{"id":"https://openalex.org/W4400524854","doi":"https://doi.org/10.1145/3626772.3657787","title":"Capability-aware Prompt Reformulation Learning for Text-to-Image Generation","display_name":"Capability-aware Prompt Reformulation Learning for Text-to-Image Generation","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4400524854","doi":"https://doi.org/10.1145/3626772.3657787"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657787","doi":"https://doi.org/10.1145/3626772.3657787","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657787","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3626772.3657787","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023520034","display_name":"Jingtao Zhan","orcid":"https://orcid.org/0000-0002-7253-5245","observed_orcids":["https://orcid.org/0000-0002-7253-5245"]},"institutions":[{"id":"https://openalex.org/I4405284363","display_name":"Quan Cheng Laboratory","ror":"https://ror.org/03drypn60","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405284363"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingtao Zhan","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University & Quan Cheng Laboratory, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7253-5245","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University & Quan Cheng Laboratory, Beijing, China","institution_ids":["https://openalex.org/I4405284363","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089655391","display_name":"Qingyao Ai","orcid":"https://orcid.org/0000-0002-5030-709X","observed_orcids":["https://orcid.org/0000-0002-5030-709X"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyao Ai","raw_affiliation_strings":["Quan Cheng Laboratory & Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5030-709X","affiliations":[{"raw_affiliation_string":"Quan Cheng Laboratory & Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668121","display_name":"Yiqun Liu","orcid":"https://orcid.org/0000-0002-0140-4512","observed_orcids":["https://orcid.org/0000-0002-0140-4512"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqun Liu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University & Zhongguancun Laboratory, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0140-4512","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University & Zhongguancun Laboratory, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100416039","display_name":"Jia Chen","orcid":"https://orcid.org/0009-0005-0957-1744","observed_orcids":["https://orcid.org/0009-0005-0957-1744","https://orcid.org/0009-0003-1174-0063"]},"institutions":[{"id":"https://openalex.org/I4401726856","display_name":"Xiaohongshu (Little Red Book) (China)","ror":"https://ror.org/02apw2076","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726856"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Chen","raw_affiliation_strings":["Xiaohongshu Inc, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-0957-1744","affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc, Beijing, China","institution_ids":["https://openalex.org/I4401726856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100760812","display_name":"Shaoping Ma","orcid":"https://orcid.org/0000-0002-8762-8268","observed_orcids":["https://orcid.org/0000-0002-8762-8268"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoping Ma","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University & Zhongguancun Laboratory, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8762-8268","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University & Zhongguancun Laboratory, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3032,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.86959934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2145","last_page":"2155"},"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":0.9599999785423279,"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":0.9599999785423279,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.025599999353289604,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.0034000000450760126,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/text-to-image-generation","display_name":"text-to-image generation","score":0.9520000219345093},{"id":"https://openalex.org/keywords/user-capabilities","display_name":"user capabilities","score":0.8539999723434448},{"id":"https://openalex.org/keywords/interaction-logs","display_name":"interaction logs","score":0.7120000123977661},{"id":"https://openalex.org/keywords/artistic-creation","display_name":"artistic creation","score":0.621999979019165},{"id":"https://openalex.org/keywords/prompt-quality","display_name":"prompt quality","score":0.6489999890327454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7276985049247742},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47102126479148865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4598691165447235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4277578294277191},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3353310823440552}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3626772.3657787","doi":"https://doi.org/10.1145/3626772.3657787","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657787","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2403.19716","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.19716","pdf_url":"https://arxiv.org/pdf/2403.19716","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.19716","doi":"https://doi.org/10.48550/arxiv.2403.19716","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.19716","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3626772.3657787","doi":"https://doi.org/10.1145/3626772.3657787","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657787","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400524854.pdf","grobid_xml":"https://content.openalex.org/works/W4400524854.