{"id":"https://openalex.org/W4416966011","doi":"https://doi.org/10.1109/tmm.2025.3639903","title":"CrossHypergraph: Consistent High-Order Semantic Network for Few-Shot Image Classification","display_name":"CrossHypergraph: Consistent High-Order Semantic Network for Few-Shot Image Classification","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4416966011","doi":"https://doi.org/10.1109/tmm.2025.3639903"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2025.3639903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3639903","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-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":null,"display_name":"Yucheng Zhang","orcid":"https://orcid.org/0009-0003-0766-7115"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yucheng Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-0766-7115","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Wang","orcid":"https://orcid.org/0009-0005-0558-111X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-0558-111X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379616","display_name":"Shuo Zhang","orcid":"https://orcid.org/0000-0003-4622-0669"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Zhang","raw_affiliation_strings":["Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, School of Computer Science &amp; Technology, Beijing Jiaotong University, Beijing, China","Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, School of Computer &amp; Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4622-0669","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, School of Computer Science &amp; Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, School of Computer &amp; Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074480499","display_name":"Biao Leng","orcid":"https://orcid.org/0000-0003-3588-5622"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Leng","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3588-5622","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19582969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"1277","last_page":"1288"},"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":0.9718000292778015,"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":0.9718000292778015,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0038999998942017555,"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":0.0031999999191612005,"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/hypergraph","display_name":"Hypergraph","score":0.7042999863624573},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5242999792098999},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48890000581741333},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.48890000581741333},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4607999920845032},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41269999742507935},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.39469999074935913},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.3804999887943268},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.3707999885082245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8544999957084656},{"id":"https://openalex.org/C2781221856","wikidata":"https://www.wikidata.org/wiki/Q840247","display_name":"Hypergraph","level":2,"score":0.7042999863624573},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5242999792098999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4977000057697296},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4607999920845032},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40459999442100525},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.39469999074935913},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3707999885082245},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.357699990272522},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3427000045776367},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3084999918937683},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.30480000376701355},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.30239999294281006},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.3003999888896942},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.28850001096725464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2870999872684479},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C2778816267","wikidata":"https://www.wikidata.org/wiki/Q21015578","display_name":"Semantic query","level":4,"score":0.2777999937534332},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3639903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3639903","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1410676039","display_name":null,"funder_award_id":"62372032","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":54,"referenced_works":["https://openalex.org/W2081580037","https://openalex.org/W2194775991","https://openalex.org/W2897169468","https://openalex.org/W2907492528","https://openalex.org/W2928798948","https://openalex.org/W2943605315","https://openalex.org/W2963101867","https://openalex.org/W2963936326","https://openalex.org/W2964105864","https://openalex.org/W2965572487","https://openalex.org/W3024314529","https://openalex.org/W3030401348","https://openalex.org/W3034187513","https://openalex.org/W3034637015","https://openalex.org/W3094502228","https://openalex.org/W3094724482","https://openalex.org/W3095388829","https://openalex.org/W3117115365","https://openalex.org/W3175609671","https://openalex.org/W3176341011","https://openalex.org/W3181932393","https://openalex.org/W3194746126","https://openalex.org/W3197005357","https://openalex.org/W3202188231","https://openalex.org/W3208426666","https://openalex.org/W4205277845","https://openalex.org/W4205536765","https://openalex.org/W4214562728","https://openalex.org/W4221161731","https://openalex.org/W4282926996","https://openalex.org/W4287121509","https://openalex.org/W4292433237","https://openalex.org/W4307340220","https://openalex.org/W4312526008","https://openalex.org/W4312935555","https://openalex.org/W4321780077","https://openalex.org/W4375946439","https://openalex.org/W4382461145","https://openalex.org/W4385768182","https://openalex.org/W4386065712","https://openalex.org/W4389060294","https://openalex.org/W4389338651","https://openalex.org/W4390874276","https://openalex.org/W4392114280","https://openalex.org/W4393033964","https://openalex.org/W4396754377","https://openalex.org/W4399188848","https://openalex.org/W4399517387","https://openalex.org/W4400216981","https://openalex.org/W4402727533","https://openalex.org/W4402754281","https://openalex.org/W4404124219","https://openalex.org/W4406858059","https://openalex.org/W4407212972"],"related_works":[],"abstract_inverted_index":{"Few-shot":[0],"classification":[1],"is":[2,46,106,141,150],"a":[3,98,128],"challenging":[4],"task":[5],"that":[6,175],"recognizes":[7],"novel":[8],"classes":[9,38],"by":[10],"learning":[11],"from":[12],"few":[13],"training":[14],"instances.":[15,121],"Metric-based":[16],"models":[17],"are":[18,39],"currently":[19],"the":[20,83,124,135],"most":[21],"effective":[22],"solutions":[23],"for":[24,48,117],"few-shot":[25,157,178],"classification.":[26,43,146],"In":[27],"these":[28,68],"models,":[29],"patch":[30],"feature":[31,63,103],"distances":[32],"between":[33],"query":[34,58,90,120],"instances":[35,91],"and":[36,57,89,119,155,164,185,192],"support":[37,56,88,118],"calculated":[40],"to":[41,51,61,72,92,108,143],"achieve":[42,144],"However,":[44],"it":[45],"difficult":[47],"patch-based":[49],"methods":[50],"mine":[52],"semantic":[53,115,131,183],"information":[54,116],"of":[55,87],"instances,":[59],"leading":[60],"inaccurate":[62],"similarity":[64],"measures.":[65],"To":[66],"address":[67],"problems,":[69],"we":[70,80,126],"propose":[71,127],"construct":[73],"CrossHypergraph":[74,110],"based":[75],"on":[76,123,152,189],"hypergraph":[77,95],"modeling.":[78],"Specifically,":[79],"first":[81],"align":[82],"local":[84],"prototype":[85],"vertices":[86],"model":[93],"consistent":[94,113,129,181],"structures.":[96],"Then":[97],"<italic":[99],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[100,167],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">vertex-hyperedge-vertex</i>-based":[101],"interactive":[102],"updating":[104],"mechanism":[105],"designed":[107,142],"generate":[109],"representation":[111],"with":[112],"high-order":[114,130,136,182],"Based":[122],"CrossHypergraph,":[125],"network,":[132],"in":[133],"which":[134],"semantic-based":[137],"weighted":[138],"metric":[139],"strategy":[140],"accurate":[145],"The":[147],"proposed":[148],"method":[149],"evaluated":[151],"general,":[153],"fine-grained,":[154],"cross-domain":[156],"benchmarks,":[158],"including":[159],"miniImageNet,":[160],"tieredImageNet,":[161],"CIFAR-FS,":[162],"FC100,":[163],"miniImageNet":[165],"<inline-formula":[166],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[168],"notation=\"LaTeX\">$\\rightarrow$</tex-math></inline-formula>":[169],"CUB":[170],"datasets.":[171],"Experimental":[172],"results":[173],"show":[174],"our":[176],"CrossHypergraph-based":[177],"classifier":[179],"generates":[180],"features,":[184],"achieves":[186],"state-of-the-art":[187],"performance":[188],"both":[190],"1-shot":[191],"5-shot":[193],"tasks.":[194]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-03T00:00:00"}