{"id":"https://openalex.org/W4409013547","doi":"https://doi.org/10.1109/bigcomp64353.2025.00070","title":"MOAT:An improved multi-modal matching algorithm based on object attention and tensor fusion","display_name":"MOAT:An improved multi-modal matching algorithm based on object attention and tensor fusion","publication_year":2025,"publication_date":"2025-02-09","ids":{"openalex":"https://openalex.org/W4409013547","doi":"https://doi.org/10.1109/bigcomp64353.2025.00070"},"language":"en","primary_location":{"id":"doi:10.1109/bigcomp64353.2025.00070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigcomp64353.2025.00070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data and Smart Computing (BigComp)","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/A5110535801","display_name":"Qian Xiong","orcid":"https://orcid.org/0009-0005-7143-3633"},"institutions":[{"id":"https://openalex.org/I38706770","display_name":"Guilin University of Technology","ror":"https://ror.org/03z391397","country_code":"CN","type":"education","lineage":["https://openalex.org/I38706770"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qian Xiong","raw_affiliation_strings":["Guilin University of Technology, 12 Jiangan Road,School of Computer Science and Engineering,Guilin,Guangxi,China"],"affiliations":[{"raw_affiliation_string":"Guilin University of Technology, 12 Jiangan Road,School of Computer Science and Engineering,Guilin,Guangxi,China","institution_ids":["https://openalex.org/I38706770"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101815430","display_name":"Xuanyi Wang","orcid":"https://orcid.org/0000-0002-8645-5393"},"institutions":[{"id":"https://openalex.org/I38706770","display_name":"Guilin University of Technology","ror":"https://ror.org/03z391397","country_code":"CN","type":"education","lineage":["https://openalex.org/I38706770"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanyi Wang","raw_affiliation_strings":["Guilin University of Technology, 12 Jiangan Road,School of Computer Science and Engineering,Guilin,Guangxi,China"],"affiliations":[{"raw_affiliation_string":"Guilin University of Technology, 12 Jiangan Road,School of Computer Science and Engineering,Guilin,Guangxi,China","institution_ids":["https://openalex.org/I38706770"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015654177","display_name":"Chao Jing","orcid":"https://orcid.org/0000-0002-4695-8746"},"institutions":[{"id":"https://openalex.org/I38706770","display_name":"Guilin University of Technology","ror":"https://ror.org/03z391397","country_code":"CN","type":"education","lineage":["https://openalex.org/I38706770"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Jing","raw_affiliation_strings":["Guilin University of Technology, 12 Jiangan Road,School of Computer Science and Engineering,Guilin,Guangxi,China"],"affiliations":[{"raw_affiliation_string":"Guilin University of Technology, 12 Jiangan Road,School of Computer Science and Engineering,Guilin,Guangxi,China","institution_ids":["https://openalex.org/I38706770"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110535801"],"corresponding_institution_ids":["https://openalex.org/I38706770"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06074123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"357","last_page":"360"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9891999959945679,"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":0.9891999959945679,"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":0.9876000285148621,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9717000126838684,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/modal","display_name":"Modal","score":0.7049567699432373},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.6152851581573486},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6147506833076477},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5481524467468262},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5190578103065491},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.478906512260437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4782218635082245},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4450923204421997},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4429049789905548},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4297771155834198},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19828057289123535},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07723128795623779},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.0682198703289032},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0496649444103241},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.048106491565704346}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7049567699432373},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6152851581573486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6147506833076477},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5481524467468262},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5190578103065491},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.478906512260437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4782218635082245},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4450923204421997},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4429049789905548},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4297771155834198},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19828057289123535},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07723128795623779},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0682198703289032},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0496649444103241},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.048106491565704346},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigcomp64353.2025.00070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigcomp64353.2025.00070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data and Smart Computing (BigComp)","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":11,"referenced_works":["https://openalex.org/W2277195237","https://openalex.org/W2962964995","https://openalex.org/W2981448908","https://openalex.org/W3035454331","https://openalex.org/W4313561518","https://openalex.org/W4390612216","https://openalex.org/W4391293808","https://openalex.org/W4393108955","https://openalex.org/W6747225742","https://openalex.org/W6791353385","https://openalex.org/W6870277322"],"related_works":["https://openalex.org/W1972035260","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W4301594054","https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W2152662039"],"abstract_inverted_index":{"This":[0],"work":[1],"proposes":[2],"an":[3],"improved":[4],"multi-modal":[5,36,81],"matching":[6,74,95,99,147],"algorithm":[7,21],"based":[8],"on":[9,60],"object":[10,39],"attention":[11,40],"and":[12,76,116,136,145],"tensor":[13,82],"fusion":[14,83],"(MOAT).":[15],"The":[16],"key":[17],"improvements":[18],"in":[19,128,143],"proposed":[20,86],"consists":[22],"of":[23,133],"two":[24,111],"parts:":[25],"(1)":[26],"In":[27],"order":[28],"to":[29,51,69,140],"construct":[30],"a":[31,80,102,125],"semantic":[32,56,63,104],"association":[33,64],"model":[34,41,77,84,142],"between":[35,73],"data,":[37],"the":[38,61,66,71,94],"with":[42,55,130],"same":[43],"feature":[44],"is":[45,68,85,108],"adopted":[46],"for":[47,98],"different":[48],"modal":[49,53],"features":[50,54],"generate":[52],"associations.":[57],"(2)":[58],"Based":[59],"established":[62],"model,":[65],"goal":[67],"find":[70],"trade-off":[72],"accuracy":[75],"complexity.":[78],"Then,":[79],"built":[87],"upon":[88],"bilinear":[89],"fusion,":[90],"which":[91],"mainly":[92],"learns":[93],"score":[96],"strategy":[97],"without":[100],"constructing":[101],"common":[103],"space.":[105],"Finally,":[106],"MOAT":[107,123],"verified":[109],"through":[110],"public":[112],"datasets,":[113],"MS":[114],"COCO":[115],"Flickr30k,":[117],"respectively.The":[118],"experimental":[119],"results":[120],"demonstrate":[121],"that":[122],"shows":[124],"better":[126],"performance":[127],"recall":[129],"maximum":[131],"improvement":[132],"$3.5":[134],"\\%$":[135,138],"$4.2":[137],"compared":[139],"CLIP":[141],"image":[144],"text":[146],"tasks.":[148]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}