{"id":"https://openalex.org/W4412888206","doi":"https://doi.org/10.18653/v1/2025.findings-acl.647","title":"CoT-VTM: Visual-to-Music Generation with Chain-of-Thought Reasoning","display_name":"CoT-VTM: Visual-to-Music Generation with Chain-of-Thought Reasoning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888206","doi":"https://doi.org/10.18653/v1/2025.findings-acl.647"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.647","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.647","pdf_url":"https://aclanthology.org/2025.findings-acl.647.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.647.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119181365","display_name":"Xikang Guan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xikang Guan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040423463","display_name":"\u6b63\u96c4 \u5c0f\u8c37","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng Gu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066091819","display_name":"Jing Huo","orcid":"https://orcid.org/0000-0002-8504-455X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Huo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119181366","display_name":"Tianyu Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyu Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100324800","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0003-0051-9120"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12493","last_page":"12510"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9923999905586243,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9923999905586243,"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":0.9879999756813049,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9818000197410583,"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":0.5048004388809204},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3974326550960541},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.26076966524124146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5048004388809204},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3974326550960541},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26076966524124146}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.647","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.647","pdf_url":"https://aclanthology.org/2025.findings-acl.647.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.647","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.647","pdf_url":"https://aclanthology.org/2025.findings-acl.647.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888206.pdf","grobid_xml":"https://content.openalex.org/works/W4412888206.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"application":[1],"of":[2,31,40,96,112],"visual-to-music":[3,106],"generation":[4,63],"(VTM)":[5],"is":[6],"rapidly":[7],"growing.However,":[8],"current":[9],"VTM":[10],"methods":[11],"struggle":[12],"with":[13,72],"capturing":[14],"the":[15,29,38,80,97,110,138,146],"relationship":[16,99],"between":[17,44,82],"visuals":[18,45],"and":[19,37,46,85,100,127,162],"music":[20,70,128],"in":[21,75],"open-domain":[22,76],"settings,":[23],"mainly":[24],"due":[25],"to":[26,60],"two":[27],"challenges:":[28],"lack":[30],"large-scale,":[32],"high-quality":[33],"visual-music":[34,98],"paired":[35,65],"datasets":[36],"absence":[39],"direct":[41],"semantic":[42],"correspondence":[43],"music.In":[47],"this":[48],"work,":[49],"we":[50,92,114,130],"propose":[51],"CoT-VTM,":[52],"a":[53,102,132,149],"framework":[54],"that":[55],"distills":[56],"Chain-of-Thought":[57],"(CoT)":[58],"reasoning":[59,111,120],"enable":[61],"visual-tomusic":[62],"without":[64],"data,":[66],"while":[67,145],"efficiently":[68],"producing":[69],"aligned":[71],"visual":[73,126],"content":[74],"settings.We":[77],"first":[78,139],"bridge":[79],"gap":[81],"visual,":[83],"music,":[84],"text":[86],"data":[87],"using":[88],"appropriate":[89],"foundation":[90],"models.Next,":[91],"identify":[93],"key":[94],"elements":[95],"design":[101,131],"CoT":[103],"prompt":[104],"for":[105],"mapping.To":[107],"fully":[108],"distill":[109],"CoT,":[113],"incorporate":[115],"latent":[116],"information":[117],"from":[118],"intermediate":[119],"steps":[121],"as":[122],"supervisory":[123],"signals":[124],"alongside":[125],"supervision.Finally,":[129],"two-stage":[133],"mapping":[134],"distillation":[135],"training":[136],"process:":[137],"stage":[140],"uses":[141,148],"discriminative":[142],"MLP":[143],"modules,":[144],"second":[147],"generative":[150],"embedding":[151],"diffusion":[152],"model":[153,155],"(EmbedDiff).Our":[154],"achieves":[156],"optimal":[157],"performance":[158],"on":[159],"both":[160],"imageto-music":[161],"video-to-music":[163],"tasks.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}