{"id":"https://openalex.org/W4401991197","doi":"https://doi.org/10.1109/icmew63481.2024.10645422","title":"Multimodal Semantic-Aware Automatic Colorization with Diffusion Prior","display_name":"Multimodal Semantic-Aware Automatic Colorization with Diffusion Prior","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4401991197","doi":"https://doi.org/10.1109/icmew63481.2024.10645422"},"language":"en","primary_location":{"id":"doi:10.1109/icmew63481.2024.10645422","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icmew63481.2024.10645422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5115695092","display_name":"Han Wang","orcid":"https://orcid.org/0000-0002-4705-8432"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Wang","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037457833","display_name":"Xinning Chai","orcid":"https://orcid.org/0009-0007-7310-6796"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinning Chai","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383452","display_name":"Yiwen Wang","orcid":"https://orcid.org/0000-0002-7594-1396"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwen Wang","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100779798","display_name":"Yuhong Zhang","orcid":"https://orcid.org/0000-0003-0942-9068"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhong Zhang","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101577089","display_name":"Rong Xie","orcid":"https://orcid.org/0000-0002-8261-5337"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Xie","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002404808","display_name":"Li Song","orcid":"https://orcid.org/0000-0002-7124-5182"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Song","raw_affiliation_strings":["Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12496","display_name":"Color perception and design","score":0.9399999976158142,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12496","display_name":"Color perception and design","score":0.9399999976158142,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7727590203285217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5511091947555542},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4428021311759949},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39302414655685425}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7727590203285217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5511091947555542},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4428021311759949},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39302414655685425},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew63481.2024.10645422","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icmew63481.2024.10645422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2245625259","https://openalex.org/W2950689937","https://openalex.org/W3010626953","https://openalex.org/W3034838697","https://openalex.org/W3036167779","https://openalex.org/W3100394409","https://openalex.org/W3162926177","https://openalex.org/W3212516020","https://openalex.org/W4230012894","https://openalex.org/W4236325002","https://openalex.org/W4288099666","https://openalex.org/W4301206121","https://openalex.org/W4311802540","https://openalex.org/W4311806086","https://openalex.org/W4312783155","https://openalex.org/W4312933868","https://openalex.org/W4312940821","https://openalex.org/W4385270985","https://openalex.org/W4386076215","https://openalex.org/W4387322643","https://openalex.org/W4390873054","https://openalex.org/W4391602018","https://openalex.org/W4403947072","https://openalex.org/W6765779288","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6790749177","https://openalex.org/W6791353385","https://openalex.org/W6795288823","https://openalex.org/W6811013733","https://openalex.org/W6847118160"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Colorizing":[0],"grayscale":[1],"images":[2],"offers":[3],"an":[4,31],"engaging":[5],"visual":[6,101],"experience.":[7],"Existing":[8],"automatic":[9,32],"colorization":[10,33],"methods":[11,126],"often":[12],"fail":[13],"to":[14,19,35,49,77,95],"generate":[15],"satisfactory":[16],"results":[17],"due":[18],"incorrect":[20],"semantic":[21,75],"colors":[22,108],"and":[23,85,98,122,132],"unsaturated":[24],"colors.":[25,88],"In":[26],"this":[27],"work,":[28],"we":[29,64,71],"propose":[30],"pipeline":[34,105],"overcome":[36,56],"these":[37],"challenges.":[38],"We":[39],"leverage":[40],"the":[41,46,57,61,66,79,82],"extraordinary":[42],"generative":[43],"ability":[44],"of":[45,129],"diffusion":[47,62],"prior":[48],"synthesize":[50],"color":[51],"with":[52],"plausible":[53,111],"semantics.":[54,112],"To":[55],"artifacts":[58],"introduced":[59],"by":[60],"prior,":[63],"apply":[65],"luminance":[67],"conditional":[68],"guidance.":[69],"Moreover,":[70],"adopt":[72],"multimodal":[73],"high-level":[74],"priors":[76],"help":[78],"model":[80],"understand":[81],"image":[83],"content":[84],"deliver":[86],"saturated":[87,107],"Besides,":[89],"a":[90],"luminance-aware":[91],"decoder":[92],"is":[93],"designed":[94],"restore":[96],"details":[97],"enhance":[99],"overall":[100],"quality.":[102],"The":[103],"proposed":[104,117],"synthesizes":[106],"while":[109],"maintaining":[110],"Experiments":[113],"indicate":[114],"that":[115],"our":[116],"method":[118],"considers":[119],"both":[120],"diversity":[121],"fidelity,":[123],"surpassing":[124],"previous":[125],"in":[127],"terms":[128],"perceptual":[130],"realism":[131],"gain":[133],"most":[134],"human":[135],"preference.":[136]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}