{"id":"https://openalex.org/W4392903035","doi":"https://doi.org/10.1109/icassp48485.2024.10448330","title":"Bridging the Gap: Sketch to Color Diffusion Model with Semantic Prompt Learning","display_name":"Bridging the Gap: Sketch to Color Diffusion Model with Semantic Prompt Learning","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903035","doi":"https://doi.org/10.1109/icassp48485.2024.10448330"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100387096","display_name":"Ning Wang","orcid":"https://orcid.org/0000-0001-8903-8790"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ning Wang","raw_affiliation_strings":["Dalian University of Technology"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072509864","display_name":"Yifei She","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifei She","raw_affiliation_strings":["Dalian University of Technology"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100745350","display_name":"Rui Xu","orcid":"https://orcid.org/0000-0003-0516-3629"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Xu","raw_affiliation_strings":["Dalian University of Technology"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395500","display_name":"Bin Liu","orcid":"https://orcid.org/0000-0002-5023-7167"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liu","raw_affiliation_strings":["Dalian University of Technology"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100616471","display_name":"Haojie Li","orcid":"https://orcid.org/0000-0003-3882-2205"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haojie Li","raw_affiliation_strings":["Dalian University of Technology"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443935","display_name":"Zhiyong Wang","orcid":"https://orcid.org/0000-0002-8043-0312"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wang","raw_affiliation_strings":["Dalian University of Technology","The University of Sydney"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"The University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100438119","display_name":"Zhihui Wang","orcid":"https://orcid.org/0000-0002-5011-9726"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Zhihui Wang","raw_affiliation_strings":["Dalian University of Technology","The University of Sydney"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"The University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100387096"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.5248,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61399838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4310","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":0.9962000250816345,"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":0.9962000250816345,"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":0.992900013923645,"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/T12908","display_name":"Media, Gender, and Advertising","score":0.9631999731063843,"subfield":{"id":"https://openalex.org/subfields/3318","display_name":"Gender Studies"},"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":0.7792847156524658},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.7730427384376526},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.7091645002365112},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.6062157154083252},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6041081547737122},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.538270115852356},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5329108238220215},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4958978593349457},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4369136691093445},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41054579615592957},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3990960419178009},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33871978521347046},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2905212640762329},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.1497991383075714},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13368821144104004},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.0775672197341919}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7792847156524658},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.7730427384376526},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7091645002365112},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.6062157154083252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6041081547737122},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.538270115852356},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5329108238220215},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4958978593349457},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4369136691093445},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41054579615592957},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3990960419178009},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33871978521347046},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2905212640762329},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.1497991383075714},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13368821144104004},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0775672197341919},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W69951162","https://openalex.org/W398859631","https://openalex.org/W2887240766","https://openalex.org/W2902318149","https://openalex.org/W2943887897","https://openalex.org/W2962793481","https://openalex.org/W2963904861","https://openalex.org/W2971074500","https://openalex.org/W3098736533","https://openalex.org/W3162926177","https://openalex.org/W3179041635","https://openalex.org/W3193744354","https://openalex.org/W3207692456","https://openalex.org/W4301206121","https://openalex.org/W4360884927","https://openalex.org/W4390873054","https://openalex.org/W4393148714","https://openalex.org/W6755312952","https://openalex.org/W6762931180","https://openalex.org/W6765779288","https://openalex.org/W6795288823","https://openalex.org/W6810940779","https://openalex.org/W6838629043","https://openalex.org/W6849949366"],"related_works":["https://openalex.org/W2128807628","https://openalex.org/W4234264766","https://openalex.org/W2415426693","https://openalex.org/W2307731113","https://openalex.org/W2473933584","https://openalex.org/W2932687906","https://openalex.org/W2384506582","https://openalex.org/W1999004178","https://openalex.org/W2280723418","https://openalex.org/W2350165951"],"abstract_inverted_index":{"Automatic":[0],"anime":[1,152],"sketch":[2,12,38,71,153],"colorization":[3,154],"aims":[4],"to":[5,18,25,39,52,113,116,149],"generate":[6,134],"a":[7,11,37,144],"color":[8,30,40],"image":[9,140],"from":[10],"image,":[13],"which":[14,107],"is":[15,84,104],"challenging":[16],"due":[17],"limited":[19],"structure":[20,56],"and":[21,28,57,72,94,101],"semantic":[22,29,44,50,58,81,136],"understanding,":[23],"leading":[24],"constrained":[26],"style,":[27],"inconsistency.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35],"introduce":[36,75],"diffusion":[41,64],"model":[42],"with":[43],"prompt":[45],"learning":[46,48,80],"(SPL),":[47],"better":[49],"prompts":[51],"stimulate":[53],"the":[54,68,89,95,102,123],"powerful":[55],"understanding":[59],"capabilities":[60],"of":[61,119],"large-scale":[62],"multi-modal":[63],"models,":[65],"effectively":[66],"bridging":[67],"gap":[69],"between":[70],"color.":[73],"We":[74],"two":[76],"distillation":[77,86,92,99,111,132],"strategies":[78,133],"for":[79],"prompts:":[82],"one":[83],"prediction-level":[85],"by":[87],"optimizing":[88],"global":[90],"knowledge":[91,98,115],"loss":[93,112],"local":[96],"activation":[97],"loss,":[100],"other":[103],"feature-level":[105],"distillation,":[106],"optimizes":[108],"hierarchy-wise":[109],"feature":[110],"transfer":[114],"output":[117],"features":[118],"different":[120],"hierarchies":[121],"in":[122,139],"model.":[124],"The":[125],"experimental":[126],"results":[127],"show":[128],"that":[129,142],"our":[130],"proposed":[131],"high-quality":[135],"prompts,":[137],"resulting":[138],"quality":[141],"exhibits":[143],"superior":[145],"visual":[146],"effect":[147],"compared":[148],"current":[150],"automatic":[151],"methods.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}