{"id":"https://openalex.org/W7105698177","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228736","title":"MAMR: Modality-Aligned Multi-modal Retrieval","display_name":"MAMR: Modality-Aligned Multi-modal Retrieval","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W7105698177","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228736"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":null,"display_name":"YangZhen Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"YangZhen Xu","raw_affiliation_strings":["South China Normal University,School of Artificial Intelligence,Foshan,China"],"affiliations":[{"raw_affiliation_string":"South China Normal University,School of Artificial Intelligence,Foshan,China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":null,"display_name":"JiaWei Mo","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"JiaWei Mo","raw_affiliation_strings":["South China Normal University,School of Artificial Intelligence,Foshan,China"],"affiliations":[{"raw_affiliation_string":"South China Normal University,School of Artificial Intelligence,Foshan,China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":null,"display_name":"FangZhen Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I2799850029","display_name":"Dongguan University of Technology","ror":"https://ror.org/01m8p7q42","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029"]},{"id":"https://openalex.org/I4210151717","display_name":"XTC (China)","ror":"https://ror.org/046916w66","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210151717"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"FangZhen Lin","raw_affiliation_strings":["Dongguan NVT Technology Co.,Ltd,Manufacture Research&Development,DongGuan,China"],"affiliations":[{"raw_affiliation_string":"Dongguan NVT Technology Co.,Ltd,Manufacture Research&Development,DongGuan,China","institution_ids":["https://openalex.org/I2799850029","https://openalex.org/I4210151717"]}]},{"author_position":"middle","author":{"id":null,"display_name":"ZeBiao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ZeBiao Chen","raw_affiliation_strings":["South China Normal University,School of Artificial Intelligence,Foshan,China"],"affiliations":[{"raw_affiliation_string":"South China Normal University,School of Artificial Intelligence,Foshan,China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":null,"display_name":"ChengFeng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ChengFeng Chen","raw_affiliation_strings":["South China Normal University,School of Artificial Intelligence,Foshan,China"],"affiliations":[{"raw_affiliation_string":"South China Normal University,School of Artificial Intelligence,Foshan,China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"last","author":{"id":null,"display_name":"ShouQiang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ShouQiang Liu","raw_affiliation_strings":["South China Normal University,School of Artificial Intelligence,Foshan,China"],"affiliations":[{"raw_affiliation_string":"South China Normal University,School of Artificial Intelligence,Foshan,China","institution_ids":["https://openalex.org/I187400657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I187400657"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57791915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.948199987411499,"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":0.948199987411499,"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":0.04230000078678131,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.00139999995008111,"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/robustness","display_name":"Robustness (evolution)","score":0.673799991607666},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5716000199317932},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.5127000212669373},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.490200012922287},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4781000018119812},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4749999940395355},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.42149999737739563},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.41519999504089355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7415000200271606},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.673799991607666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6650000214576721},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5716000199317932},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.5127000212669373},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.490200012922287},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4781000018119812},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.42149999737739563},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.41519999504089355},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3093999922275543},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2939000129699707},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2919999957084656},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5252874493598938,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2162915993","https://openalex.org/W2947312908","https://openalex.org/W2963588253","https://openalex.org/W2964303913","https://openalex.org/W2966317026","https://openalex.org/W2968225067","https://openalex.org/W3021397474","https://openalex.org/W3099700870","https://openalex.org/W3217305727","https://openalex.org/W4226321975","https://openalex.org/W4252076394","https://openalex.org/W4306317212","https://openalex.org/W4312643954","https://openalex.org/W4312971273","https://openalex.org/W4319300119","https://openalex.org/W4385565470","https://openalex.org/W4385572252","https://openalex.org/W4386065803","https://openalex.org/W4387969587","https://openalex.org/W4389519872","https://openalex.org/W4389523839","https://openalex.org/W4390872646","https://openalex.org/W4402672071","https://openalex.org/W4402716379"],"related_works":[],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"(RAG)":[2],"is":[3],"a":[4,120,176],"mainstream":[5],"approach":[6,124,184],"to":[7,35,140,161],"tackling":[8],"complex":[9,76],"Visual":[10,18],"Question":[11,19],"Answering":[12,20],"(VQA)":[13],"tasks,":[14],"such":[15],"as":[16],"Knowledge-Based":[17],"(KB-VQA).":[21],"However,":[22],"previous":[23],"multimodal":[24,122],"retrieval":[25,123,158],"methods":[26,56,218],"typically":[27],"rely":[28],"on":[29,207],"pre-trained":[30],"textual":[31,93],"and":[32,40,59,70,138,153,168,180,210,219],"visual":[33,83,101,172,203],"models":[34],"generate":[36],"feature":[37,84,94,178],"representations":[38],"separately":[39],"retrieve":[41],"knowledge":[42],"bases":[43],"by":[44],"concatenating":[45],"vectors":[46,85],"directly":[47],"or":[48],"using":[49],"simple":[50],"networks":[51],"for":[52],"processing.":[53],"While":[54],"these":[55,116],"are":[57,86],"intuitive":[58],"effective,":[60],"they":[61],"often":[62],"overlook":[63],"the":[64,79,109,163,166,186,199,208],"deep":[65],"semantic":[66],"correlations":[67],"between":[68,105],"text":[69,139],"image,":[71],"limiting":[72],"their":[73],"robustness":[74,164],"in":[75,97,100,171],"scenarios.":[77],"Moreover,":[78],"spatial":[80,187],"dimensions":[81,188],"of":[82,92,111,165,189,201],"usually":[87],"significantly":[88,149],"higher":[89],"than":[90],"those":[91],"vectors,":[95],"resulting":[96],"considerable":[98],"redundancy":[99,170],"representations.":[102],"This":[103,183],"imbalance":[104],"modalities":[106],"further":[107],"undermines":[108],"effectiveness":[110],"modality":[112,127,151],"alignment.":[113],"To":[114],"address":[115],"issues,":[117],"we":[118,174],"propose":[119],"novel":[121],"with":[125],"enhanced":[126],"alignment":[128,152],"capabilities,":[129,155],"named":[130],"Modality-Aligned":[131],"Multimodal":[132],"Retrieval":[133],"(MAMR).":[134],"By":[135],"enabling":[136],"image":[137,190],"learn":[141],"relevant":[142],"information":[143],"from":[144],"each":[145],"other":[146],"mutually,":[147],"MAMR":[148,215],"improves":[150],"fusion":[154,181],"achieving":[156],"superior":[157],"performance.":[159],"Furthermore,":[160],"enhance":[162],"model":[167],"reduce":[169],"features,":[173],"introduce":[175],"multi-level":[177],"segmentation":[179],"method.":[182],"reduces":[185],"features":[191],"while":[192],"integrating":[193],"multi-scale":[194],"local":[195],"information,":[196],"thereby":[197],"strengthening":[198],"representation":[200],"global":[202],"features.":[204],"Experimental":[205],"results":[206],"OKVQA":[209],"EVQA":[211],"datasets":[212],"demonstrate":[213],"that":[214],"outperforms":[216],"numerous":[217],"achieves":[220],"state-of-the-art":[221],"(SOTA)":[222],"performance":[223],"across":[224],"most":[225],"evaluation":[226],"metrics.":[227]},"counts_by_year":[],"updated_date":"2025-11-15T23:13:30.683059","created_date":"2025-11-14T00:00:00"}