{"id":"https://openalex.org/W4293519407","doi":"https://doi.org/10.1109/icme52920.2022.9860026","title":"Instance-Level Semantic Alignment for Zero-Shot Cross-Modal Retrieval","display_name":"Instance-Level Semantic Alignment for Zero-Shot Cross-Modal Retrieval","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293519407","doi":"https://doi.org/10.1109/icme52920.2022.9860026"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9860026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9860026","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":"conference-paper","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/A5088756163","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0001-9839-966X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Wang","raw_affiliation_strings":["Center for Future Media & School of Computer Science and Engineering, University of Electronic Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media & School of Computer Science and Engineering, University of Electronic Science and Technology of China,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398570","display_name":"Yifan Wang","orcid":"https://orcid.org/0000-0002-6719-5063"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Wang","raw_affiliation_strings":["Center for Future Media & School of Computer Science and Engineering, University of Electronic Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media & School of Computer Science and Engineering, University of Electronic Science and Technology of China,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["Center for Future Media & School of Computer Science and Engineering, University of Electronic Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media & School of Computer Science and Engineering, University of Electronic Science and Technology of China,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020177102","display_name":"Zuo Cao","orcid":"https://orcid.org/0000-0001-9446-5105"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuo Cao","raw_affiliation_strings":["Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068562468","display_name":"Xunliang Cai","orcid":"https://orcid.org/0000-0003-0685-9556"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xunliang Cai","raw_affiliation_strings":["Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5548,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75449969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9994000196456909,"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":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.7865363359451294},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6790292263031006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5612845420837402},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.460308313369751},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4477965533733368},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4432534873485565},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4353387951850891},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40790748596191406},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.325591117143631},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1345769464969635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7865363359451294},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6790292263031006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5612845420837402},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.460308313369751},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4477965533733368},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4432534873485565},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4353387951850891},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40790748596191406},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.325591117143631},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1345769464969635},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9860026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9860026","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":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1900201161","display_name":null,"funder_award_id":"61976049,62072080","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1972420097","https://openalex.org/W2007972815","https://openalex.org/W2106277773","https://openalex.org/W2119775030","https://openalex.org/W2326180695","https://openalex.org/W2466618734","https://openalex.org/W2808336545","https://openalex.org/W2915533878","https://openalex.org/W2962856082","https://openalex.org/W2962945761","https://openalex.org/W2964130424","https://openalex.org/W2988772405","https://openalex.org/W2997918867","https://openalex.org/W3111984153","https://openalex.org/W3112919685","https://openalex.org/W3142108776","https://openalex.org/W3191326487","https://openalex.org/W6677994088","https://openalex.org/W6743443402","https://openalex.org/W6759047919","https://openalex.org/W6765975681","https://openalex.org/W6766095500","https://openalex.org/W6785876359","https://openalex.org/W6787508211"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2714992399","https://openalex.org/W2383812217","https://openalex.org/W2326515389","https://openalex.org/W2491005386"],"abstract_inverted_index":{"Zero-shot":[0],"Cross-Modal":[1],"Retrieval":[2],"(ZS-CMR)":[3],"is":[4],"challenging":[5],"due":[6],"to":[7,56,74,88],"the":[8,15,49,57,79,90,119,130,142,149],"heterogeneous":[9],"distributions":[10,117],"across":[11,18],"different":[12,33],"modalities":[13,34,94],"and":[14,20,98,108],"inconsistent":[16],"semantics":[17],"seen":[19],"unseen":[21],"classes.":[22],"Previous":[23],"methods":[24],"usually":[25],"perform":[26,129],"class-level":[27,52],"semantic":[28,105,122],"alignment":[29],"of":[30,40,51,59,78,140],"data":[31,91],"from":[32,92],"by":[35,118],"introducing":[36],"auxiliary":[37,126],"word":[38],"embeddings":[39],"class":[41],"labels,":[42],"which":[43],"have":[44],"a":[45,109],"fatal":[46],"limitation":[47],"as":[48],"learning":[50],"information":[53],"will":[54],"lead":[55],"ignorance":[58],"intra-modal":[60],"variance.":[61],"To":[62],"solve":[63],"this":[64],"problem,":[65],"we":[66],"propose":[67],"our":[68,146],"Instance-Level":[69],"Semantic":[70],"Alignment":[71],"(ILSA)":[72],"method":[73,147],"make":[75],"full":[76],"use":[77,83],"instance-level":[80,104,121],"information.":[81],"We":[82,128],"two":[84,93,138],"disentanglement":[85],"variational":[86],"auto-encoders":[87],"decompose":[89],"into":[95],"modal":[96,99],"specific":[97],"invariant":[100],"features.":[101],"With":[102],"an":[103],"features":[106],"extractor":[107],"distribution":[110],"generator,":[111],"ILSA":[112],"could":[113],"generate":[114],"more":[115],"appropriate":[116],"learned":[120],"features,":[123],"without":[124],"any":[125],"knowledge.":[127],"experiment":[131],"on":[132,137,153],"six":[133],"widely":[134],"used":[135],"datasets":[136],"scenarios":[139],"ZS-CMR,":[141],"results":[143],"show":[144],"that":[145],"establishes":[148],"new":[150],"state-of-the-art":[151],"performance":[152],"all":[154],"datasets.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}