{"id":"https://openalex.org/W4415538763","doi":"https://doi.org/10.1145/3746027.3755169","title":"CoCoNO: Attention Contrast-and-Complete for Initial Noise Optimization in Text-to-Image Synthesis","display_name":"CoCoNO: Attention Contrast-and-Complete for Initial Noise Optimization in Text-to-Image Synthesis","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538763","doi":"https://doi.org/10.1145/3746027.3755169"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755169","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755169","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755169","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085047920","display_name":"Arjun Sundaram","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Aravindan Kamatchi Sundaram","raw_affiliation_strings":["Data Science and Artificial Intelligence, Indian Institute of Technology, Madras, Chennai, Tamil Nadu, India"],"raw_orcid":"https://orcid.org/0009-0008-7007-006X","affiliations":[{"raw_affiliation_string":"Data Science and Artificial Intelligence, Indian Institute of Technology, Madras, Chennai, Tamil Nadu, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ujjayan Pal","orcid":"https://orcid.org/0009-0008-3658-4171"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ujjayan Pal","raw_affiliation_strings":["Computer Science and Engineering, Indian Institute of Technology, Madras, Chennai, Tamil Nadu, India"],"raw_orcid":"https://orcid.org/0009-0008-3658-4171","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology, Madras, Chennai, Tamil Nadu, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111083227","display_name":"Abhimanyu Chauhan","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhimanyu Chauhan","raw_affiliation_strings":["Mechanical Engineering, Indian Institute of Technology, Bombay, Mumbai, Maharashtra, India"],"raw_orcid":"https://orcid.org/0009-0003-2069-1830","affiliations":[{"raw_affiliation_string":"Mechanical Engineering, Indian Institute of Technology, Bombay, Mumbai, Maharashtra, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101908796","display_name":"Aishwarya Agarwal","orcid":"https://orcid.org/0000-0002-5368-2442"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aishwarya Agarwal","raw_affiliation_strings":["Adobe Research, Bengaluru, Karnataka, India"],"raw_orcid":"https://orcid.org/0000-0002-5368-2442","affiliations":[{"raw_affiliation_string":"Adobe Research, Bengaluru, Karnataka, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044410531","display_name":"Srikrishna Karanam","orcid":"https://orcid.org/0000-0002-7627-7765"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srikrishna Karanam","raw_affiliation_strings":["Adobe Research, Bengaluru, Karnataka, India"],"raw_orcid":"https://orcid.org/0000-0002-7627-7765","affiliations":[{"raw_affiliation_string":"Adobe Research, Bengaluru, Karnataka, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085047920"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28780784,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9862","last_page":"9870"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9991999864578247,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9991999864578247,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.994700014591217,"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":0.9900000095367432,"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/noise","display_name":"Noise (video)","score":0.6226999759674072},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5343000292778015},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.45410001277923584},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.414000004529953},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.40450000762939453},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.39590001106262207},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.365200012922287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7232000231742859},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6226999759674072},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5343000292778015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49799999594688416},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36719998717308044},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29089999198913574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28850001096725464},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2849000096321106},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755169","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755169","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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":{"id":"doi:10.1145/3746027.3755169","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755169","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2962770929","https://openalex.org/W2962793481","https://openalex.org/W2962974533","https://openalex.org/W2963073614","https://openalex.org/W2963966654","https://openalex.org/W2966792645","https://openalex.org/W4312933868","https://openalex.org/W4312977351","https://openalex.org/W4386113271","https://openalex.org/W4390873875"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"recent":[1],"advancements":[2],"in":[3,10,55],"text-to-image":[4,11],"models,":[5],"achieving":[6],"semantically":[7],"accurate":[8],"images":[9],"diffusion":[12],"models":[13],"is":[14,152,180],"a":[15,52,62,81,99,156,189],"persistent":[16],"challenge.":[17],"While":[18],"existing":[19],"initial":[20,105],"latent":[21,106],"optimization":[22,191],"methods":[23],"have":[24,51],"demonstrated":[25],"impressive":[26],"performance,":[27],"we":[28,96,206],"identify":[29,119],"two":[30,135],"key":[31],"limitations:":[32],"(a)":[33],"attention":[34,67,129,140,150,160,164,173],"neglect,":[35],"where":[36,69],"the":[37,44,56,70,104,109,123,139,163,169,194,216,220],"synthesized":[38],"image":[39,72],"omits":[40],"certain":[41],"subjects":[42,78],"from":[43,122],"input":[45],"prompt":[46],"because":[47,79],"they":[48],"do":[49],"not":[50],"designated":[53],"region":[54],"self-attention":[57,87,113,124],"map":[58,125],"despite":[59,60],"having":[61],"high-response":[63],"cross-attention,":[64],"and":[65,86,114,126,162,182,214],"(b)":[66],"interference,":[68],"generated":[71],"has":[73],"mixed-up":[74],"properties":[75],"of":[76,80,89,219],"multiple":[77,204],"conflicting":[82],"overlap":[83,146],"between":[84],"cross-":[85],"maps":[88],"different":[90],"subjects.":[91],"To":[92],"address":[93],"these":[94,172],"limitations,":[95],"introduce":[97],"CoCoNO,":[98],"new":[100,136],"algorithm":[101],"that":[102,177,208],"optimizes":[103],"by":[107,147],"leveraging":[108],"complementary":[110],"information":[111],"within":[112,171,188],"cross-attention":[115],"maps.":[116],"We":[117],"first":[118],"subject-specific":[120],"regions":[121],"term":[127],"them":[128],"zones.":[130],"Our":[131,185],"method":[132],"then":[133],"introduces":[134],"loss":[137],"functions:":[138],"contrast":[141],"loss,":[142,166],"which":[143,167],"minimizes":[144],"undesirable":[145],"ensuring":[148],"each":[149,178],"zone":[151],"exclusively":[153],"linked":[154],"to":[155,175,196],"specific":[157],"subject's":[158],"cross":[159],"map,":[161],"complete":[165],"maximizes":[168],"activation":[170],"zones":[174],"guarantee":[176],"subject":[179],"fully":[181],"distinctly":[183],"represented.":[184],"approach":[186],"operates":[187],"noise":[190],"framework,":[192],"avoiding":[193],"need":[195],"retrain":[197],"base":[198],"models.":[199],"Through":[200],"extensive":[201],"experiments":[202],"on":[203],"benchmarks,":[205],"demonstrate":[207],"CoCoNO":[209],"significantly":[210],"improves":[211],"text-image":[212],"alignment":[213],"outperforms":[215],"current":[217],"state":[218],"art.":[221]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}