{"id":"https://openalex.org/W7137928829","doi":"https://doi.org/10.1609/aaai.v40i29.39609","title":"Aligning the True Semantics: Constrained Decoupling and Distribution Sampling for Cross-Modal Alignment","display_name":"Aligning the True Semantics: Constrained Decoupling and Distribution Sampling for Cross-Modal Alignment","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137928829","doi":"https://doi.org/10.1609/aaai.v40i29.39609"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i29.39609","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i29.39609","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i29.39609","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiang Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lexin Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lexin Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Litian Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Litian Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Caiming Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caiming Zhang","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":"40","issue":"29","first_page":"24290","last_page":"24298"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9667999744415283,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9667999744415283,"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/T10028","display_name":"Topic Modeling","score":0.0044999998062849045,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0044999998062849045,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.5964000225067139},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.45489999651908875},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4104999899864197},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.38119998574256897},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.3702000081539154},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.3619999885559082},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.33959999680519104},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.33889999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6858000159263611},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5964000225067139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48809999227523804},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.45489999651908875},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4244000017642975},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3702000081539154},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3303000032901764},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3086000084877014},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.29170000553131104},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2818000018596649},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2815000116825104},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2680000066757202}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i29.39609","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i29.39609","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/39609","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/39609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i29.39609","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i29.39609","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1265043282","display_name":null,"funder_award_id":"62576193","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5338855155","display_name":null,"funder_award_id":"U22A2033","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Cross-modal":[0],"alignment":[1,86,101,146],"is":[2,46,69,115,134],"a":[3,98],"crucial":[4],"task":[5],"in":[6,40],"multimodal":[7],"learning":[8],"aimed":[9],"at":[10],"achieving":[11],"semantic":[12,33,52,59,75,85],"consistency":[13,30],"between":[14],"vision":[15],"and":[16,53,76,106,153],"language.":[17],"This":[18],"requires":[19],"that":[20],"image-text":[21],"pairs":[22],"exhibit":[23],"similar":[24],"semantics.":[25],"Traditional":[26],"algorithms":[27],"pursue":[28],"embedding":[29],"to":[31,47,117,125,136,166],"achieve":[32],"consistency,":[34],"ignoring":[35],"the":[36,41,49,58,93,120,138,142,145,157],"non-semantic":[37],"information":[38,89],"present":[39],"embedding.":[42],"An":[43],"intuitive":[44],"approach":[45],"decouple":[48,119],"embeddings":[50],"into":[51],"modality":[54,81,139],"components,":[55],"aligning":[56],"only":[57],"component.":[60],"However,":[61],"this":[62],"introduces":[63],"two":[64],"main":[65],"challenges:":[66],"(1)":[67,111],"There":[68],"no":[70],"established":[71],"standard":[72],"for":[73],"distinguishing":[74],"modal":[77],"information.":[78],"(2)":[79,129],"The":[80],"gap":[82],"can":[83],"cause":[84],"deviation":[87],"or":[88],"loss.":[90],"To":[91],"align":[92],"true":[94],"semantics,":[95],"we":[96],"propose":[97],"novel":[99],"cross-modal":[100],"algorithm":[102],"via":[103],"Constrained":[104],"Decoupling":[105],"Distribution":[107],"Sampling":[108],"(CDDS).":[109],"Specifically,":[110],"A":[112,130],"dual-path":[113],"UNet":[114],"introduced":[116],"adaptively":[118],"embeddings,":[121],"applying":[122],"multiple":[123],"constraints":[124],"ensure":[126],"effective":[127],"separation.":[128],"distribution":[131],"sampling":[132],"method":[133],"proposed":[135],"bridge":[137],"gap,":[140],"ensuring":[141],"rationality":[143],"of":[144,159],"process.":[147],"Extensive":[148],"experiments":[149],"on":[150],"various":[151],"benchmarks":[152],"model":[154],"backbones":[155],"demonstrate":[156],"superiority":[158],"CDDS,":[160],"outperforming":[161],"state-of-the-art":[162],"methods":[163],"by":[164],"6.6%":[165],"14.2%.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2026-03-11T00:00:00"}