{"id":"https://openalex.org/W4415538219","doi":"https://doi.org/10.1145/3746027.3755367","title":"ObjCtrl: Object-based Control Relaxation for Conditional Text-to-Image Generation","display_name":"ObjCtrl: Object-based Control Relaxation for Conditional Text-to-Image Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538219","doi":"https://doi.org/10.1145/3746027.3755367"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755367","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5073055348","display_name":"Xinlong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinlong Zhang","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0000-7700-4024","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015625724","display_name":"Zejian Li","orcid":"https://orcid.org/0000-0001-5313-2742"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zejian Li","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-5313-2742","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318189","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-4383-3905"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["School of Design, Southwest Jiaotong University, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0002-4383-3905","affiliations":[{"raw_affiliation_string":"School of Design, Southwest Jiaotong University, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoyu Zhang","orcid":"https://orcid.org/0009-0000-7094-884X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Zhang","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0000-7094-884X","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103930976","display_name":"Jia Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Wei","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0005-2996-203X","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chengyu Lin","orcid":"https://orcid.org/0009-0000-2369-7419"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyu Lin","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0000-2369-7419","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101465600","display_name":"Yongchuan Tang","orcid":"https://orcid.org/0000-0002-0157-7771"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongchuan Tang","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-0157-7771","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5073055348"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28738306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10064","last_page":"10073"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9965999722480774,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9965999722480774,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9940000176429749,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9926999807357788,"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/controllability","display_name":"Controllability","score":0.6644999980926514},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.534600019454956},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5141000151634216},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.49959999322891235},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.47769999504089355},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.39719998836517334},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.39100000262260437},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.38760000467300415},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.357699990272522}],"concepts":[{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.6644999980926514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6470999717712402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5372999906539917},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.534600019454956},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5141000151634216},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.49959999322891235},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.47769999504089355},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39719998836517334},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.39100000262260437},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3659999966621399},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.357699990272522},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C2776029896","wikidata":"https://www.wikidata.org/wiki/Q3935810","display_name":"Relaxation (psychology)","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3294999897480011},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.32659998536109924},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30649998784065247},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C174920663","wikidata":"https://www.wikidata.org/wiki/Q5159256","display_name":"Conditional dependence","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C2780527621","wikidata":"https://www.wikidata.org/wiki/Q7936593","display_name":"Visual control","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2515999972820282},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755367","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7631846708","display_name":null,"funder_award_id":"No. 2024M752677","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2145023731","https://openalex.org/W2955639361","https://openalex.org/W4312933868","https://openalex.org/W4385682474","https://openalex.org/W4386075631","https://openalex.org/W4386076027","https://openalex.org/W4386076403","https://openalex.org/W4390872387","https://openalex.org/W4390873054","https://openalex.org/W4392427699","https://openalex.org/W4394625750","https://openalex.org/W4402754201","https://openalex.org/W4403791099","https://openalex.org/W4403791999","https://openalex.org/W4403946930","https://openalex.org/W4404124928","https://openalex.org/W4404613153","https://openalex.org/W4404722797","https://openalex.org/W4405270825"],"related_works":[],"abstract_inverted_index":{"Conditional":[0],"text-to-image":[1,8],"diffusion":[2],"models":[3],"enhance":[4],"the":[5,78,111,144,155],"controllability":[6],"of":[7,170],"generation":[9,56],"by":[10],"incorporating":[11],"additional":[12],"visual":[13,26,40,60,79,107,141],"conditions.":[14],"However,":[15],"they":[16],"often":[17],"encounter":[18],"two":[19],"main":[20],"challenges":[21],"when":[22],"dealing":[23],"with":[24,62,150],"complex":[25],"conditions":[27],"(namely,":[28],"including":[29],"multiple":[30],"different":[31],"objects):":[32],"semantic":[33,64,83],"leakage":[34],"among":[35],"objects":[36,69],"and":[37,42,106,140,175],"conflicts":[38,136],"between":[39,137],"inputs":[41],"text":[43],"descriptions.":[44],"To":[45,81],"address":[46,82],"these":[47],"issues,":[48],"we":[49,85,120],"propose":[50,121],"an":[51,87,96,122],"innovative":[52],"object-level":[53,116,130],"conditional":[54,108],"image":[55],"method.":[57],"It":[58],"associates":[59],"features":[61,147,152],"object":[63,104,138],"information,":[65],"ensuring":[66],"that":[67,162],"generated":[68],"are":[70,148],"accurately":[71],"positioned":[72],"in":[73,168],"their":[74],"expected":[75],"locations":[76],"within":[77],"inputs.":[80],"leakage,":[84],"design":[86],"Object-level":[88,123],"Structure":[89],"Controller":[90],"(OSC)":[91],"module.":[92],"This":[93],"module":[94,127],"utilizes":[95],"attention":[97],"mechanism":[98],"to":[99,113,128,153],"fuse":[100],"bounding":[101],"box":[102],"annotations,":[103],"prompts,":[105],"inputs,":[109],"allowing":[110],"model":[112],"learn":[114],"essential":[115],"structural":[117,151,173],"features.":[118,142,158],"Besides,":[119],"Control":[124],"Relaxation":[125],"(OCR)":[126],"predict":[129],"scale":[131],"features,":[132],"which":[133],"can":[134],"reconcile":[135],"semantics":[139],"Finally,":[143],"scaled":[145],"backbone":[146],"fused":[149],"form":[154],"final":[156],"output":[157],"Extensive":[159],"experiments":[160],"demonstrate":[161],"our":[163],"approach":[164],"outperforms":[165],"state-of-the-art":[166],"methods":[167],"terms":[169],"text-image":[171],"alignment,":[172],"similarity,":[174],"spatial":[176],"fidelity.":[177]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}
