{"id":"https://openalex.org/W3193135654","doi":"https://doi.org/10.1109/tpami.2021.3052490","title":"Few-Shot Image and Sentence Matching via Aligned Cross-Modal Memory","display_name":"Few-Shot Image and Sentence Matching via Aligned Cross-Modal Memory","publication_year":2021,"publication_date":"2021-02-25","ids":{"openalex":"https://openalex.org/W3193135654","doi":"https://doi.org/10.1109/tpami.2021.3052490","mag":"3193135654","pmid":"https://pubmed.ncbi.nlm.nih.gov/33460367"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2021.3052490","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3052490","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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":"Yan Huang","orcid":"https://orcid.org/0000-0002-8239-7229"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":["Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Center for Excellence in Brain Science and Intelligence Technology (CEBSIT), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8239-7229","affiliations":[{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Center for Excellence in Brain Science and Intelligence Technology (CEBSIT), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210097554","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingdong Wang","orcid":"https://orcid.org/0000-0002-4888-4445"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingdong Wang","raw_affiliation_strings":["Media Computing Group, Microsoft Research Asia, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4888-4445","affiliations":[{"raw_affiliation_string":"Media Computing Group, Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":null,"display_name":"Liang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Wang","raw_affiliation_strings":["Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Center for Excellence in Brain Science and Intelligence Technology (CEBSIT), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Center for Excellence in Brain Science and Intelligence Technology (CEBSIT), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210097554","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6326,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.66190084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"44","issue":"6","first_page":"2968","last_page":"2983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8381999731063843,"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":0.8381999731063843,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.02759999968111515,"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":0.025100000202655792,"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/sentence","display_name":"Sentence","score":0.7713000178337097},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6316999793052673},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6197999715805054},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5622000098228455},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.49380001425743103},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41499999165534973},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.3603000044822693}],"concepts":[{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7713000178337097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7458000183105469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6317999958992004},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6316999793052673},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6197999715805054},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5622000098228455},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.49380001425743103},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36239999532699585},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33970001339912415},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2825999855995178},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26499998569488525},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.260699987411499},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2021.3052490","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3052490","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:33460367","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33460367","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2222490201","display_name":null,"funder_award_id":"61806194","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5273665290","display_name":null,"funder_award_id":"Z201100006820079","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"},{"id":"https://openalex.org/G5858177368","display_name":null,"funder_award_id":"61525306","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6431871145","display_name":null,"funder_award_id":"61721004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7010190359","display_name":"\u6df1\u5ea6\u8ba4\u77e5\u795e\u7ecf\u7f51\u7edc\u7406\u8bba\u4e0e\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61633021","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7145271284","display_name":null,"funder_award_id":"61976132","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"},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1905882502","https://openalex.org/W1916445035","https://openalex.org/W1949478088","https://openalex.org/W1957706851","https://openalex.org/W2173180041","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2284126738","https://openalex.org/W2334493732","https://openalex.org/W2346425926","https://openalex.org/W2530887700","https://openalex.org/W2546696630","https://openalex.org/W2552579943","https://openalex.org/W2554906389","https://openalex.org/W2560920409","https://openalex.org/W2606473278","https://openalex.org/W2745461083","https://openalex.org/W2778100917","https://openalex.org/W2798280084","https://openalex.org/W2798782720","https://openalex.org/W2806331055","https://openalex.org/W2807887362","https://openalex.org/W2903529742","https://openalex.org/W2956018683","https://openalex.org/W2962739339","https://openalex.org/W2962781483","https://openalex.org/W2962870798","https://openalex.org/W2962964995","https://openalex.org/W2962990451","https://openalex.org/W2963012286","https://openalex.org/W2963040148","https://openalex.org/W2963052338","https://openalex.org/W2963088515","https://openalex.org/W2963389687","https://openalex.org/W2963467339","https://openalex.org/W2963486920","https://openalex.org/W2963863119","https://openalex.org/W2964092725","https://openalex.org/W2964120214","https://openalex.org/W2964187781","https://openalex.org/W2979304729","https://openalex.org/W2988823324","https://openalex.org/W2991118492","https://openalex.org/W6631516269","https://openalex.org/W6636510571","https://openalex.org/W6637373629","https://openalex.org/W6638318767","https://openalex.org/W6639102338","https://openalex.org/W6640212811","https://openalex.org/W6676647902","https://openalex.org/W6678360021","https://openalex.org/W6678470764","https://openalex.org/W6679844565","https://openalex.org/W6684821475","https://openalex.org/W6685183736","https://openalex.org/W6697449767","https://openalex.org/W6717697761","https://openalex.org/W6732742072","https://openalex.org/W6735236233","https://openalex.org/W6741383107","https://openalex.org/W6745654871","https://openalex.org/W6746260573","https://openalex.org/W6748083814","https://openalex.org/W6748284727","https://openalex.org/W6752083267","https://openalex.org/W6761665040"],"related_works":[],"abstract_inverted_index":{"Image":[0],"and":[1,9,34,42,54,77,80,102,112,139,145,164,167,170],"sentence":[2,78,168],"matching":[3,49],"has":[4,55],"attracted":[5],"much":[6],"attention":[7],"recently,":[8],"many":[10],"effective":[11],"methods":[12],"have":[13],"been":[14],"proposed":[15,176],"to":[16,89,149],"deal":[17,90],"with":[18,91],"it.":[19,92],"But":[20],"even":[21],"the":[22,134,143,172,175,180],"current":[23],"state-of-the-arts":[24],"still":[25],"cannot":[26],"well":[27],"associate":[28],"those":[29],"challenging":[30,72],"pairs":[31],"of":[32,117,152,161,174],"images":[33],"sentences":[35],"containing":[36],"few-shot":[37,48,75,100,118,138,163],"content":[38,141],"in":[39,63,104,142,159],"their":[40],"regions":[41,101],"words.":[43],"In":[44,66],"fact,":[45],"such":[46],"a":[47,57,105],"problem":[50,73],"is":[51],"seldom":[52],"studied":[53],"become":[56],"bottleneck":[58],"for":[59],"further":[60],"performance":[61],"improvement":[62],"real-world":[64],"applications.":[65],"this":[67,71],"work,":[68],"we":[69],"formulate":[70],"as":[74,120],"image":[76,144,166],"matching,":[79,169],"accordingly":[81],"propose":[82],"an":[83],"Aligned":[84],"Cross-Modal":[85],"Memory":[86],"(ACMM)":[87],"model":[88,94,129,177],"The":[93,128],"can":[95,130],"not":[96],"only":[97],"softly":[98],"align":[99],"words":[103],"weakly-supervised":[106],"manner,":[107],"but":[108],"also":[109,131],"persistently":[110],"store":[111],"update":[113],"cross-modal":[114],"prototypical":[115],"representations":[116],"classes":[119],"references,":[121],"without":[122],"using":[123],"any":[124],"groundtruth":[125],"region-word":[126],"correspondence.":[127],"adaptively":[132],"balance":[133],"relative":[135],"importance":[136],"between":[137],"common":[140],"sentence,":[146],"which":[147],"leads":[148],"better":[150],"measurement":[151],"overall":[153],"similarity.":[154],"We":[155],"perform":[156],"extensive":[157],"experiments":[158],"terms":[160],"both":[162],"conventional":[165],"demonstrate":[171],"effectiveness":[173],"by":[178],"achieving":[179],"state-of-the-art":[181],"results":[182],"on":[183],"two":[184],"public":[185],"benchmark":[186],"datasets.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2021-08-16T00:00:00"}