{"id":"https://openalex.org/W4313011276","doi":"https://doi.org/10.1109/mmsp55362.2022.9948891","title":"Knowledge Graph enhanced Multimodal Learning for Few-shot Visual Recognition","display_name":"Knowledge Graph enhanced Multimodal Learning for Few-shot Visual Recognition","publication_year":2022,"publication_date":"2022-09-26","ids":{"openalex":"https://openalex.org/W4313011276","doi":"https://doi.org/10.1109/mmsp55362.2022.9948891"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp55362.2022.9948891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp55362.2022.9948891","pdf_url":null,"source":{"id":"https://openalex.org/S4363605768","display_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","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 24th International Workshop on Multimedia Signal Processing (MMSP)","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/A5065577924","display_name":"Mengya Han","orcid":"https://orcid.org/0000-0003-3499-3832"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mengya Han","raw_affiliation_strings":["School of Computer Science, Wuhan University,Hubei Luojia Laboratory,Wuhan,China","Hubei Luojia Laboratory, School of Computer Science, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University,Hubei Luojia Laboratory,Wuhan,China","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I196699116"]},{"raw_affiliation_string":"Hubei Luojia Laboratory, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074672983","display_name":"Yibing Zhan","orcid":"https://orcid.org/0000-0003-3180-0484"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibing Zhan","raw_affiliation_strings":["JD Explore Academy,Beijing,China","JD Explore Academy, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD Explore Academy,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD Explore Academy, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085309099","display_name":"Baosheng Yu","orcid":"https://orcid.org/0000-0002-0761-7893"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Baosheng Yu","raw_affiliation_strings":["School of Computer Science, The University of Sydney,Sydney,Australia","School of Computer Science, The University of Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney,Sydney,Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"School of Computer Science, The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039158745","display_name":"Yong Luo","orcid":"https://orcid.org/0000-0002-2296-6370"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Luo","raw_affiliation_strings":["School of Computer Science, Wuhan University,Hubei Luojia Laboratory,Wuhan,China","Hubei Luojia Laboratory, School of Computer Science, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University,Hubei Luojia Laboratory,Wuhan,China","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I196699116"]},{"raw_affiliation_string":"Hubei Luojia Laboratory, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060042752","display_name":"Bo Du","orcid":"https://orcid.org/0000-0002-0059-8458"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Du","raw_affiliation_strings":["School of Computer Science, Wuhan University,Hubei Luojia Laboratory,Wuhan,China","Hubei Luojia Laboratory, School of Computer Science, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University,Hubei Luojia Laboratory,Wuhan,China","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I196699116"]},{"raw_affiliation_string":"Hubei Luojia Laboratory, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["JD Explore Academy,Beijing,China","JD Explore Academy, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD Explore Academy,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD Explore Academy, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5065577924"],"corresponding_institution_ids":["https://openalex.org/I196699116","https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.1039,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.33392588,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"32","issue":null,"first_page":"1","last_page":"6"},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9934999942779541,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9014000296592712,"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/computer-science","display_name":"Computer science","score":0.7765375375747681},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.591526210308075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5737889409065247},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.560642421245575},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5372047424316406},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5153002738952637},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5026421546936035},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46479859948158264},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.44172734022140503},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.43865203857421875},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.43709808588027954},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4168263077735901},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41051948070526123},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3854779005050659},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3591819405555725},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.13823136687278748}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7765375375747681},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.591526210308075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5737889409065247},