{"id":"https://openalex.org/W4387677990","doi":"https://doi.org/10.1109/icac57885.2023.10275301","title":"Att-Sinkhorn: Multimodal Alignment with Sinkhorn-based Deep Attention Architecture","display_name":"Att-Sinkhorn: Multimodal Alignment with Sinkhorn-based Deep Attention Architecture","publication_year":2023,"publication_date":"2023-08-30","ids":{"openalex":"https://openalex.org/W4387677990","doi":"https://doi.org/10.1109/icac57885.2023.10275301"},"language":"en","primary_location":{"id":"doi:10.1109/icac57885.2023.10275301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icac57885.2023.10275301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 28th International Conference on Automation and Computing (ICAC)","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/A5023579469","display_name":"Qianxia Ma","orcid":"https://orcid.org/0000-0002-6635-2792"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qianxia Ma","raw_affiliation_strings":["Ant Group,Shanghai,China","Ant Group, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group,Shanghai,China","institution_ids":[]},{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100753657","display_name":"Ming Zhang","orcid":"https://orcid.org/0000-0001-5202-5574"},"institutions":[{"id":"https://openalex.org/I169199633","display_name":"Aston University","ror":"https://ror.org/05j0ve876","country_code":"GB","type":"education","lineage":["https://openalex.org/I169199633"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ming Zhang","raw_affiliation_strings":["Aston University,Birmingham,UK","Aston University, Birmingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aston University,Birmingham,UK","institution_ids":["https://openalex.org/I169199633"]},{"raw_affiliation_string":"Aston University, Birmingham, UK","institution_ids":["https://openalex.org/I169199633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090522574","display_name":"Yan Tang","orcid":"https://orcid.org/0000-0001-6476-8228"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Tang","raw_affiliation_strings":["Ant Group,Hangzhou,China","Ant Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group,Hangzhou,China","institution_ids":[]},{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011008665","display_name":"Zhen Huang","orcid":"https://orcid.org/0000-0003-4819-373X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhen Huang","raw_affiliation_strings":["Ant Group,Hangzhou,China","Ant Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group,Hangzhou,China","institution_ids":[]},{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.991100013256073,"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":0.7663716673851013},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4845353960990906},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45535990595817566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40424880385398865},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3362533748149872},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1465587317943573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7663716673851013},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4845353960990906},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45535990595817566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40424880385398865},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3362533748149872},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1465587317943573},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icac57885.2023.10275301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icac57885.2023.10275301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 28th International Conference on Automation and Computing (ICAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1686810756","https://openalex.org/W1895577753","https://openalex.org/W1902237438","https://openalex.org/W2097117768","https://openalex.org/W2111725927","https://openalex.org/W2159243025","https://openalex.org/W2171361956","https://openalex.org/W2194775991","https://openalex.org/W2619383789","https://openalex.org/W2972463723","https://openalex.org/W2979675031","https://openalex.org/W3047682456","https://openalex.org/W4206471589","https://openalex.org/W4298333447","https://openalex.org/W6630875275","https://openalex.org/W6637373629","https://openalex.org/W6639478124","https://openalex.org/W6683512859","https://openalex.org/W6685230081"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Multimodal":[0],"alignment":[1,29,37,54,112],"aims":[2],"to":[3,80,86,106],"establish":[4],"a":[5,35,118,150],"matching":[6,56],"relationship":[7],"between":[8,58,75,161],"multimodal":[9,31,154,178],"features,":[10,32],"connecting":[11],"parts":[12],"of":[13,27,30,96,126,142,173],"different":[14,59,81],"modalities":[15,82],"that":[16],"contain":[17],"the":[18,25,28,41,53,63,68,73,76,90,93,97,124,130,140,143,171,174],"same":[19],"or":[20],"similar":[21],"semantics.":[22],"To":[23,138],"increase":[24],"accuracy":[26],"we":[33,146],"propose":[34],"modality":[36],"method":[38],"based":[39,122],"on":[40,123,149],"Sinkhorn":[42,131],"metric":[43],"and":[44,55,129,163,168],"attention":[45],"mechanism":[46],"-":[47],"Att-Sinkhorn":[48,175],"algorithm.":[49],"The":[50,110],"algorithm":[51,91,132,176],"converts":[52],"problem":[57,66,101,113,121],"modal":[60],"features":[61],"into":[62],"discrete":[64,99],"Monge":[65,100],"in":[67,153],"optimal":[69],"transport,":[70],"which":[71,158],"compares":[72],"distance":[74],"probability":[77],"distributions":[78],"corresponding":[79],"directly.":[83],"In":[84],"order":[85],"get":[87],"practical":[88],"solutions,":[89],"obtains":[92],"approximate":[94],"solution":[95],"original":[98],"by":[102],"introducing":[103],"entropy":[104],"regularization":[105],"perform":[107],"Kantorovich":[108],"relaxation.":[109],"transformed":[111],"can":[114],"be":[115],"considered":[116],"as":[117],"matrix":[119],"scaling":[120],"principle":[125],"mass":[127],"conservation,":[128],"is":[133],"used":[134],"for":[135,177],"iterative":[136],"solutions.":[137],"verify":[139],"effectiveness":[141,172],"Att-Sinikhorn":[144],"algorithm,":[145],"adopt":[147],"experiments":[148],"typical":[151],"task":[152],"alignment,":[155],"image":[156],"captioning,":[157],"requires":[159],"mapping":[160],"textual":[162],"visual":[164],"information.":[165],"Empirical":[166],"results":[167],"analysis":[169],"indicate":[170],"alignment.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}