{"id":"https://openalex.org/W4414165850","doi":"https://doi.org/10.1109/tmm.2025.3607759","title":"Box It to Bind It: Unified Layout Control and Attribute Binding in Text-to-Image Diffusion Models","display_name":"Box It to Bind It: Unified Layout Control and Attribute Binding in Text-to-Image Diffusion Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414165850","doi":"https://doi.org/10.1109/tmm.2025.3607759"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3607759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3607759","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5023139332","display_name":"Ashkan Taghipour","orcid":"https://orcid.org/0000-0002-1950-5143"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ashkan Taghipour","raw_affiliation_strings":["Department of Computer Science and Software Engineering, The University of Western Australia, Crawley, WA, Australia","Department of Computer Science and Software Engineering, The University of Western Australia, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1950-5143","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Crawley, WA, Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019512958","display_name":"Morteza Ghahremani","orcid":"https://orcid.org/0000-0001-6423-6475"},"institutions":[{"id":"https://openalex.org/I4210121368","display_name":"Machine Science","ror":"https://ror.org/02hrr9v50","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210121368"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Morteza Ghahremani","raw_affiliation_strings":["Munich Center for Machine Learning (MCML), M&#x00FC;nchen, Germany","Munich Center for Machine Learning (MCML), Technical Univeristy of Munich (TUM), Germany"],"raw_orcid":"https://orcid.org/0000-0001-6423-6475","affiliations":[{"raw_affiliation_string":"Munich Center for Machine Learning (MCML), M&#x00FC;nchen, Germany","institution_ids":["https://openalex.org/I4210121368"]},{"raw_affiliation_string":"Munich Center for Machine Learning (MCML), Technical Univeristy of Munich (TUM), Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009750573","display_name":"Mohammed Bennamoun","orcid":"https://orcid.org/0000-0002-6603-3257"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mohammed Bennamoun","raw_affiliation_strings":["Department of Computer Science and Software Engineering, The University of Western Australia, Crawley, WA, Australia","Department of Computer Science and Software Engineering, The University of Western Australia, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6603-3257","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Crawley, WA, Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, The University of Western Australia, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079424927","display_name":"Aref Miri Rekavandi","orcid":"https://orcid.org/0000-0001-9542-759X"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Aref Miri Rekavandi","raw_affiliation_strings":["University of Melbourne, Parkville, VIC, Australia","University of Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9542-759X","affiliations":[{"raw_affiliation_string":"University of Melbourne, Parkville, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002077138","display_name":"Hamid Laga","orcid":"https://orcid.org/0000-0002-4758-7510"},"institutions":[{"id":"https://openalex.org/I176790772","display_name":"Murdoch University","ror":"https://ror.org/00r4sry34","country_code":"AU","type":"education","lineage":["https://openalex.org/I176790772"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hamid Laga","raw_affiliation_strings":["School of Information Technology, Murdoch University, Murdoch, WA, Australia","School of Information Technology, Murdoch University, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4758-7510","affiliations":[{"raw_affiliation_string":"School of Information Technology, Murdoch University, Murdoch, WA, Australia","institution_ids":["https://openalex.org/I176790772"]},{"raw_affiliation_string":"School of Information Technology, Murdoch University, Australia","institution_ids":["https://openalex.org/I176790772"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014216530","display_name":"Farid Boussa\u00efd","orcid":"https://orcid.org/0000-0001-7250-7407"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Farid Boussaid","raw_affiliation_strings":["Department of Electrical, Electronics and Computer Engineering, The University of Western Australia, Crawley, WA, Australia","Department of Electrical, Electronics and Computer Engineering, The University of Western Australia, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7250-7407","affiliations":[{"raw_affiliation_string":"Department of Electrical, Electronics and Computer Engineering, The University of Western Australia, Crawley, WA, Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"Department of Electrical, Electronics and Computer Engineering, The University of Western Australia, Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8854,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80054463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"27","issue":null,"first_page":"8393","last_page":"8407"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12162","display_name":"Cellular Automata and Applications","score":0.4408999979496002,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12162","display_name":"Cellular Automata and Applications","score":0.4408999979496002,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/minimum-bounding-box","display_name":"Minimum bounding