{"id":"https://openalex.org/W4402769626","doi":"https://doi.org/10.1109/cvpr52733.2024.02514","title":"Dynamic Prompt Optimizing for Text-to-Image Generation","display_name":"Dynamic Prompt Optimizing for Text-to-Image Generation","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402769626","doi":"https://doi.org/10.1109/cvpr52733.2024.02514"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.02514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.02514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5102609478","display_name":"Wenyi Mo","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenyi Mo","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425850","display_name":"Tianyu Zhang","orcid":"https://orcid.org/0000-0002-3908-7962"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyu Zhang","raw_affiliation_strings":["Du Xiaoman Technology"],"affiliations":[{"raw_affiliation_string":"Du Xiaoman Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054533256","display_name":"Yalong Bai","orcid":"https://orcid.org/0000-0002-8416-9027"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yalong Bai","raw_affiliation_strings":["Du Xiaoman Technology"],"affiliations":[{"raw_affiliation_string":"Du Xiaoman Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032925835","display_name":"Bing Su","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Su","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084170249","display_name":"Ji\u2013Rong Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji\u2013Rong Wen","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044479996","display_name":"Yang Qing","orcid":"https://orcid.org/0000-0003-2844-5098"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qing Yang","raw_affiliation_strings":["Du Xiaoman Technology"],"affiliations":[{"raw_affiliation_string":"Du Xiaoman Technology","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102609478"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":3.4115,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.9384146,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"26617","last_page":"26626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.8774999976158142,"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/T11439","display_name":"Video Analysis and Summarization","score":0.8774999976158142,"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/T12290","display_name":"Human Motion and Animation","score":0.7835999727249146,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.7175999879837036,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6984222531318665},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5073766112327576},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4872783422470093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4606251120567322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6984222531318665},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5073766112327576},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4872783422470093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4606251120567322}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.02514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.02514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7092948576","display_name":null,"funder_award_id":"62376277","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"},{"id":"https://openalex.org/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Text-to-image":[0],"generative":[1],"models,":[2],"specifically":[3],"those":[4],"based":[5],"on":[6,63],"diffusion":[7],"models":[8],"like":[9],"Imagen":[10],"and":[11,70,76,114,140],"Stable":[12],"Diffusion,":[13],"have":[14],"made":[15],"substantial":[16],"advancements.":[17],"Recently,":[18],"there":[19],"has":[20],"been":[21],"a":[22],"surge":[23],"of":[24,30,42,53,59,66,74,118],"interest":[25],"in":[26,45],"the":[27,38,46,51,57,64,67,71,89,96,112,123,132,152],"delicate":[28],"refinement":[29],"text":[31,47,68],"prompts.":[32,126],"Users":[33],"assign":[34],"weights":[35,75,113],"or":[36],"alter":[37],"injection":[39,115],"time":[40,77,116],"steps":[41,117],"certain":[43],"words":[44],"prompts":[48,61,69,98],"to":[49,110,122,134],"improve":[50],"quality":[52],"generated":[54],"images.":[55],"However,":[56],"success":[58],"fine-control":[60,125],"depends":[62],"accuracy":[65],"careful":[72],"selection":[73],"steps,":[78],"which":[79],"requires":[80],"significant":[81],"manual":[82],"intervention.":[83],"To":[84],"address":[85],"this,":[86],"we":[87,102],"introduce":[88],"Prompt":[90],"Auto-Editing":[91],"(PAE)":[92],"method.":[93],"Besides":[94],"refining":[95],"original":[97,153],"for":[99],"image":[100],"generation,":[101],"further":[103],"employ":[104],"an":[105],"online":[106],"reinforcement":[107],"learning":[108],"strategy":[109],"explore":[111],"each":[119],"word,":[120],"leading":[121],"dynamic":[124],"The":[127],"re-wardfunction":[128],"during":[129],"training":[130],"encourages":[131],"model":[133],"consider":[135],"aesthetic":[136],"score,":[137],"semantic":[138,162],"consistency,":[139],"user":[141],"prefer-ences.":[142],"Experimental":[143],"results":[144],"demonstrate":[145],"that":[146],"our":[147],"proposed":[148],"method":[149],"effectively":[150],"improves":[151],"prompts,":[154],"generating":[155],"visually":[156],"more":[157],"appealing":[158],"images":[159],"while":[160],"maintaining":[161],"alignment.":[163],"Code":[164],"is":[165],"available":[166],"at":[167],"this":[168],"https":[169],"URL.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}