{"id":"https://openalex.org/W4408354811","doi":"https://doi.org/10.1109/icassp49660.2025.10890356","title":"LTOS: Layout-controllable Text-object Synthesis via Adaptive Cross-attention Fusions","display_name":"LTOS: Layout-controllable Text-object Synthesis via Adaptive Cross-attention Fusions","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354811","doi":"https://doi.org/10.1109/icassp49660.2025.10890356"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890356","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/A5003760885","display_name":"Xiaoran Zhao","orcid":"https://orcid.org/0000-0001-7878-048X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoran Zhao","raw_affiliation_strings":["School of National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of National University of Defense Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100678109","display_name":"Tianhao Wu","orcid":"https://orcid.org/0000-0002-6141-5512"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianhao Wu","raw_affiliation_strings":["School of Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Nanyang Technological University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102536562","display_name":"Yu Lai","orcid":"https://orcid.org/0009-0001-9242-6775"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Lai","raw_affiliation_strings":["School of National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of National University of Defense Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062005460","display_name":"Zhiliang Tian","orcid":"https://orcid.org/0000-0002-8906-5198"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiliang Tian","raw_affiliation_strings":["School of National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of National University of Defense Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011008665","display_name":"Zhen Huang","orcid":"https://orcid.org/0000-0003-4819-373X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhen Huang","raw_affiliation_strings":["School of National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of National University of Defense Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100313821","display_name":"Yahui Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yahui Liu","raw_affiliation_strings":["Huawei Technologies Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047498670","display_name":"Zejiang He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejiang He","raw_affiliation_strings":["School of National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of National University of Defense Technology","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440903","display_name":"Dongsheng Li","orcid":"https://orcid.org/0000-0001-9743-2034"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongsheng Li","raw_affiliation_strings":["School of National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of National University of Defense Technology","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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/T10028","display_name":"Topic Modeling","score":0.9728000164031982,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9728000164031982,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.967199981212616,"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"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9621999859809875,"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":0.7436929941177368},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5575484037399292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3677927851676941}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7436929941177368},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5575484037399292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3677927851676941}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890356","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2111643688","https://openalex.org/W2185175083","https://openalex.org/W2314720829","https://openalex.org/W2343052201","https://openalex.org/W2568262903","https://openalex.org/W3203593958","https://openalex.org/W4283262825","https://openalex.org/W4312933868","https://openalex.org/W4312956471","https://openalex.org/W4320002812","https://openalex.org/W4385245566","https://openalex.org/W4385490028","https://openalex.org/W4385801729","https://openalex.org/W4386076027","https://openalex.org/W4390873054","https://openalex.org/W4393147980","https://openalex.org/W4403770375","https://openalex.org/W6640963894","https://openalex.org/W6767440493","https://openalex.org/W6779823529","https://openalex.org/W6839401645","https://openalex.org/W6850630192","https://openalex.org/W6852594708","https://openalex.org/W6852862680","https://openalex.org/W6852949445","https://openalex.org/W6854106264","https://openalex.org/W6858475632","https://openalex.org/W6863031173"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Controllable":[0],"text-to-image":[1],"generation":[2,20,26,150],"synthesizes":[3],"visual":[4,15,77,97],"text":[5,16,57,98,110,130,156],"and":[6,18,59,79,99,111,128,131,186,195],"objects":[7,119,132],"in":[8,133,189],"images":[9,94],"with":[10,95],"certain":[11],"conditions.":[12],"However,":[13],"existing":[14],"rendering":[17,58,107],"layout-to-image":[19],"tasks":[21],"focus":[22],"on":[23],"single":[24],"modality":[25],"or":[27],"rendering,":[28],"leaving":[29],"yet-to-be-bridged":[30],"gaps":[31],"between":[32],"the":[33,40,71,122,137,148,172,183],"approaches":[34],"correspondingly":[35],"designed":[36],"for":[37,70],"each":[38],"of":[39,174],"tasks.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,103,140,162],"introduce":[46],"a":[47,65,85,105,142,160,164],"unified":[48],"task":[49],"called":[50],"layout-controllable":[51,86],"text-object":[52,67,87],"synthesis":[53,68],"(LTOS),":[54],"which":[55,92],"merges":[56],"layout-based":[60],"object":[61,80],"generation.":[62],"We":[63,82,191],"construct":[64,104],"layout-aware":[66],"dataset":[69,194],"LTOS":[72],"task,":[73],"containing":[74],"well-aligned":[75],"labels":[76],"text,":[78],"information.":[81],"also":[83],"propose":[84,141],"adaptive":[88],"fusion":[89,145],"(TOF)":[90],"model,":[91],"generates":[93],"legible":[96],"plausible":[100],"objects.":[101],"Specifically,":[102],"visual-text":[106],"to":[108,117,125,151,154,168,170],"synthesize":[109],"employ":[112],"an":[113],"object-layout":[114],"control":[115,171],"module":[116],"generate":[118,127],"while":[120],"integrating":[121],"two":[123],"modules":[124],"harmoniously":[126],"integrate":[129],"images.":[134],"To":[135],"enhance":[136],"image-text":[138],"integration,":[139],"self-adaptive":[143,165],"cross-attention":[144,175],"that":[146,179],"forces":[147],"image":[149],"attend":[152],"more":[153],"important":[155],"spans.":[157],"Within":[158],"such":[159],"fusion,":[161],"use":[163],"learnable":[166],"factor":[167],"learn":[169],"influence":[173],"outputs.":[176],"Experiments":[177],"show":[178],"our":[180,193],"model":[181],"excels":[182],"strong":[184],"baselines":[185],"obtain":[187],"SOTA":[188],"LTOS.":[190],"release":[192],"codes":[196],"<sup":[197],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[198],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
