{"id":"https://openalex.org/W4416017403","doi":"https://doi.org/10.1145/3746252.3760958","title":"MOVER: Multimodal Optimal Transport with Volume-based Embedding Regularization","display_name":"MOVER: Multimodal Optimal Transport with Volume-based Embedding Regularization","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416017403","doi":"https://doi.org/10.1145/3746252.3760958"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3760958","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3760958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","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/A5102631359","display_name":"Haochen You","orcid":"https://orcid.org/0009-0008-9178-2912"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haochen You","raw_affiliation_strings":["Columbia University, New York, NY, USA"],"raw_orcid":"https://orcid.org/0009-0008-9178-2912","affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075692649","display_name":"Baojing Liu","orcid":"https://orcid.org/0009-0007-1444-7267"},"institutions":[{"id":"https://openalex.org/I4210130954","display_name":"China Institute Of Communications","ror":"https://ror.org/0395ve714","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210130954"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baojing Liu","raw_affiliation_strings":["Hebei Institute of Communications, Shijiazhuang, Hebei, China"],"raw_orcid":"https://orcid.org/0009-0007-1444-7267","affiliations":[{"raw_affiliation_string":"Hebei Institute of Communications, Shijiazhuang, Hebei, China","institution_ids":["https://openalex.org/I4210130954"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0842,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89231779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5444","last_page":"5448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.2784000039100647,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.2784000039100647,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.22470000386238098,"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/T10860","display_name":"Speech and Audio Processing","score":0.13910000026226044,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/embedding","display_name":"Embedding","score":0.8109999895095825},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6305000185966492},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6136000156402588},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5414000153541565},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4830000102519989},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.47920000553131104},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.47699999809265137},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.45890000462532043}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8109999895095825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7293000221252441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6496000289916992},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6305000185966492},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6136000156402588},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5414000153541565},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","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":0.47920000553131104},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.45890000462532043},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.44119998812675476},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41909998655319214},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40790000557899475},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2639000117778778}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3760958","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3760958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","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":10,"referenced_works":["https://openalex.org/W2425121537","https://openalex.org/W2593116425","https://openalex.org/W2989322838","https://openalex.org/W3015371781","https://openalex.org/W3015591594","https://openalex.org/W4386071707","https://openalex.org/W4396816283","https://openalex.org/W4401863453","https://openalex.org/W4402703093","https://openalex.org/W4408692328"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,22,29,45,95,112,131],"multimodal":[3,73],"learning":[4],"have":[5],"largely":[6],"relied":[7],"on":[8,100],"pairwise":[9],"contrastive":[10],"objectives":[11],"to":[12,35,67,123],"align":[13],"different":[14],"modalities,":[15],"such":[16],"as":[17],"text,":[18],"video,":[19],"and":[20,40,71,115,127],"audio,":[21],"a":[23,54,77,82,96],"shared":[24],"embedding":[25,134],"space.":[26,135],"While":[27],"effective":[28],"bi-modal":[30],"setups,":[31],"these":[32],"approaches":[33],"struggle":[34],"generalize":[36],"across":[37,92],"multiple":[38],"modalities":[39,94],"often":[41],"lack":[42],"semantic":[43],"structure":[44],"high-dimensional":[46],"spaces.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51],"propose":[52],"MOVER,":[53],"novel":[55],"framework":[56],"that":[57,105],"combines":[58],"optimal":[59],"transport-based":[60],"soft":[61],"alignment":[62,91],"with":[63,81],"volume-based":[64],"geometric":[65,83],"regularization":[66],"build":[68],"semantically":[69],"aligned":[70],"structured":[72],"representations.":[74],"By":[75],"integrating":[76],"transport-guided":[78],"matching":[79],"mechanism":[80],"volume":[84],"minimization":[85],"objective":[86],"(GAVE),":[87],"MOVER":[88,106],"encourages":[89],"consistent":[90],"all":[93],"modality-agnostic":[97],"manner.":[98],"Experiments":[99],"text-video-audio":[101],"retrieval":[102],"tasks":[103],"demonstrate":[104],"significantly":[107],"outperforms":[108],"prior":[109],"state-of-the-art":[110],"methods":[111],"both":[113],"zero-shot":[114],"finetuned":[116],"settings.":[117],"Additional":[118],"analysis":[119],"shows":[120],"improved":[121],"generalization":[122],"unseen":[124],"modality":[125],"combinations":[126],"stronger":[128],"structural":[129],"consistency":[130],"the":[132],"learned":[133]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2025-11-08T00:00:00"}