{"id":"https://openalex.org/W4415538087","doi":"https://doi.org/10.1145/3746027.3755794","title":"Context-aware Image-to-Music Generation via Bridging Modalities through Musical Captions","display_name":"Context-aware Image-to-Music Generation via Bridging Modalities through Musical Captions","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538087","doi":"https://doi.org/10.1145/3746027.3755794"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755794","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755794","pdf_url":null,"source":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755794","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shilin Liu","orcid":"https://orcid.org/0009-0005-6624-407X"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shilin Liu","raw_affiliation_strings":["Hokkaido University, Sapporo, Hokkaido, Japan"],"raw_orcid":"https://orcid.org/0009-0005-6624-407X","affiliations":[{"raw_affiliation_string":"Hokkaido University, Sapporo, Hokkaido, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015425921","display_name":"Kyohei Kamikawa","orcid":"https://orcid.org/0000-0002-7054-7920"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kyohei Kamikawa","raw_affiliation_strings":["Hokkaido University, Sapporo, Hokkaido, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7054-7920","affiliations":[{"raw_affiliation_string":"Hokkaido University, Sapporo, Hokkaido, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033215072","display_name":"Keisuke Maeda","orcid":"https://orcid.org/0000-0001-8039-3462"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Maeda","raw_affiliation_strings":["Hokkaido University, Sapporo, Hokkaido, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8039-3462","affiliations":[{"raw_affiliation_string":"Hokkaido University, Sapporo, Hokkaido, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009032240","display_name":"Takahiro Ogawa","orcid":"https://orcid.org/0000-0001-5332-8112"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Ogawa","raw_affiliation_strings":["Hokkaido University, Sapporo, Hokkaido, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5332-8112","affiliations":[{"raw_affiliation_string":"Hokkaido University, Sapporo, Hokkaido, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":null,"display_name":"Miki Haseyama","orcid":"https://orcid.org/0000-0003-1496-1761"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Miki Haseyama","raw_affiliation_strings":["Hokkaido University, Sapporo, Hokkaido, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1496-1761","affiliations":[{"raw_affiliation_string":"Hokkaido University, Sapporo, Hokkaido, Japan","institution_ids":["https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205349734"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28713021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2235","last_page":"2243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9937000274658203,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9937000274658203,"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":0.9918000102043152,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9830999970436096,"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/musical","display_name":"Musical","score":0.769599974155426},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5375999808311462},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.508899986743927},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4830000102519989},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4708999991416931},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4571000039577484},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.37529999017715454},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.35929998755455017}],"concepts":[{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.769599974155426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742900013923645},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5375999808311462},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.508899986743927},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4708999991416931},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46239998936653137},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40459999442100525},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3614000082015991},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.35929998755455017},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.35109999775886536},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32010000944137573},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C109568592","wikidata":"https://www.wikidata.org/wiki/Q207628","display_name":"Musical composition","level":3,"score":0.2818000018596649},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25760000944137573},{"id":"https://openalex.org/C196017715","wikidata":"https://www.wikidata.org/wiki/Q862597","display_name":"Musical form","level":3,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755794","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755794","pdf_url":null,"source":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755794","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755794","pdf_url":null,"source":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1667593550","display_name":null,"funder_award_id":"JP24K02942,JP23K21676, JP23K11211, JP23KJ0046","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2972478942","https://openalex.org/W4376131672","https://openalex.org/W4389371446","https://openalex.org/W4391407078","https://openalex.org/W4399743538","https://openalex.org/W4402703029","https://openalex.org/W4407408487"],"related_works":[],"abstract_inverted_index":{"Music":[0],"generation":[1,9,41,74],"has":[2,12,59],"developed":[3],"remarkably,":[4],"and":[5,55,57,120,165,205,225,234],"research":[6],"on":[7,175],"music":[8,33,97,224],"from":[10],"text":[11,24],"progressed.":[13],"However,":[14],"there":[15],"are":[16,52],"cases":[17],"where":[18],"it":[19,58],"is":[20,35,42,46,181,197],"difficult":[21,61],"to":[22,31,62,92,183,189,217],"use":[23],"as":[25,113],"the":[26,81,84,94,105,109,118,131,138,142,171,185,190,207,219,222,226,240],"query":[27],"when":[28],"users":[29],"want":[30],"obtain":[32],"that":[34,136],"suitable":[36],"for":[37],"images,":[38,50],"while":[39],"image-to-music":[40,73,212],"still":[43],"unexplored.":[44],"There":[45],"a":[47,176,201],"gap":[48],"between":[49,117],"which":[51,79],"visual":[53],"content,":[54],"music,":[56],"been":[60],"associate":[63],"them":[64],"directly.":[65],"To":[66],"address":[67],"this":[68],"problem,":[69],"we":[70,155],"realize":[71],"an":[72,89,114,157],"method":[75,124,209],"through":[76,130,147,231],"musical":[77,101,134,148,168,186,195],"captions":[78,87,102,135,149,169],"describe":[80,137],"characteristics":[82],"of":[83,96,108,133,141,221,242],"music.":[85,121,143],"Musical":[86],"possess":[88],"enhanced":[90],"capability":[91],"steer":[93],"process":[95],"generation.":[98,213],"Therefore,":[99],"if":[100],"effectively":[103],"convey":[104],"intended":[106],"message":[107],"image,":[110],"they":[111],"serve":[112],"excellent":[115],"intermediary":[116],"images":[119,146,164,230],"The":[122,193,237,246],"proposed":[123,208,244],"connects":[125],"these":[126],"two":[127],"different":[128],"modalities":[129],"medium":[132],"specialized":[139],"content":[140],"By":[144],"generating":[145],"using":[150],"multi-modal":[151,177],"large":[152,178],"language":[153,179],"models,":[154],"construct":[156],"image-musical":[158],"caption":[159,187,196],"pair":[160],"dataset.":[161],"Using":[162],"query-similar":[163],"their":[166],"paired":[167],"in":[170],"dataset,":[172],"in-context":[173],"learning":[174],"model":[180],"conducted":[182,215],"generate":[184],"corresponding":[188],"target":[191,229],"image.":[192],"generated":[194,223],"then":[198],"input":[199],"into":[200],"text-to-music":[202],"generative":[203],"model,":[204],"thus,":[206],"enables":[210],"high-quality":[211],"We":[214],"experiments":[216],"evaluate":[218],"quality":[220],"consistency":[227],"with":[228],"both":[232],"subjective":[233],"objective":[235],"metrics.":[236],"results":[238],"confirm":[239],"effectiveness":[241],"our":[243],"method.":[245],"code":[247],"can":[248],"be":[249],"found":[250],"at":[251],"https://github.com/lsllsls/CAI2M.":[252]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}