{"id":"https://openalex.org/W4304084267","doi":"https://doi.org/10.1145/3503161.3548308","title":"SIM-Trans: Structure Information Modeling Transformer for Fine-grained Visual Categorization","display_name":"SIM-Trans: Structure Information Modeling Transformer for Fine-grained Visual Categorization","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304084267","doi":"https://doi.org/10.1145/3503161.3548308"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548308","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548308","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/A5100755638","display_name":"Hongbo Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbo Sun","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017511861","display_name":"Xiangteng He","orcid":"https://orcid.org/0000-0001-8502-5685"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangteng He","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047811387","display_name":"Yuxin Peng","orcid":"https://orcid.org/0000-0001-7658-3845"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Peng","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":120,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5853","last_page":"5861"},"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":0.9997000098228455,"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":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.8349758386611938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7421095371246338},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7342652678489685},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6505875587463379},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6217392086982727},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.569581925868988},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5106804966926575},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.46346133947372437},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4328550100326538},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.41004714369773865},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.373532772064209},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.21743598580360413},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09872481226921082}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8349758386611938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7421095371246338},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7342652678489685},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6505875587463379},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6217392086982727},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.569581925868988},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5106804966926575},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.46346133947372437},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4328550100326538},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.41004714369773865},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.373532772064209},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.21743598580360413},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09872481226921082},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548308","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548308","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":[{"score":0.75,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W56385144","https://openalex.org/W2118696714","https://openalex.org/W2194775991","https://openalex.org/W2740620254","https://openalex.org/W2761785940","https://openalex.org/W2765268259","https://openalex.org/W2773003563","https://openalex.org/W2797977484","https://openalex.org/W2883888092","https://openalex.org/W2889469641","https://openalex.org/W2891951760","https://openalex.org/W2913688275","https://openalex.org/W2940925558","https://openalex.org/W2961018736","https://openalex.org/W2963393555","https://openalex.org/W2963407932","https://openalex.org/W2990495699","https://openalex.org/W2997300818","https://openalex.org/W2997809650","https://openalex.org/W2998345525","https://openalex.org/W3028797339","https://openalex.org/W3034676907","https://openalex.org/W3035220232","https://openalex.org/W3094502228","https://openalex.org/W3108870912","https://openalex.org/W3166091781","https://openalex.org/W3170841864","https://openalex.org/W3174336354","https://openalex.org/W3187314660","https://openalex.org/W3195399086","https://openalex.org/W3206734547","https://openalex.org/W3209048284","https://openalex.org/W4214736485","https://openalex.org/W4236965008"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2116862786","https://openalex.org/W2952115151","https://openalex.org/W3208297503","https://openalex.org/W3119773509","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353","https://openalex.org/W2145850538"],"abstract_inverted_index":{"Fine-grained":[0],"visual":[1,181,229],"categorization":[2,230],"(FGVC)":[3],"aims":[4],"at":[5,237],"recognizing":[6],"objects":[7],"from":[8],"similar":[9],"subordinate":[10],"categories,":[11],"which":[12,45,142,201],"is":[13,119,143,160],"challenging":[14],"and":[15,40,53,87,101,169,189,197,217],"practical":[16],"for":[17,32,48,76,149,178],"human's":[18],"accurate":[19,179],"automatic":[20],"recognition":[21],"needs.":[22],"Most":[23],"FGVC":[24],"approaches":[25],"focus":[26],"on":[27,204,227],"the":[28,58,63,84,93,113,123,131,135,138,147,154,164,205,211,221],"attention":[29,206],"mechanism":[30],"research":[31],"discriminative":[33,50,78],"regions":[34],"mining":[35],"while":[36],"neglecting":[37],"their":[38],"interdependencies":[39],"composed":[41],"holistic":[42],"object":[43,71,132],"structure,":[44],"are":[46,187],"essential":[47],"model's":[49],"information":[51,73,86,115],"localization":[52],"understanding":[54],"ability.":[55],"To":[56],"address":[57],"above":[59],"limitations,":[60],"we":[61,91],"propose":[62],"Structure":[64],"Information":[65],"Modeling":[66],"Transformer":[67],"(SIM-Trans)":[68],"to":[69,81,121,162,174],"incorporate":[70],"structure":[72,88,114,151],"into":[74,95,146,193],"transformer":[75,106,195,213],"enhancing":[77],"representation":[79],"learning":[80,116,171],"contain":[82],"both":[83],"appearance":[85],"information.":[89],"Specifically,":[90],"encode":[92],"image":[94],"a":[96,103],"sequence":[97],"of":[98,127,137,166],"patch":[99],"tokens":[100],"build":[102],"strong":[104],"vision":[105,212],"framework":[107],"with":[108,134,210],"two":[109,185],"well-designed":[110],"modules:":[111],"(i)":[112],"(SIL)":[117],"module":[118,159],"proposed":[120,184,222],"mine":[122],"spatial":[124],"context":[125],"relation":[126],"significant":[128],"patches":[129],"within":[130],"extent":[133],"help":[136],"transformer's":[139],"self-attention":[140],"weights,":[141],"further":[144],"injected":[145],"model":[148],"importing":[150],"information;":[152],"(ii)":[153],"multi-level":[155,167],"feature":[156,176],"boosting":[157],"(MFB)":[158],"introduced":[161],"exploit":[163],"complementary":[165],"features":[168],"contrastive":[170],"among":[172],"classes":[173],"enhance":[175],"robustness":[177],"fine-grained":[180,228],"categorization.":[182],"The":[183,232],"modules":[186],"light-weighted":[188],"can":[190],"be":[191,235],"plugged":[192],"any":[194],"network":[196],"trained":[198],"end-to-end":[199],"easily,":[200],"only":[202],"depends":[203],"weights":[207],"that":[208,220],"come":[209],"itself.":[214],"Extensive":[215],"experiments":[216],"analyses":[218],"demonstrate":[219],"SIM-Trans":[223],"achieves":[224],"state-of-the-art":[225],"performance":[226],"benchmarks.":[231],"code":[233],"will":[234],"available":[236],"https://github.com/PKU-ICST-MIPL/SIM-Trans_ACMMM2022.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":40},{"year":2024,"cited_by_count":49},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}