box","score":0.7013999819755554},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6917999982833862},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.6658999919891357},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5813000202178955},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5781999826431274},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5453000068664551},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.45170000195503235},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4433000087738037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8601999878883362},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.7013999819755554},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6917999982833862},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.6658999919891357},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5813000202178955},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5781999826431274},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5453000068664551},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5011000037193298},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4433000087738037},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.42399999499320984},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3368000090122223},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.3025999963283539},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2745000123977661},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2630000114440918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.258899986743927},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25130000710487366},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2508000135421753},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2025.3607759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3607759","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/ad6e9dd4-4701-45c3-8661-7fc2661dd613","is_oa":false,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/ad6e9dd4-4701-45c3-8661-7fc2661dd613","pdf_url":null,"source":{"id":"https://openalex.org/S4306402492","display_name":"UWA Profiles and Research Repository (UWA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Taghipour, A, Ghahremani, M, Bennamoun, M, Rekavandi, A M, Laga, H & Boussaid, F 2025, 'Box It to Bind It : Unified Layout Control and Attribute Binding in Text-to-Image Diffusion Models', IEEE Transactions on Multimedia, vol. 27, pp. 8393-8407. https://doi.org/10.1109/TMM.2025.3607759","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2964225075","https://openalex.org/W4312456860","https://openalex.org/W4312824283","https://openalex.org/W4312933868","https://openalex.org/W4385270985","https://openalex.org/W4386071676","https://openalex.org/W4386076027","https://openalex.org/W4386076403","https://openalex.org/W4386973803","https://openalex.org/W4388263958","https://openalex.org/W4388579521","https://openalex.org/W4388756695","https://openalex.org/W4389539696","https://openalex.org/W4390872387","https://openalex.org/W4390872671","https://openalex.org/W4390873054","https://openalex.org/W4390873784","https://openalex.org/W4390874140","https://openalex.org/W4390874566","https://openalex.org/W4390889801","https://openalex.org/W4391547560","https://openalex.org/W4391547658","https://openalex.org/W4393148622","https://openalex.org/W4393148753","https://openalex.org/W4393156217","https://openalex.org/W4393253100","https://openalex.org/W4394625750","https://openalex.org/W4401841076","https://openalex.org/W4402715994","https://openalex.org/W4402716004","https://openalex.org/W4402716307","https://openalex.org/W4402727642","https://openalex.org/W4402727925","https://openalex.org/W4402733577","https://openalex.org/W4402753498","https://openalex.org/W4402753507","https://openalex.org/W4402754083","https://openalex.org/W4402782221","https://openalex.org/W4402997354","https://openalex.org/W4403021114","https://openalex.org/W4403990754","https://openalex.org/W4404612908","https://openalex.org/W4409366044","https://openalex.org/W4411119331"],"related_works":[],"abstract_inverted_index":{"While":[0],"latent":[1,78],"diffusion":[2,48],"models":[3,120],"(LDMs)":[4],"excel":[5],"at":[6],"creating":[7],"imaginative":[8],"images,":[9],"they":[10],"often":[11],"lack":[12],"precision":[13],"in":[14,45,55,106,130,157],"semantic":[15,43],"fidelity":[16],"and":[17,42,61,84,91,124,143,147],"spatial":[18,40],"control":[19,41],"over":[20],"where":[21,150],"objects":[22,100],"are":[23],"generated.":[24],"To":[25],"address":[26],"these":[27,132,170],"deficiencies,":[28],"we":[29],"introduce":[30],"the":[31,77,107,140],"Box-it-to-Bind-it":[32],"(B2B)":[33],"module\u2014a":[34],"novel,":[35],"training-free":[36],"approach":[37],"for":[38,117],"improving":[39],"accuracy":[44],"text-to-image":[46],"(T2I)":[47],"models.":[49],"B2B":[50,109,151],"targets":[51],"three":[52],"key":[53,133],"challenges":[54],"T2I:":[56],"catastrophic":[57],"neglect,":[58],"attribute":[59,159],"binding,":[60],"layout":[62,162],"guidance.":[63],"The":[64],"process":[65],"encompasses":[66],"two":[67],"main":[68],"steps:":[69],"(i)":[70],"<italic":[71,93],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[72,94],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Object":[73],"generation</i>,":[74],"which":[75],"adjusts":[76],"encoding":[79],"to":[80,102,172],"guarantee":[81],"object":[82],"generation":[83],"directs":[85],"it":[86],"within":[87],"specified":[88,104],"bounding":[89],"boxes,":[90],"(ii)":[92],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Attribute":[95],"binding</i>,":[96],"ensuring":[97],"that":[98],"generated":[99],"adhere":[101],"their":[103],"attributes":[105],"prompt.":[108],"is":[110],"designed":[111],"as":[112],"a":[113],"compatible":[114],"plug-and-play":[115],"module":[116],"existing":[118],"T2I":[119],"like":[121],"Stable":[122],"Diffusion":[123],"Gligen,":[125],"markedly":[126],"enhancing":[127],"models\u2019":[128],"performance":[129],"addressing":[131],"challenges.":[134],"We":[135],"assess":[136],"our":[137],"technique":[138],"on":[139],"well-established":[141],"CompBench":[142],"TIFA":[144],"score":[145],"benchmarks,":[146],"HRS":[148],"dataset":[149],"not":[152],"only":[153],"surpasses":[154],"methods":[155],"specialized":[156],"either":[158],"binding":[160],"or":[161],"guidance":[163],"but":[164],"also":[165],"uniquely":[166],"excels":[167],"by":[168],"integrating":[169],"capabilities":[171],"deliver":[173],"enhanced":[174],"overall":[175],"performance.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
