{"id":"https://openalex.org/W4408353933","doi":"https://doi.org/10.1109/icassp49660.2025.10890155","title":"Semantic Attention and LLM-based Layout Guidance for Text-to-Image Generation","display_name":"Semantic Attention and LLM-based Layout Guidance for Text-to-Image Generation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353933","doi":"https://doi.org/10.1109/icassp49660.2025.10890155"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890155","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890155","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5063720114","display_name":"Yuxiang Song","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Song","raw_affiliation_strings":["East China Normal University,School of Computer Science and Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106439267","display_name":"Zhaoguang Long","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoguang Long","raw_affiliation_strings":["East China Normal University,School of Computer Science and Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Man Lan","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Man Lan","raw_affiliation_strings":["East China Normal University,School of Computer Science and Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100890759","display_name":"Changzhi Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changzhi Sun","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011502262","display_name":"Aimin Zhou","orcid":"https://orcid.org/0000-0003-1015-9966"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aimin Zhou","raw_affiliation_strings":["East China Normal University,School of Computer Science and Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042884230","display_name":"Yuefeng Chen","orcid":"https://orcid.org/0000-0002-5925-2291"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuefeng Chen","raw_affiliation_strings":["Shanghai Transsion Co., Ltd,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Transsion Co., Ltd,Shanghai,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101166841","display_name":"Hao Yuan","orcid":"https://orcid.org/0009-0001-8956-9804"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Yuan","raw_affiliation_strings":["Shanghai Transsion Co., Ltd,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Transsion Co., Ltd,Shanghai,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050692367","display_name":"Fei Cao","orcid":"https://orcid.org/0000-0001-9191-4278"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Cao","raw_affiliation_strings":["Shanghai Transsion Co., Ltd,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Transsion Co., Ltd,Shanghai,China","institution_ids":[]}]}],"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.8968999981880188,"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":0.8968999981880188,"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":0.8379999995231628,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.7850000262260437,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.7462477087974548},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5494717955589294},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4572443962097168},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40351545810699463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37361064553260803},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.362876832485199},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.357693076133728}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7462477087974548},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5494717955589294},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4572443962097168},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40351545810699463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37361064553260803},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.362876832485199},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.357693076133728}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890155","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890155","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337495","display_name":"Technology Development","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W4312456860","https://openalex.org/W4312933868","https://openalex.org/W4385270985","https://openalex.org/W4386066731","https://openalex.org/W4386076027","https://openalex.org/W4386076403","https://openalex.org/W4387968301","https://openalex.org/W4390872671","https://openalex.org/W4390873054","https://openalex.org/W4390889801","https://openalex.org/W4393148714","https://openalex.org/W4394625750","https://openalex.org/W4402733577","https://openalex.org/W6739901393","https://openalex.org/W6791353385","https://openalex.org/W6809646742","https://openalex.org/W6809885388","https://openalex.org/W6810081322","https://openalex.org/W6838639034","https://openalex.org/W6841366371","https://openalex.org/W6846007759","https://openalex.org/W6849938875","https://openalex.org/W6852162230","https://openalex.org/W6852567072","https://openalex.org/W6852922754"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2779427294","https://openalex.org/W2775347418","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W3003936178","https://openalex.org/W2145652935","https://openalex.org/W2563206327","https://openalex.org/W2069885731"],"abstract_inverted_index":{"Diffusion":[0],"models":[1],"have":[2],"substantially":[3],"advanced":[4],"text-to-image":[5,55],"generation,":[6],"achieving":[7],"remarkable":[8],"performance":[9],"in":[10,31,92,134],"creating":[11],"high-quality":[12],"images":[13,24],"from":[14,49,105],"textual":[15],"prompts.":[16,33],"However,":[17],"they":[18],"often":[19],"struggle":[20],"with":[21],"accurately":[22],"generating":[23,139],"representing":[25],"spatial":[26],"locations":[27],"described":[28],"or":[29],"implied":[30],"the":[32,72,79,83,87,93,101,106],"To":[34],"address":[35],"this,":[36],"we":[37],"introduce":[38],"SALT,":[39],"a":[40],"training-free":[41,132],"method":[42,58],"leveraging":[43],"semantic":[44],"attention":[45,108],"and":[46,63,122,138],"layout":[47,80],"guidance":[48],"Large":[50],"Language":[51],"Models":[52],"(LLMs)":[53],"for":[54],"generation.":[56],"This":[57],"effectively":[59],"guides":[60],"both":[61],"cross-attention":[62],"self-attention":[64],"layers":[65],"within":[66],"diffusion":[67,88],"models,":[68],"steering":[69],"generation":[70],"toward":[71],"direction":[73],"of":[74,86],"high-attention":[75],"values":[76],"provided":[77],"by":[78],"guidance.":[81],"During":[82],"denoising":[84],"process":[85],"model,":[89],"image":[90],"features":[91],"latent":[94],"space":[95],"are":[96],"iteratively":[97],"refined":[98],"based":[99],"on":[100,115],"loss":[102],"function":[103],"calculated":[104],"desired":[107],"maps.":[109],"Our":[110],"approach":[111],"has":[112],"been":[113],"executed":[114],"two":[116],"benchmarks,":[117],"providing":[118],"detailed":[119],"qualitative":[120],"examples":[121],"comprehensive":[123],"quantitative":[124],"analyses.":[125],"Results":[126],"demonstrate":[127],"that":[128],"SALT":[129],"outperforms":[130],"existing":[131],"methods":[133],"controlling":[135],"object":[136],"layouts":[137],"attributes.<sup":[140],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[141],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}