{"id":"https://openalex.org/W4308222471","doi":"https://doi.org/10.1145/3536221.3556575","title":"Multi-level Fusion of Multi-modal Semantic Embeddings for Zero Shot Learning","display_name":"Multi-level Fusion of Multi-modal Semantic Embeddings for Zero Shot Learning","publication_year":2022,"publication_date":"2022-11-04","ids":{"openalex":"https://openalex.org/W4308222471","doi":"https://doi.org/10.1145/3536221.3556575"},"language":"en","primary_location":{"id":"doi:10.1145/3536221.3556575","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3536221.3556575","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3536221.3556575","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3536221.3556575","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079767092","display_name":"Zhe Kong","orcid":"https://orcid.org/0000-0001-8680-5376"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"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":"Zhe Kong","raw_affiliation_strings":["State Key Laboratory of Information Security, Institute of Information Engineering, CAS, China and School of Cyber Security, University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0001-8680-5376","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Information Security, Institute of Information Engineering, CAS, China and School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101903908","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-1069-4830"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Institute of Information Engineering, CAS, China"],"raw_orcid":"https://orcid.org/0000-0002-1069-4830","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, CAS, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072074260","display_name":"Neng Gao","orcid":"https://orcid.org/0000-0002-0870-5692"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Neng Gao","raw_affiliation_strings":["State Key Laboratory of Information Security, Institute of Information Engineering, CAS, China"],"raw_orcid":"https://orcid.org/0000-0002-0870-5692","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Information Security, Institute of Information Engineering, CAS, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021535403","display_name":"Yifei Zhang","orcid":"https://orcid.org/0000-0001-7068-1700"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifei Zhang","raw_affiliation_strings":["State Key Laboratory of Information Security, Institute of Information Engineering, CAS, China"],"raw_orcid":"https://orcid.org/0000-0001-7068-1700","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Information Security, Institute of Information Engineering, CAS, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001346139","display_name":"Yuhan Liu","orcid":"https://orcid.org/0000-0003-3576-6666"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"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":"Yuhan Liu","raw_affiliation_strings":["State Key Laboratory of Information Security, Institute of Information Engineering, CAS, China and School of Cyber Security, University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0003-3576-6666","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Information Security, Institute of Information Engineering, CAS, China and School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086465211","display_name":"Chenyang Tu","orcid":"https://orcid.org/0000-0003-2130-0531"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Tu","raw_affiliation_strings":["State Key Laboratory of Information Security, Institute of Information Engineering, CAS, China"],"raw_orcid":"https://orcid.org/0000-0003-2130-0531","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Information Security, Institute of Information Engineering, CAS, China","institution_ids":["https://openalex.org/I4210156404"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1687,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42947417,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"310","last_page":"318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9854000210762024,"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/T11606","display_name":"Infrastructure Maintenance and Monitoring","score":0.9210000038146973,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6950646042823792},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5976037383079529},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5350080132484436},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.44510388374328613},{"id":"https://openalex.org/keywords/semantic-memory","display_name":"Semantic memory","score":0.4431758224964142},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44210460782051086},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4305751919746399},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4220760762691498},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35424894094467163},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.1758059859275818}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6950646042823792},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5976037383079529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5350080132484436},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.44510388374328613},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.4431758224964142},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44210460782051086},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4305751919746399},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4220760762691498},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35424894094467163},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.1758059859275818},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3536221.3556575","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3536221.3556575","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3536221.3556575","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3536221.3556575","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3536221.3556575","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3536221.3556575","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308222471.pdf","grobid_xml":"https://content.openalex.org/works/W4308222471.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2044913453","https://openalex.org/W2070148066","https://openalex.org/W2097117768","https://openalex.org/W2098411764","https://openalex.org/W2109317801","https://openalex.org/W2128532956","https://openalex.org/W2194775991","https://openalex.org/W2289084343","https://openalex.org/W2611632661","https://openalex.org/W2924476266","https://openalex.org/W2932399282","https://openalex.org/W2962762077","https://openalex.org/W2963486920","https://openalex.org/W2963499153","https://openalex.org/W2964086552","https://openalex.org/W3109728025","https://openalex.org/W3135367836","https://openalex.org/W3143107425"],"related_works":["https://openalex.org/W2521519254","https://openalex.org/W3139833644","https://openalex.org/W3123110765","https://openalex.org/W4383553409","https://openalex.org/W2104948296","https://openalex.org/W1735800226","https://openalex.org/W4285172739","https://openalex.org/W3123208392","https://openalex.org/W2212953222","https://openalex.org/W4372316851"],"abstract_inverted_index":{"Zero":[0],"shot":[1,60,158],"learning":[2,61],"aims":[3],"to":[4,23,31,52,81,84,101,107],"recognize":[5],"objects":[6],"whose":[7],"instances":[8],"may":[9],"not":[10],"be":[11,130],"covered":[12],"by":[13],"the":[14,24,45,64,87,118,124],"training":[15],"data.":[16],"To":[17,72],"generalize":[18],"knowledge":[19,33,54,110],"from":[20,34,69],"seen":[21],"classes":[22,48,90],"novel":[25],"ones,":[26],"semantic":[27,39,42,67,96,114],"space":[28],"is":[29,153],"built":[30],"embed":[32],"various":[35,145],"views":[36],"into":[37],"multi-modal":[38,113],"embeddings.":[40,97],"Existing":[41],"embeddings":[43,68,115],"neglect":[44],"relationships":[46],"between":[47,55,66,89],"which":[49],"are":[50],"essential":[51],"transfer":[53],"classes.":[56],"Moreover,":[57],"existing":[58],"zero":[59,157],"models":[62],"ignore":[63],"complementarity":[65],"different":[70],"modalities.":[71],"tackle":[73],"these":[74],"problems,":[75],"in":[76,112],"this":[77],"work,":[78],"we":[79,99],"resort":[80],"graph":[82],"theory":[83],"explicitly":[85],"model":[86,106,139],"interdependence":[88],"and":[91,133],"then":[92],"obtain":[93],"new":[94],"modal":[95],"Furthermore,":[98],"pioneer":[100],"propose":[102],"a":[103],"multi-level":[104,127],"fusion":[105,122,128],"effectively":[108],"combine":[109],"encoded":[111],"together.":[116],"By":[117],"virtue":[119],"of":[120,126],"subsequent":[121],"block,":[123],"results":[125,143],"can":[129],"furtherly":[131],"enriched":[132],"fused.":[134],"Experiments":[135],"show":[136],"that":[137,150],"our":[138,151],"could":[140],"achieve":[141],"promising":[142],"on":[144],"datasets.":[146],"Ablation":[147],"study":[148],"suggests":[149],"method":[152],"well":[154],"suited":[155],"for":[156],"learning.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}