{"id":"https://openalex.org/W4412403798","doi":"https://doi.org/10.1109/mmul.2025.3588977","title":"SD-Prompt: Learnable and Adaptive Prompts for Enhancing Subject-Driven Text-to-Image Synthesis","display_name":"SD-Prompt: Learnable and Adaptive Prompts for Enhancing Subject-Driven Text-to-Image Synthesis","publication_year":2025,"publication_date":"2025-07-01","ids":{"openalex":"https://openalex.org/W4412403798","doi":"https://doi.org/10.1109/mmul.2025.3588977"},"language":"en","primary_location":{"id":"doi:10.1109/mmul.2025.3588977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2025.3588977","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE MultiMedia","raw_type":"journal-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/A5076639787","display_name":"Mengling Xu","orcid":"https://orcid.org/0009-0002-4809-9129"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengling Xu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0002-4809-9129","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102776884","display_name":"Ming Tao","orcid":"https://orcid.org/0000-0002-4662-7170"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Tao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-4662-7170","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440133","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0002-8662-9488"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-8662-9488","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":null,"display_name":"Bing-Kun Bao","orcid":"https://orcid.org/0000-0001-5956-831X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5956-831X","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13210555,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"3","first_page":"94","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9724000096321106,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9724000096321106,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9275000095367432,"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":0.9083999991416931,"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/computer-science","display_name":"Computer science","score":0.7533433437347412},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.6109960079193115},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.45435065031051636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43722572922706604},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41995203495025635},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3629211485385895},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32773804664611816},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.25842487812042236}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7533433437347412},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.6109960079193115},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.45435065031051636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43722572922706604},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41995203495025635},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3629211485385895},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32773804664611816},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25842487812042236}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmul.2025.3588977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2025.3588977","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE MultiMedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G5851403343","display_name":null,"funder_award_id":"62325206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G626853494","display_name":null,"funder_award_id":"62206132","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":13,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W2533598788","https://openalex.org/W2886641317","https://openalex.org/W2966792645","https://openalex.org/W3199400376","https://openalex.org/W4312977351","https://openalex.org/W4379466097","https://openalex.org/W4385245566","https://openalex.org/W4386071848","https://openalex.org/W4387934929","https://openalex.org/W4389524329","https://openalex.org/W4392902491","https://openalex.org/W4411630052"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4388258507","https://openalex.org/W2392013855","https://openalex.org/W4318064328","https://openalex.org/W2357926602","https://openalex.org/W3200517220","https://openalex.org/W2374569605","https://openalex.org/W2386062718","https://openalex.org/W4393047559","https://openalex.org/W899618282"],"abstract_inverted_index":{"Large-scale":[0],"pre-trained":[1,22],"text-to-image":[2],"models":[3],"have":[4],"made":[5],"incredible":[6],"progress":[7],"recently.":[8],"When":[9],"synthesizing":[10],"the":[11,21,30,52,64,75,109,119,127,137],"appearance":[12],"of":[13,32,55,66,129],"subjects":[14],"in":[15,44,131,153],"given":[16],"texts,":[17],"existing":[18],"works":[19],"fine-tune":[20],"model":[23],"or":[24],"use":[25],"manual":[26,49],"prompts":[27,50,115,130],"to":[28,92,116],"improve":[29],"quality":[31,65],"images.":[33],"However,":[34],"fine-tuning":[35],"requires":[36],"storing":[37],"parameters":[38],"for":[39,121],"each":[40],"subject,":[41],"which":[42,58],"results":[43,144],"expensive":[45],"computational":[46,71,94],"costs,":[47,72],"and":[48,69,114,156],"need":[51,120],"artificial":[53],"selection":[54,105],"different":[56],"subjects,":[57],"brings":[59],"subjective":[60],"uncertainties.":[61],"To":[62,125],"enhance":[63],"synthetic":[67],"images":[68],"reduce":[70,93],"we":[73,86,100,134],"introduce":[74],"<bold":[76,81],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[77,79,82],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">S</b>ubject-<bold":[78],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">D</b>riven":[80],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Prompt</b>":[83],"(SD-Prompt).":[84],"Specifically,":[85],"propose":[87,101],"a":[88,102],"prompt":[89,104],"generation":[90],"module":[91,106],"costs":[95],"through":[96],"learnable":[97],"prefixes.":[98],"Furthermore,":[99],"text-adaptive":[103],"that":[107,146],"evaluates":[108],"feature":[110],"similarity":[111],"between":[112],"texts":[113],"automatically":[117],"accommodate":[118],"subject-driven":[122],"image":[123,154],"generation.":[124],"explore":[126],"performance":[128],"complex":[132],"scenarios,":[133],"also":[135],"collect":[136],"CC3M-S5C":[138],"dataset":[139],"from":[140],"CC3M":[141],"dataset.":[142],"Experimental":[143],"show":[145],"our":[147],"work":[148],"outperforms":[149],"other":[150],"methods":[151],"both":[152],"fidelity":[155],"text-image":[157],"semantic":[158],"consistency.":[159]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}