{"id":"https://openalex.org/W4293518982","doi":"https://doi.org/10.1109/icme52920.2022.9859738","title":"Fine-Grained Cross-Modal Retrieval with Triple-Streamed Memory Fusion Transformer Encoder","display_name":"Fine-Grained Cross-Modal Retrieval with Triple-Streamed Memory Fusion Transformer Encoder","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293518982","doi":"https://doi.org/10.1109/icme52920.2022.9859738"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859738","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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/A5048432022","display_name":"Weikuo Guo","orcid":"https://orcid.org/0000-0003-2830-3962"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weikuo Guo","raw_affiliation_strings":["Dalian University of Technology"],"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005195235","display_name":"Huaibo Huang","orcid":"https://orcid.org/0000-0001-5866-2283"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaibo Huang","raw_affiliation_strings":["University of Chinese Academy of Sciences","National Laboratory of Pattern Recognition, CASIA"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082414888","display_name":"Xiangwei Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangwei Kong","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112749024","display_name":"Ran He","orcid":"https://orcid.org/0000-0002-3807-991X"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran He","raw_affiliation_strings":["University of Chinese Academy of Sciences","National Laboratory of Pattern Recognition, CASIA"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA","institution_ids":["https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048432022"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.1199,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.40446314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"06"},"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":0.998199999332428,"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":0.9973000288009644,"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/encoder","display_name":"Encoder","score":0.6308566331863403},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5979673862457275},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5320262312889099},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4863477349281311},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.24340423941612244},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.1569463312625885},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.15027183294296265},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11823630332946777},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0821046233177185}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6308566331863403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5979673862457275},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5320262312889099},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4863477349281311},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.24340423941612244},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.1569463312625885},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.15027183294296265},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11823630332946777},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0821046233177185},{"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:10.1109/icme52920.2022.9859738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859738","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8750985170","display_name":null,"funder_award_id":"61772111","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2185175083","https://openalex.org/W2481240925","https://openalex.org/W2737766105","https://openalex.org/W2774267535","https://openalex.org/W2896457183","https://openalex.org/W2962964995","https://openalex.org/W2979304729","https://openalex.org/W2986670728","https://openalex.org/W2998356391","https://openalex.org/W3010363512","https://openalex.org/W3035454331","https://openalex.org/W3035552787","https://openalex.org/W3035605030","https://openalex.org/W3092820619","https://openalex.org/W3110042533","https://openalex.org/W3118694826","https://openalex.org/W3171668871","https://openalex.org/W3175888430","https://openalex.org/W3189718596","https://openalex.org/W3190055600","https://openalex.org/W3206477365","https://openalex.org/W3213100861","https://openalex.org/W6639102338","https://openalex.org/W6740863234","https://openalex.org/W6749537441","https://openalex.org/W6755207826","https://openalex.org/W6779546310","https://openalex.org/W6787902397"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Recently,":[0],"the":[1,11,16,51,55,64,69,80,85,92,98,112,123],"powerful":[2],"attention":[3],"mechanism":[4],"has":[5],"been":[6],"wildly":[7],"used":[8],"to":[9,83,91,110],"learn":[10],"fine-grained":[12,47],"cross-modal":[13,48,99],"correspondences.":[14],"However,":[15],"trade-off":[17],"between":[18,79],"effectiveness":[19],"and":[20,67,77],"efficiency":[21],"sometimes":[22],"bothers":[23],"existing":[24],"attention-mechanism-based":[25],"meth-ods.":[26],"To":[27,62],"address":[28],"this":[29],"deficiency,":[30],"we":[31],"propose":[32],"a":[33,38,71,103],"novel":[34],"Triple-streamed":[35],"architecture":[36],"with":[37],"newly":[39],"designed":[40,76],"Memory":[41],"fusion":[42,73],"Transformer":[43],"Encoder":[44],"(Tri-MTE)":[45],"for":[46],"retrieval.":[49],"Specifically,":[50],"whole":[52],"model":[53],"reserves":[54],"\u201clate":[56],"fusion\u201d":[57],"strategy":[58],"thus":[59],"ensuring":[60],"efficiency.":[61],"strengthen":[63],"inter-modality":[65],"interaction":[66],"improve":[68],"effectiveness,":[70],"memory":[72,105],"stream":[74],"is":[75,108],"inserted":[78],"modality":[81,93],"streams":[82],"remember":[84],"modality-irrelevant":[86],"infor-mation.":[87],"Encoding":[88],"such":[89],"information":[90],"represen-tation":[94],"would":[95],"significantly":[96],"enhance":[97],"retrieval":[100],"performance.":[101],"Finally,":[102],"bionic":[104],"activation":[106],"constrain-t":[107],"proposed":[109,124],"aid":[111],"learning":[113],"procedure.":[114],"Extensive":[115],"ex-periments":[116],"on":[117],"two":[118],"benchmark":[119],"datasets":[120],"show":[121],"that":[122],"method":[125],"achieves":[126],"promising":[127],"results.":[128]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}