{"id":"https://openalex.org/W3206402863","doi":"https://doi.org/10.1145/3474085.3475532","title":"Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classification","display_name":"Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classification","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206402863","doi":"https://doi.org/10.1145/3474085.3475532","mag":"3206402863"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475532","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th 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/A5075742545","display_name":"Yike Wu","orcid":"https://orcid.org/0000-0001-7384-8836"},"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":"Yike Wu","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/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, 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/A5003400275","display_name":"Gang Yu","orcid":"https://orcid.org/0000-0001-5570-2710"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Yu","raw_affiliation_strings":["Tencent, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Weixi Zhang","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":"Weixi Zhang","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/A5100612534","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0002-1589-8939"},"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":"Bin Wang","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/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":"last","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"107","last_page":"115"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9984999895095825,"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":0.9983999729156494,"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/discriminative-model","display_name":"Discriminative model","score":0.7825942039489746},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7768341302871704},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7156749963760376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6773912906646729},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.600289523601532},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.585845947265625},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5405745506286621},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5266088247299194},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5244351029396057},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5181035399436951},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5103222727775574},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5050352215766907},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4900323152542114},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46777811646461487},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4466606378555298},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4256933629512787},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.42305389046669006},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35891157388687134}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7825942039489746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7768341302871704},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7156749963760376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6773912906646729},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.600289523601532},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.585845947265625},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5405745506286621},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5266088247299194},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5244351029396057},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5181035399436951},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5103222727775574},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5050352215766907},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4900323152542114},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46777811646461487},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4466606378555298},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4256933629512787},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.42305389046669006},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35891157388687134},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475532","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W56385144","https://openalex.org/W603908379","https://openalex.org/W1797268635","https://openalex.org/W1954152232","https://openalex.org/W1955942245","https://openalex.org/W2104657103","https://openalex.org/W2112796928","https://openalex.org/W2118696714","https://openalex.org/W2135706578","https://openalex.org/W2138011018","https://openalex.org/W2554320282","https://openalex.org/W2604763608","https://openalex.org/W2611605760","https://openalex.org/W2618530766","https://openalex.org/W2740620254","https://openalex.org/W2773003563","https://openalex.org/W2904218366","https://openalex.org/W2957105406","https://openalex.org/W2963066927","https://openalex.org/W2963070905","https://openalex.org/W2963341924","https://openalex.org/W2964105864","https://openalex.org/W2964112702","https://openalex.org/W2965572487","https://openalex.org/W2979689312","https://openalex.org/W2985128858","https://openalex.org/W2990495699","https://openalex.org/W2997809650","https://openalex.org/W2998619563","https://openalex.org/W3012255272","https://openalex.org/W3012473455","https://openalex.org/W3034587791","https://openalex.org/W3034827765","https://openalex.org/W3034978645","https://openalex.org/W3035163205","https://openalex.org/W3035531117","https://openalex.org/W3035607448","https://openalex.org/W3096805028","https://openalex.org/W3108009835","https://openalex.org/W3108870912"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2110523656","https://openalex.org/W2761785940","https://openalex.org/W2129933262","https://openalex.org/W2565656575"],"abstract_inverted_index":{"The":[0,121],"goal":[1],"of":[2,23,42,58,100,139],"few-shot":[3],"fine-grained":[4,12,48],"image":[5,36,66,146],"classification":[6,217],"is":[7,74,98,123,150,169],"to":[8,125,152,171,181],"recognize":[9],"rarely":[10],"seen":[11],"objects":[13],"in":[14,26],"the":[15,27,59,64,71,79,137,148,154,166,173,178,190,203],"query":[16,65,191],"set,":[17],"given":[18],"only":[19],"a":[20,39,101,108,115,160],"few":[21],"samples":[22,44],"this":[24,87],"class":[25],"support":[28,72,175],"set.":[29],"Previous":[30],"works":[31],"focus":[32],"on":[33,198],"learning":[34],"discriminative":[35,60],"features":[37,62,185],"from":[38],"limited":[40],"number":[41],"training":[43],"for":[45,77],"distinguishing":[46],"various":[47],"classes,":[49],"but":[50],"ignore":[51],"one":[52],"important":[53],"fact":[54],"that":[55],"spatial":[56,94,117],"alignment":[57,95],"semantic":[61,80,110,157],"between":[63,82,144],"with":[67,189],"arbitrary":[68],"changes":[69],"and":[70,114,129,202,215],"image,":[73],"also":[75],"critical":[76],"computing":[78],"similarity":[81,163],"each":[83],"support-query":[84,145],"pair.":[85],"In":[86],"work,":[88],"we":[89],"propose":[90],"an":[91],"object-aware":[92],"long-short-range":[93],"approach,":[96],"which":[97],"composed":[99],"foreground":[102,132],"object":[103,133,141],"feature":[104,142,162,176],"enhancement":[105],"(FOE)":[106],"module,":[107],"long-range":[109,140,156,179],"correspondence":[111,158],"(LSC)":[112],"module":[113,168],"short-range":[116,183],"manipulation":[118],"(SSM)":[119],"module.":[120],"FOE":[122],"developed":[124,170],"weaken":[126],"background":[127],"disturbance":[128],"encourage":[130],"higher":[131],"response.":[134],"To":[135],"address":[136],"problem":[138],"misalignment":[143],"pairs,":[147],"LSC":[149],"proposed":[151],"learn":[153],"transferable":[155],"by":[159],"designed":[161],"metric.":[164],"Further,":[165],"SSM":[167],"refine":[172],"transformed":[174],"after":[177],"step":[180],"align":[182],"misaligned":[184],"(or":[186],"local":[187],"details)":[188],"features.":[192],"Extensive":[193],"experiments":[194],"have":[195],"been":[196],"conducted":[197],"four":[199],"benchmark":[200],"datasets,":[201],"results":[204],"show":[205],"superior":[206],"performance":[207],"over":[208],"most":[209],"state-of-the-art":[210],"methods":[211],"under":[212],"both":[213],"1-shot":[214],"5-shot":[216],"scenarios.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}