{"id":"https://openalex.org/W1999758002","doi":"https://doi.org/10.1145/2647868.2654937","title":"Fused one-vs-all mid-level features for fine-grained visual categorization","display_name":"Fused one-vs-all mid-level features for fine-grained visual categorization","publication_year":2014,"publication_date":"2014-10-31","ids":{"openalex":"https://openalex.org/W1999758002","doi":"https://doi.org/10.1145/2647868.2654937","mag":"1999758002"},"language":"en","primary_location":{"id":"doi:10.1145/2647868.2654937","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2647868.2654937","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Multimedia","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/A5100614065","display_name":"Xiaopeng Zhang","orcid":"https://orcid.org/0000-0001-6337-5748"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaopeng Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","[Shanghai Jiao Tong University, Shanghai, China]"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"[Shanghai Jiao Tong University, Shanghai, China]","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002494284","display_name":"Hongkai Xiong","orcid":"https://orcid.org/0000-0003-4552-0029"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongkai Xiong","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","[Shanghai Jiao Tong University, Shanghai, China]"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"[Shanghai Jiao Tong University, Shanghai, China]","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046805800","display_name":"Wengang Zhou","orcid":"https://orcid.org/0000-0003-1690-9836"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China",", University of Science and Technology of China, Hefei, China#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":", University of Science and Technology of China, Hefei, China#TAB#","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111504451","display_name":"Qi Tian","orcid":"https://orcid.org/0009-0003-2676-5300"},"institutions":[{"id":"https://openalex.org/I45438204","display_name":"The University of Texas at San Antonio","ror":"https://ror.org/01kd65564","country_code":"US","type":"education","lineage":["https://openalex.org/I45438204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["University of Texas at San Antonio, Texas, TX, USA","University of Texas at San Antonio, Texas, TX, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Texas at San Antonio, Texas, TX, USA","institution_ids":["https://openalex.org/I45438204"]},{"raw_affiliation_string":"University of Texas at San Antonio, Texas, TX, USA#TAB#","institution_ids":["https://openalex.org/I45438204"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100614065"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":3.707,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.94546141,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"287","last_page":"296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10036","display_name":"Advanced Neural Network Applications","score":0.9975000023841858,"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":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7670703530311584},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7660324573516846},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7123916149139404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.668563723564148},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.6408143043518066},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5822713971138},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5803160667419434},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5603426098823547},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.53947913646698},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5275779962539673},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5163460969924927},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5057742595672607},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45577573776245117},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.188003808259964},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11502042412757874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670703530311584},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7660324573516846},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7123916149139404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.668563723564148},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6408143043518066},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5822713971138},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5803160667419434},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5603426098823547},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.53947913646698},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5275779962539673},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5163460969924927},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5057742595672607},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45577573776245117},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.188003808259964},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11502042412757874},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2647868.2654937","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2647868.2654937","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.724.7360","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.724.7360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ivm.sjtu.edu.cn/files/papers/zxp_acmm14.