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1564094940","https://openalex.org/W1993378086","https://openalex.org/W1993692165","https://openalex.org/W2000672666","https://openalex.org/W2030960598","https://openalex.org/W2083159545","https://openalex.org/W2137931117","https://openalex.org/W2745673470","https://openalex.org/W2884663330","https://openalex.org/W2964121744","https://openalex.org/W2998096503","https://openalex.org/W3088584794","https://openalex.org/W3114303895","https://openalex.org/W3141117710","https://openalex.org/W3155638432","https://openalex.org/W3159809086","https://openalex.org/W3199400376","https://openalex.org/W4289600032","https://openalex.org/W4306820534","https://openalex.org/W4310428424","https://openalex.org/W4312933868","https://openalex.org/W4318147046","https://openalex.org/W4321471653","https://openalex.org/W4327810025","https://openalex.org/W4380994608","https://openalex.org/W4383472654","https://openalex.org/W4385570204","https://openalex.org/W4386066462","https://openalex.org/W4386071814","https://openalex.org/W4386076339","https://openalex.org/W4386076458","https://openalex.org/W4387801427","https://openalex.org/W4390632065","https://openalex.org/W4401024329","https://openalex.org/W7133208264","https://openalex.org/W7133208667"],"related_works":["https://openalex.org/W4392619076","https://openalex.org/W7127976041","https://openalex.org/W4387934929","https://openalex.org/W4393159172","https://openalex.org/W7212273594","https://openalex.org/W4384808007","https://openalex.org/W4327810025","https://openalex.org/W4414758720","https://openalex.org/W7133208667","https://openalex.org/W4387801427"],"abstract_inverted_index":{"Text-to-image":[0],"generation":[1],"systems":[2,29,217],"have":[3],"emerged":[4],"as":[5,146],"revolutionary":[6],"tools":[7],"in":[8,17,90,93,152],"the":[9,25,34,85,94,108,120,127,155,161,205],"realm":[10],"of":[11,27,36,73,96,207,229],"artistic":[12,221],"creation,":[13],"offering":[14],"unprecedented":[15],"ease":[16],"transforming":[18],"textual":[19],"prompts":[20,139],"into":[21,119],"visual":[22],"art.":[23],"However,":[24],"efficacy":[26],"these":[28,74],"is":[30,81],"intricately":[31],"linked":[32],"to":[33,44,63,141,157,167,178],"quality":[35,95],"user-provided":[37],"prompts,":[38],"which":[39],"often":[40],"poses":[41],"a":[42,142,226],"challenge":[43,54],"users":[45],"unfamiliar":[46],"with":[47,215],"prompt":[48,67,79],"crafting.":[49],"This":[50,164],"paper":[51],"addresses":[52],"this":[53,102],"by":[55,148],"leveraging":[56],"user":[57,78,117,144,175,181],"reformulation":[58,68,80,97,121,171,182],"data":[59,103],"from":[60],"interaction":[61,214],"logs":[62,75],"develop":[64],"an":[65],"automatic":[66],"model.":[69],"Our":[70],"in-depth":[71],"analysis":[72],"reveals":[76],"that":[77],"heavily":[82],"dependent":[83],"on":[84,198],"individual":[86],"user's":[87],"capability,":[88,145],"resulting":[89],"significant":[91],"variance":[92],"pairs.":[98],"To":[99],"effectively":[100,168],"use":[101],"for":[104,225],"training,":[105],"we":[106],"introduce":[107],"Capability-aware":[109],"Prompt":[110],"Reformulation":[111,129],"(CAPR)":[112],"framework.":[113],"CAPR":[114,166,210],"innovatively":[115],"integrates":[116],"capability":[118],"process":[122],"through":[123],"two":[124],"key":[125],"components:":[126],"Conditional":[128],"Model":[130],"(CRM)":[131],"and":[132,159,177,194,218],"Configurable":[133],"Capability":[134],"Features":[135],"(CCF).":[136],"CRM":[137],"reformulates":[138],"according":[140],"specified":[143],"represented":[147],"CCF.":[149],"The":[150],"CCF,":[151],"turn,":[153],"offers":[154],"flexibility":[156],"tune":[158],"guide":[160],"CRM's":[162],"behavior.":[163],"enables":[165],"learn":[169],"diverse":[170],"strategies":[172],"across":[173],"various":[174],"capacities":[176],"simulate":[179],"high-capability":[180],"during":[183],"inference.":[184],"Extensive":[185],"experiments":[186],"demonstrate":[187],"CAPR's":[188],"superior":[189],"performance":[190],"over":[191],"existing":[192],"baselines":[193],"its":[195],"remarkable":[196],"robustness":[197],"unseen":[199],"systems.":[200],"Furthermore,":[201],"comprehensive":[202],"analyses":[203],"validate":[204],"effectiveness":[206],"different":[208],"components.":[209],"can":[211],"facilitate":[212],"user-friendly":[213],"text-to-image":[216],"make":[219],"advanced":[220],"creation":[222],"more":[223],"achievable":[224],"broader":[227],"range":[228],"users.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-07-12T00:00:00"}