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.560642421245575},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5372047424316406},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5153002738952637},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5026421546936035},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46479859948158264},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.44172734022140503},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.43865203857421875},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.43709808588027954},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4168263077735901},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41051948070526123},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3854779005050659},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3591819405555725},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.13823136687278748},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp55362.2022.9948891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp55362.2022.9948891","pdf_url":null,"source":{"id":"https://openalex.org/S4363605768","display_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","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 24th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G2898152415","display_name":null,"funder_award_id":"62002090","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":35,"referenced_works":["https://openalex.org/W2115733720","https://openalex.org/W2601450892","https://openalex.org/W2604763608","https://openalex.org/W2787035179","https://openalex.org/W2913318911","https://openalex.org/W2962895018","https://openalex.org/W2963070905","https://openalex.org/W2963341924","https://openalex.org/W2963559058","https://openalex.org/W2964105864","https://openalex.org/W2964112702","https://openalex.org/W2980347982","https://openalex.org/W2990216037","https://openalex.org/W3035143213","https://openalex.org/W3108975329","https://openalex.org/W3139143706","https://openalex.org/W3172122903","https://openalex.org/W3173908982","https://openalex.org/W3176127409","https://openalex.org/W3177423475","https://openalex.org/W3184256368","https://openalex.org/W3205249428","https://openalex.org/W4288573225","https://openalex.org/W4295521014","https://openalex.org/W6717697761","https://openalex.org/W6735236233","https://openalex.org/W6735913928","https://openalex.org/W6736057607","https://openalex.org/W6748284727","https://openalex.org/W6753311412","https://openalex.org/W6759807521","https://openalex.org/W6767471572","https://openalex.org/W6784643021","https://openalex.org/W6791909203","https://openalex.org/W6797879730"],"related_works":["https://openalex.org/W4389505417","https://openalex.org/W2604454537","https://openalex.org/W2962931510","https://openalex.org/W2808284704","https://openalex.org/W2897702399","https://openalex.org/W4380551887","https://openalex.org/W4206028705","https://openalex.org/W2757431232","https://openalex.org/W2941608206","https://openalex.org/W4285159263"],"abstract_inverted_index":{"Few-shot":[0],"learning":[1],"(FSL)":[2],"aims":[3],"to":[4,34,40,59,88,95,149,152,165],"learn":[5,35,166],"a":[6,13,30,51,85,97,133],"classifier":[7],"for":[8,81,101,170,188,222],"novel":[9],"classes":[10],"with":[11],"only":[12,47],"few":[14],"labeled":[15,72],"samples":[16,73],"per":[17],"category":[18,145],"available.":[19],"The":[20,178],"mainstream":[21],"FSL":[22,109,208],"approaches":[23,45],"fall":[24],"in":[25,76,122,132,176,197],"the":[26,61,67,71,79,90,113,119,126,140,144,154,167,192,216,219,232],"meta-learning":[27,99],"paradigm,":[28],"where":[29],"meta-learner":[31],"is":[32,84,162,195],"used":[33],"transferable":[36],"knowledge":[37,68,134],"and":[38,57,124,129,146,180,186,211,225],"generalize":[39],"new":[41,98],"tasks.":[42],"However,":[43],"these":[44],"usually":[46],"leverage":[48],"information":[49,62,80,114,121,131,221],"from":[50,63,115],"single":[52],"modality":[53],"(e.g.,":[54,66],"visual":[55,103,120,174,179],"image)":[56],"fail":[58],"explore":[60],"other":[64,150],"modalities":[65],"graph).":[69],"Since":[70],"are":[74,183],"scarce":[75],"FSL,":[77],"increasing":[78],"each":[82,171],"example":[83],"possible":[86],"solution":[87],"improve":[89,153],"performance.":[91],"This":[92],"motivates":[93],"us":[94],"develop":[96],"framework":[100,194],"few-shot":[102,223],"recognition":[104],"termed":[105],"Knowledge":[106],"Graph":[107],"enhanced":[108],"(KGFSL),":[110],"which":[111],"combines":[112],"multiple":[116],"modalities:":[117],"1)":[118],"images":[123],"2)":[125],"rich":[127],"semantics":[128],"structural":[130],"graph":[135,158],"(KG).":[136],"Specifically,":[137],"KGFSL":[138],"exploits":[139],"word":[141],"embedding":[142],"of":[143,218],"its":[147],"relationship":[148],"categories":[151],"visual-based":[155],"models.":[156],"A":[157],"convolutional":[159],"network":[160],"(GCN)":[161],"first":[163],"introduced":[164],"semantic":[168,181],"embeddings":[169,182],"node":[172],"(a":[173],"category)":[175],"KG.":[177],"then":[184],"aligned":[185],"combined":[187],"final":[189],"prediction.":[190],"Finally,":[191],"whole":[193],"trained":[196],"an":[198],"end-to-end":[199],"manner.":[200],"We":[201],"conduct":[202],"extensive":[203],"experiments":[204],"on":[205],"two":[206],"widely-used":[207],"benchmarks:":[209],"miniImageNet":[210],"tieredImageNet.":[212],"Experimental":[213],"results":[214],"demonstrate":[215],"effectiveness":[217],"multimodal":[220],"learning,":[224],"our":[226],"proposed":[227],"method":[228],"can":[229],"significantly":[230],"outperform":[231],"state-of-the-art":[233],"approaches.":[234]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}