{"id":"https://openalex.org/W4416995336","doi":"https://doi.org/10.1109/wacv61042.2026.00419","title":"DCText: Scheduled Attention Masking for Visual Text Generation via Divide-and-Conquer Strategy","display_name":"DCText: Scheduled Attention Masking for Visual Text Generation via Divide-and-Conquer Strategy","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416995336","doi":"https://doi.org/10.1109/wacv61042.2026.00419"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00419","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00419","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.01302","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jaewoo Song","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewoo Song","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jooyoung Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jooyoung Choi","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kanghyun Baek","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kanghyun Baek","raw_affiliation_strings":["IPAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IPAI","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sangyub Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sangyub Lee","raw_affiliation_strings":["IPAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IPAI","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Daemin Park","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daemin Park","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051318852","display_name":"Sungroh Yoon","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungroh Yoon","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01625408,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4305","last_page":"4314"},"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":0.5932000279426575,"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":0.5932000279426575,"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":0.13809999823570251,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05420000106096268,"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/initialization","display_name":"Initialization","score":0.76910001039505},{"id":"https://openalex.org/keywords/text-generation","display_name":"Text generation","score":0.718500018119812},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6851999759674072},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5142999887466431},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4943000078201294},{"id":"https://openalex.org/keywords/visual-masking","display_name":"Visual masking","score":0.49309998750686646},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42750000953674316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7822999954223633},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.76910001039505},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.718500018119812},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6851999759674072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6118999719619751},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5142999887466431},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4943000078201294},{"id":"https://openalex.org/C2779200073","wikidata":"https://www.wikidata.org/wiki/Q18395575","display_name":"Visual masking","level":4,"score":0.49309998750686646},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4625999927520752},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.453000009059906},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.37369999289512634},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.3625999987125397},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28349998593330383},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.26350000500679016}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00419","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00419","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.01302","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.01302","pdf_url":"https://arxiv.org/pdf/2512.01302","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.01302","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.01302","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.01302","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.01302","pdf_url":"https://arxiv.org/pdf/2512.01302","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"recent":[1],"text-to-image":[2],"models":[3],"achieving":[4],"high-fidelity":[5],"text":[6,27,93,115],"rendering,":[7],"they":[8],"still":[9],"struggle":[10],"with":[11],"long":[12],"or":[13],"multiple":[14],"texts":[15],"due":[16],"to":[17,60],"diluted":[18],"global":[19],"attention.":[20],"We":[21],"propose":[22],"DC-Text,":[23],"a":[24,32,48,61],"training-free":[25],"visual":[26],"generation":[28,39,126],"method":[29,45],"that":[30,110],"adopts":[31],"divide-and-conquer":[33],"strategy,":[34],"leveraging":[35],"the":[36,54,113,124],"reliable":[37],"short-text":[38],"of":[40],"Multi-Modal":[41],"Diffusion":[42],"Transformers.":[43],"Our":[44],"first":[46],"decomposes":[47],"prompt":[49],"by":[50],"extracting":[51],"and":[52,82,95,106],"dividing":[53],"target":[55],"text,":[56],"then":[57],"assigns":[58],"each":[59,67],"designated":[62],"region.":[63],"To":[64],"accurately":[65],"render":[66],"segment":[68],"within":[69],"their":[70],"regions":[71],"while":[72,121],"preserving":[73],"overall":[74],"image":[75,119],"coherence,":[76],"we":[77],"introduce":[78],"two":[79],"attention":[80],"masks\u2014Text-Focus":[81],"Context-Expansion\u2014applied":[83],"sequentially":[84],"during":[85],"denoising.":[86],"Additionally,":[87],"Localized":[88],"Noise":[89],"Initialization":[90],"further":[91],"improves":[92],"accuracy":[94,116],"region":[96],"alignment":[97],"without":[98,117],"increasing":[99],"computational":[100],"cost.":[101],"Extensive":[102],"experiments":[103],"on":[104],"single-":[105],"multi-sentence":[107],"benchmarks":[108],"show":[109],"DCText":[111],"achieves":[112],"best":[114],"compromising":[118],"quality":[120],"also":[122],"delivering":[123],"lowest":[125],"latency.":[127]},"counts_by_year":[],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-12-03T00:00:00"}