{"id":"https://openalex.org/W4387969123","doi":"https://doi.org/10.1145/3581783.3613781","title":"Contrast-augmented Diffusion Model with Fine-grained Sequence Alignment for Markup-to-Image Generation","display_name":"Contrast-augmented Diffusion Model with Fine-grained Sequence Alignment for Markup-to-Image Generation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969123","doi":"https://doi.org/10.1145/3581783.3613781"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3613781","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3613781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/A5089792276","display_name":"Guojin Zhong","orcid":"https://orcid.org/0000-0002-6054-3694"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guojin Zhong","raw_affiliation_strings":["Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100603557","display_name":"Jin Yuan","orcid":"https://orcid.org/0000-0002-9600-7789"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Yuan","raw_affiliation_strings":["Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035818251","display_name":"Pan Wang","orcid":"https://orcid.org/0009-0004-2013-4791"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Wang","raw_affiliation_strings":["Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027010844","display_name":"Kailun Yang","orcid":"https://orcid.org/0000-0002-1090-667X"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kailun Yang","raw_affiliation_strings":["Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075938343","display_name":"Weili Guan","orcid":"https://orcid.org/0000-0002-5658-5509"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Weili Guan","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100396723","display_name":"Zhiyong Li","orcid":"https://orcid.org/0000-0001-9720-5915"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Li","raw_affiliation_strings":["Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5089792276"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":0.8358,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75589894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5311","last_page":"5320"},"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":0.9991000294685364,"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":0.9991000294685364,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9936000108718872,"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":0.9883000254631042,"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/markup-language","display_name":"Markup language","score":0.8491737842559814},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7789539098739624},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.646717369556427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5420653820037842},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5345900058746338},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5268087387084961},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.5125231742858887},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47998568415641785},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45483797788619995},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4031904637813568},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.34529584646224976}],"concepts":[{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.8491737842559814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7789539098739624},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.646717369556427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5420653820037842},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5345900058746338},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5268087387084961},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.5125231742858887},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47998568415641785},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45483797788619995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4031904637813568},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34529584646224976},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3613781","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3613781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2518937804","display_name":null,"funder_award_id":"21A20518","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2781639450","display_name":null,"funder_award_id":"61976086","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3269000616","display_name":null,"funder_award_id":"kq2202177","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4335622648","display_name":null,"funder_award_id":"6227215","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5466994634","display_name":null,"funder_award_id":"No.62272157, No.U21A20518, No.61976086","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6058138561","display_name":null,"funder_award_id":", No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8354495100","display_name":null,"funder_award_id":"U21A20518","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8565926968","display_name":null,"funder_award_id":"U21A2051","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8637866159","display_name":null,"funder_award_id":"62272157","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8863666567","display_name":null,"funder_award_id":"and No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2963163163","https://openalex.org/W2963966654","https://openalex.org/W2981689412","https://openalex.org/W3013224334","https://openalex.org/W3034371424","https://openalex.org/W3096831136","https://openalex.org/W3174525637","https://openalex.org/W3175855397","https://openalex.org/W3176823897","https://openalex.org/W3198064418","https://openalex.org/W3205866742","https://openalex.org/W3207865986","https://openalex.org/W4226470037","https://openalex.org/W4298054444","https://openalex.org/W4304086151","https://openalex.org/W4304086649","https://openalex.org/W4306317797","https://openalex.org/W4312388283","https://openalex.org/W4312419008","https://openalex.org/W4312933868","https://openalex.org/W4312977351","https://openalex.org/W4385270985","https://openalex.org/W4386071814","https://openalex.org/W4390871953","https://openalex.org/W4390873332"],"related_works":["https://openalex.org/W4385386698","https://openalex.org/W4388119604","https://openalex.org/W2378211422","https://openalex.org/W2954418080","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W3121570353","https://openalex.org/W818235636","https://openalex.org/W4388119676","https://openalex.org/W1566913699"],"abstract_inverted_index":{"The":[0],"recently":[1],"rising":[2],"markup-to-image":[3,63],"generation":[4],"poses":[5],"greater":[6],"challenges":[7],"as":[8,21,23],"compared":[9],"to":[10,15,59,73,99,117,134],"natural":[11],"image":[12],"generation,":[13],"due":[14],"its":[16],"low":[17],"tolerance":[18],"for":[19,62,83,122],"errors":[20],"well":[22,74],"the":[24,56,76,80,90,123,127,136,143,163,167,170],"complex":[25],"sequence":[26,77],"and":[27,32,103,162],"context":[28],"correlations":[29],"between":[30,79],"markup":[31,140],"rendered":[33],"image.":[34],"This":[35],"paper":[36],"proposes":[37],"a":[38,68,95,108,119],"novel":[39,109],"model":[40,58,98],"named":[41],"\"Contrast-augmented":[42],"Diffusion":[43],"Model":[44],"with":[45],"Fine-grained":[46],"Sequence":[47],"Alignment''":[48],"(FSA-CDM),":[49],"which":[50,113],"introduces":[51],"contrastive":[52,110],"positive/negative":[53],"samples":[54,105],"into":[55],"diffusion":[57,97],"boost":[60],"performance":[61,178],"generation.":[64],"Technically,":[65],"we":[66,93],"design":[67],"fine-grained":[69],"cross-modal":[70],"alignment":[71],"module":[72,131],"explore":[75,101],"similarity":[78],"two":[81],"modalities":[82],"learning":[84],"robust":[85],"feature":[86],"representations.":[87],"To":[88],"improve":[89],"generalization":[91],"ability,":[92],"propose":[94],"contrast-augmented":[96],"explicitly":[100],"positive":[102],"negative":[104],"by":[106,179],"maximizing":[107],"variational":[111],"objective,":[112],"is":[114,132],"mathematically":[115],"inferred":[116],"provide":[118],"tighter":[120],"bound":[121],"model's":[124],"optimization.":[125],"Moreover,":[126],"context-aware":[128],"cross":[129],"attention":[130],"developed":[133],"capture":[135],"contextual":[137],"information":[138],"within":[139],"language":[141],"during":[142],"denoising":[144],"process,":[145],"yielding":[146],"better":[147],"noise":[148],"prediction":[149],"results.":[150],"Extensive":[151],"experiments":[152],"are":[153],"conducted":[154],"on":[155],"four":[156],"benchmark":[157],"datasets":[158],"from":[159],"different":[160],"domains,":[161],"experimental":[164],"results":[165],"demonstrate":[166],"effectiveness":[168],"of":[169],"proposed":[171],"components":[172],"in":[173],"FSA-CDM,":[174],"significantly":[175],"exceeding":[176],"state-of-the-art":[177],"about":[180],"2%":[181],"~":[182],"12%":[183],"DTW":[184],"improvements.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}