{"id":"https://openalex.org/W4283834642","doi":"https://doi.org/10.1145/3503161.3547961","title":"Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification","display_name":"Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4283834642","doi":"https://doi.org/10.1145/3503161.3547961"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547961","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547961","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5100335202","display_name":"Bo Zhang","orcid":"https://orcid.org/0000-0001-8052-782X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhang","raw_affiliation_strings":["Fudan University, Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075760208","display_name":"Jiakang Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiakang Yuan","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087869694","display_name":"Baopu Li","orcid":"https://orcid.org/0000-0002-9032-3991"},"institutions":[{"id":"https://openalex.org/I1342911587","display_name":"Oracle (United States)","ror":"https://ror.org/006c77m33","country_code":"US","type":"company","lineage":["https://openalex.org/I1342911587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baopu Li","raw_affiliation_strings":["Oracle Health and AI, Redwood City, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oracle Health and AI, Redwood City, CA, USA","institution_ids":["https://openalex.org/I1342911587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021220108","display_name":"Tao Chen","orcid":"https://orcid.org/0000-0002-0779-9818"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Chen","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102013595","display_name":"Jiayuan Fan","orcid":"https://orcid.org/0000-0001-7494-0255"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayuan Fan","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058342038","display_name":"Botian Shi","orcid":"https://orcid.org/0000-0003-3677-7252"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Botian Shi","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2135","last_page":"2144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9997000098228455,"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":0.9987000226974487,"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":0.7840431928634644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6552140712738037},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6031621098518372},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5096714496612549},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.483750581741333},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.4820885956287384},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4753943681716919},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4745757579803467},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.43254202604293823},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42802488803863525},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.41543048620224},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.343603253364563},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2605704367160797}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7840431928634644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6552140712738037},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6031621098518372},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5096714496612549},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.483750581741333},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.4820885956287384},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4753943681716919},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4745757579803467},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.43254202604293823},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42802488803863525},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.41543048620224},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.343603253364563},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2605704367160797},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547961","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547961","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7626924423","display_name":null,"funder_award_id":"62101137","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":35,"referenced_works":["https://openalex.org/W1954152232","https://openalex.org/W2138011018","https://openalex.org/W2193145675","https://openalex.org/W2752782242","https://openalex.org/W2909383239","https://openalex.org/W2963078860","https://openalex.org/W2963845150","https://openalex.org/W2965572487","https://openalex.org/W2982806777","https://openalex.org/W2991559096","https://openalex.org/W2998619563","https://openalex.org/W3012255272","https://openalex.org/W3030401348","https://openalex.org/W3034827765","https://openalex.org/W3035143213","https://openalex.org/W3035163205","https://openalex.org/W3035370595","https://openalex.org/W3035531117","https://openalex.org/W3035588244","https://openalex.org/W3035607448","https://openalex.org/W3092900959","https://openalex.org/W3093400813","https://openalex.org/W3096805028","https://openalex.org/W3106250896","https://openalex.org/W3107763055","https://openalex.org/W3131500599","https://openalex.org/W3176341011","https://openalex.org/W3192357270","https://openalex.org/W3195146806","https://openalex.org/W3199778150","https://openalex.org/W3205498423","https://openalex.org/W3206402863","https://openalex.org/W3207395111","https://openalex.org/W4213284407","https://openalex.org/W4214842573"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Few-shot":[0],"fine-grained":[1,18,50,109,165,173,189],"learning":[2,21],"aims":[3],"to":[4,34,63,159],"classify":[5],"a":[6,12,57,72],"query":[7],"image":[8],"into":[9],"one":[10],"of":[11,14,80,136,164],"set":[13],"support":[15],"categories":[16],"with":[17,133],"differences.":[19],"Although":[20],"different":[22,89],"objects'":[23],"local":[24,129,150],"differences":[25,163],"via":[26],"Deep":[27],"Neural":[28],"Networks":[29],"has":[30],"achieved":[31],"success,":[32],"how":[33],"exploit":[35],"the":[36,48,65,102,119,134,138,143,156,181],"query-support":[37],"cross-image":[38,66,124,182],"object":[39,67,130,183],"semantic":[40,68,184],"relations":[41],"in":[42,47,71,126,152],"Transformer-based":[43,58],"architecture":[44],"remains":[45],"under-explored":[46],"few-shot":[49],"scenario.":[51],"In":[52],"this":[53],"work,":[54],"we":[55],"propose":[56],"double-helix":[59],"model,":[60],"namely":[61],"HelixFormer,":[62],"achieve":[64],"relation":[69,185],"mining":[70],"bidirectional":[73],"and":[74,91,201],"symmetrical":[75],"manner.":[76],"The":[77],"HelixFormer":[78,177],"consists":[79],"two":[81],"steps:":[82],"1)":[83],"Relation":[84,113],"Mining":[85],"Process":[86,95],"(RMP)":[87],"across":[88],"branches,":[90],"2)":[92],"Representation":[93],"Enhancement":[94],"(REP)":[96],"within":[97],"each":[98,105,153],"individual":[99],"branch.":[100],"By":[101],"designed":[103],"RMP,":[104],"branch":[106],"can":[107,141,178],"extract":[108],"object-level":[110],"Cross-image":[111],"Semantic":[112],"Maps":[114],"(CSRMs)":[115],"using":[116],"information":[117],"from":[118],"other":[120],"branch,":[121,154],"ensuring":[122],"better":[123,193],"interaction":[125],"semantically":[127],"related":[128],"regions.":[131],"Further,":[132],"aid":[135],"CSRMs,":[137],"developed":[139],"REP":[140],"strengthen":[142],"extracted":[144],"features":[145],"for":[146,187],"those":[147],"discovered":[148],"semantically-related":[149],"regions":[151],"boosting":[155],"model's":[157],"ability":[158],"distinguish":[160],"subtle":[161],"feature":[162],"objects.":[166],"Extensive":[167],"experiments":[168],"conducted":[169],"on":[170],"five":[171],"public":[172],"benchmarks":[174],"demonstrate":[175],"that":[176],"effectively":[179],"enhance":[180],"matching":[186],"recognizing":[188],"objects,":[190],"achieving":[191],"much":[192],"performance":[194],"over":[195],"most":[196],"state-of-the-art":[197],"methods":[198],"under":[199],"1-shot":[200],"5-shot":[202],"scenarios.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}