generation","display_name":"Bridging The Domain Gap Arising from Text Description Differences for Stable Text-To-Image Generation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910548","doi":"https://doi.org/10.1109/icassp48485.2024.10447092"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447092","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5039523706","display_name":"Tian Tan","orcid":"https://orcid.org/0000-0003-4639-8301"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tian Tan","raw_affiliation_strings":["Fudan University,School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing,Shanghai,China","School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048621299","display_name":"Weimin Tan","orcid":"https://orcid.org/0000-0001-7677-4772"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weimin Tan","raw_affiliation_strings":["Fudan University,School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing,Shanghai,China","School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102819669","display_name":"Xuhao Jiang","orcid":"https://orcid.org/0000-0002-4646-5052"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuhao Jiang","raw_affiliation_strings":["Fudan University,School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing,Shanghai,China","School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101822868","display_name":"Yueming Jiang","orcid":"https://orcid.org/0000-0002-0951-074X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueming Jiang","raw_affiliation_strings":["Fudan University,School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing,Shanghai,China","School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081115024","display_name":"Bo Yan","orcid":"https://orcid.org/0000-0003-0256-9682"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Yan","raw_affiliation_strings":["Fudan University,School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing,Shanghai,China","School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039523706"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02601936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7155","last_page":"7159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.95660001039505,"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/T11439","display_name":"Video Analysis and Summarization","score":0.95660001039505,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9204999804496765,"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/bridging","display_name":"Bridging (networking)","score":0.8828330039978027},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7047738432884216},{"id":"https://openalex.org/keywords/text-generation","display_name":"Text generation","score":0.47262927889823914},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4600209593772888},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43402644991874695},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4223829507827759},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3860810399055481},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3357372283935547},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10131609439849854}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8828330039978027},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7047738432884216},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.47262927889823914},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4600209593772888},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43402644991874695},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4223829507827759},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3860810399055481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3357372283935547},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10131609439849854},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447092","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1553109372","display_name":null,"funder_award_id":"21ZR1406600","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"},{"id":"https://openalex.org/G3448428807","display_name":null,"funder_award_id":"U2001209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4772181003","display_name":null,"funder_award_id":"62372117","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"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":15,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W1861492603","https://openalex.org/W2143017621","https://openalex.org/W2963966654","https://openalex.org/W3013575054","https://openalex.org/W3035500781","https://openalex.org/W3091653824","https://openalex.org/W3141117710","https://openalex.org/W3216352822","https://openalex.org/W4214485011","https://openalex.org/W4312933868","https://openalex.org/W4312977351","https://openalex.org/W6600609147","https://openalex.org/W6775218022","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2054685365","https://openalex.org/W2056057048","https://openalex.org/W2667588871","https://openalex.org/W2990774877","https://openalex.org/W3093339210","https://openalex.org/W2122804826","https://openalex.org/W2138640103"],"abstract_inverted_index":{"Generating":[0],"high-quality":[1],"images":[2],"that":[3,33,110],"conform":[4],"to":[5,22,50,59,93,97],"the":[6,52,70,75,85,95,100,114],"semantics":[7],"of":[8],"captions":[9,86],"has":[10],"numerous":[11],"potential":[12],"applications.":[13],"However,":[14],"text-to-image":[15,62],"generation":[16],"is":[17],"a":[18,47],"challenging":[19],"task":[20],"due":[21],"its":[23],"cross-modality":[24],"nature.":[25],"Current":[26],"generative":[27],"models":[28],"are":[29,104,123],"typically":[30],"unstable,":[31],"meaning":[32],"complex":[34],"sentences":[35],"can":[36,81],"result":[37],"in":[38],"poor":[39],"image":[40,91],"quality.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"propose":[46],"novel":[48],"model":[49,65,96,122],"bridge":[51],"domain":[53],"gap":[54],"arising":[55],"from":[56,84],"sentence":[57],"complexity":[58],"achieve":[60],"stable":[61],"generation.":[63],"Our":[64,102,118],"includes":[66],"two":[67],"key":[68],"modules,":[69],"attribute":[71,76],"extraction":[72],"module":[73],"and":[74,87,106,120],"fusion":[77],"module.":[78],"These":[79],"modules":[80,103],"extract":[82],"attributes":[83],"fuse":[88],"them":[89],"with":[90],"features":[92],"encourage":[94],"accurately":[98],"understand":[99],"semantics.":[101],"plug-and-play":[105],"extensive":[107],"experiments":[108],"demonstrate":[109],"our":[111],"approach":[112],"outperforms":[113],"state-of-the-art":[115],"GAN":[116],"model.":[117],"code":[119],"trained":[121],"available":[124],"at":[125],"https://github.com/tantian21/stable-t2i-generation.":[126]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}