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G2226386891","display_name":null,"funder_award_id":"61128007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5702699330","display_name":null,"funder_award_id":"W911NF-12-1-0057","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8999783826","display_name":null,"funder_award_id":"61228101","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"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1625255723","https://openalex.org/W1797268635","https://openalex.org/W1977295328","https://openalex.org/W1980526845","https://openalex.org/W1995318441","https://openalex.org/W1995543189","https://openalex.org/W2027252237","https://openalex.org/W2027922120","https://openalex.org/W2045978154","https://openalex.org/W2066941820","https://openalex.org/W2079789819","https://openalex.org/W2083367367","https://openalex.org/W2090042335","https://openalex.org/W2091759811","https://openalex.org/W2113080973","https://openalex.org/W2116046277","https://openalex.org/W2118696714","https://openalex.org/W2120419212","https://openalex.org/W2134270519","https://openalex.org/W2135706578","https://openalex.org/W2136705357","https://openalex.org/W2143516773","https://openalex.org/W2148596671","https://openalex.org/W2155541015","https://openalex.org/W2162915993","https://openalex.org/W2163605009","https://openalex.org/W2169501191","https://openalex.org/W2604272474","https://openalex.org/W2963542991","https://openalex.org/W3143107425","https://openalex.org/W3206507930","https://openalex.org/W6636494156"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2965546495","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W151699219","https://openalex.org/W2085633464","https://openalex.org/W1966122760","https://openalex.org/W2797752778"],"abstract_inverted_index":{"As":[0],"an":[1],"emerging":[2],"research":[3],"topic,":[4],"fine-grained":[5,28,66,109,147,294,331],"visual":[6,110,332],"categorization":[7],"has":[8],"been":[9],"attracting":[10],"growing":[11],"attentions":[12],"in":[13,27,65,330],"recent":[14],"years.":[15],"Due":[16],"to":[17,95,181,197,219,282],"the":[18,69,100,114,128,132,151,158,160,166,170,173,186,189,211,220,232,245,248,255,265,269,284,288,292,303,308,318,327],"large":[19,137],"inter-class":[20],"similarity":[21],"and":[22,33,90,123,201,274,298,312,325],"intra-class":[23],"variance,":[24],"recognizing":[25],"objects":[26],"domains":[29,67],"is":[30,92,176,217,225,236,260,272],"extremely":[31,78],"challenging,":[32],"sometimes":[34],"even":[35,203],"humans":[36],"can":[37,275],"not":[38,73],"recognize":[39],"them":[40],"accurately.":[41],"Traditional":[42],"bag-of-words":[43],"model":[44],"could":[45],"obtain":[46,182],"desirable":[47],"results":[48],"for":[49,108,146,262],"basic-level":[50],"category":[51],"classification":[52,184,319],"by":[53,86,119,301,321],"weak":[54],"alignment":[55],"using":[56],"spatial":[57,115,207],"pyramid":[58,208],"matching":[59],"model,":[60],"but":[61,76],"may":[62],"easily":[63,277],"fail":[64],"since":[68],"discriminative":[70],"features":[71,141,154,164,175,192,216,235,250,271,305],"are":[72,143,251],"only":[74],"subtle":[75],"also":[77],"localized.":[79],"The":[80],"fine":[81],"differences":[82],"often":[83],"get":[84],"swamped":[85],"those":[87],"irrelevant":[88],"features,":[89],"it":[91],"virtually":[93],"impossible":[94],"distinguish":[96],"them.":[97],"To":[98],"address":[99],"problems":[101],"above,":[102],"we":[103,134,316],"propose":[104],"a":[105,136,240,322],"new":[106],"framework":[107],"categorization.":[111,333],"We":[112,286],"strengthen":[113],"correspondence":[116],"among":[117],"parts":[118],"including":[120],"foreground":[121],"segmentation":[122],"part":[124,129],"localization.":[125],"Based":[126],"on":[127,291,307],"representations":[130],"of":[131,139,172,188,199,213,222,231,244,268],"images,":[133,159],"learn":[135],"set":[138],"mid-level":[140,163,174,215,234,249,270,304],"which":[142,224,238,259],"more":[144,241,252],"suitable":[145],"tasks.":[148],"Comparing":[149],"with":[150,279],"low":[152,190,256],"level":[153,191,257],"directly":[155],"extracted":[156],"from":[157],"learned":[161],"one-vs-all":[162],"enjoy":[165],"following":[167],"advantages.":[168],"First,":[169],"dimension":[171,187,212],"relatively":[177],"small.":[178],"In":[179],"order":[180],"high":[183],"accuracy,":[185],"usually":[193],"reaches":[194],"several":[195],"thousand":[196],"tens":[198],"thousand,":[200],"becomes":[202],"larger":[204],"when":[205],"introducing":[206],"model.":[209],"However,":[210],"our":[214],"related":[218],"number":[221],"classes,":[223],"far":[226],"less.":[227],"Second,":[228],"each":[229],"entry":[230],"proposed":[233,289],"meaningful,":[237],"forms":[239],"compact":[242],"representation":[243],"image.":[246],"Third,":[247],"robust":[253],"than":[254],"ones,":[258],"helpful":[261],"classification.":[263],"Fourth,":[264],"learning":[266,302],"process":[267],"independent":[273],"be":[276],"combined":[278],"other":[280],"techniques":[281],"boost":[283,317],"performance.":[285],"evaluate":[287],"approach":[290],"extensive":[293],"dataset":[295],"CUB":[296],"200-2011":[297],"Stanford":[299],"Dogs,":[300],"based":[306],"popular":[309],"Fisher":[310],"vectors":[311],"convolutional":[313],"neural":[314],"network,":[315],"accuracy":[320],"considerable":[323],"margin":[324],"advance":[326],"state-of-the-art":[328],"performance":[329]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":8}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}