{"id":"https://openalex.org/W4403791011","doi":"https://doi.org/10.1145/3664647.3681577","title":"Partially Aligned Cross-modal Retrieval via Optimal Transport-based Prototype Alignment Learning","display_name":"Partially Aligned Cross-modal Retrieval via Optimal Transport-based Prototype Alignment Learning","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791011","doi":"https://doi.org/10.1145/3664647.3681577"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681577","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681577","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5020018413","display_name":"Junsheng Wang","orcid":"https://orcid.org/0000-0003-1605-1219"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junsheng Wang","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032269269","display_name":"Tiantian Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiantian Gong","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031758174","display_name":"Yan Yan","orcid":"https://orcid.org/0000-0002-7618-119X"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Yan","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, USA","institution_ids":["https://openalex.org/I180949307"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020018413"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":0.2493,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54495083,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"701","last_page":"709"},"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9961000084877014,"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":0.7881572246551514},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7798819541931152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4241953492164612},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3571566641330719},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07273682951927185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7881572246551514},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7798819541931152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4241953492164612},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3571566641330719},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07273682951927185},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681577","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681577","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":35,"referenced_works":["https://openalex.org/W1949478088","https://openalex.org/W1964073652","https://openalex.org/W2007972815","https://openalex.org/W2013535308","https://openalex.org/W2030899956","https://openalex.org/W2106277773","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2605649771","https://openalex.org/W2725249286","https://openalex.org/W2765440071","https://openalex.org/W2914911817","https://openalex.org/W2954672622","https://openalex.org/W2963314614","https://openalex.org/W2963526065","https://openalex.org/W2964081303","https://openalex.org/W2964216321","https://openalex.org/W2967957126","https://openalex.org/W2997072756","https://openalex.org/W3091560917","https://openalex.org/W3093199520","https://openalex.org/W3105976186","https://openalex.org/W3155366680","https://openalex.org/W3168698796","https://openalex.org/W3212272595","https://openalex.org/W4213303451","https://openalex.org/W4256361765","https://openalex.org/W4297323222","https://openalex.org/W4304092489","https://openalex.org/W4312384316","https://openalex.org/W4317496691","https://openalex.org/W4361801760","https://openalex.org/W4387294141","https://openalex.org/W4387546363","https://openalex.org/W4390872786"],"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":{"Supervised":[0],"cross-modal":[1,58,83,106,148,188],"retrieval":[2,59,149],"(CMR)":[3],"achieves":[4],"excellent":[5],"performance":[6,150],"thanks":[7],"to":[8,18,69,104],"the":[9,70,100,116,141,152,161,178],"semantic":[10,20],"information":[11,108],"provided":[12],"by":[13],"its":[14],"labels,":[15],"which":[16,175],"helps":[17],"establish":[19,87,105],"correlations":[21,79,89,179],"between":[22,80,90,109,118,180],"samples":[23,110,119,182,185],"from":[24],"different":[25],"modalities.":[26],"However,":[27],"in":[28,75,207],"real-world":[29,209],"scenarios,":[30],"there":[31],"often":[32],"exists":[33],"a":[34,54,125,168,187],"large":[35],"amount":[36],"of":[37,134,143],"unlabeled":[38],"and":[39,93,111,113,120,183,205],"unpaired":[40],"multimodal":[41,145],"training":[42],"data,":[43],"rendering":[44],"existing":[45],"methods":[46],"unfeasible.":[47],"To":[48,95,158],"address":[49,160],"this":[50,135],"issue,":[51],"we":[52,86,98,137,166],"propose":[53],"novel":[55],"partially":[56,153],"aligned":[57,154],"method":[60,200],"called":[61],"Optimal":[62],"Transport-based":[63],"Prototype":[64],"Alignment":[65],"Learning":[66],"(OTPAL).":[67],"Due":[68],"high":[71],"computational":[72],"complexity":[73],"involved":[74],"directly":[76],"establishing":[77],"matching":[78,88],"unannotated":[81],"unaligned":[82],"samples,":[84],"instead,":[85],"shared":[91],"prototypes":[92,123],"samples.":[94],"be":[96],"specific,":[97],"employ":[99],"optimal":[101],"transport":[102],"algorithm":[103],"alignment":[107,129],"prototypes,":[112],"then":[114],"minimize":[115],"distance":[117],"their":[121],"corresponding":[122],"through":[124,186],"specially":[126],"designed":[127],"prototype":[128],"loss.":[130],"As":[131],"an":[132],"extension":[133],"paper,":[136],"also":[138],"extensively":[139],"investigate":[140],"influence":[142],"incomplete":[144,181],"data":[146],"on":[147,193],"under":[151],"setting":[155],"proposed":[156],"above.":[157],"further":[159],"above":[162],"more":[163],"challenging":[164],"scenario,":[165],"raise":[167],"scalable":[169],"prototype-based":[170],"neighbor":[171,184],"feature":[172],"completion":[173],"method,":[174],"better":[176],"captures":[177],"self-attention":[189],"mechanism.":[190],"Experimental":[191],"results":[192],"four":[194],"benchmark":[195],"datasets":[196],"show":[197],"that":[198],"our":[199],"can":[201],"obtain":[202],"satisfactory":[203],"accuracy":[204],"scalability":[206],"various":[208],"scenarios.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}