{"id":"https://openalex.org/W4220813865","doi":"https://doi.org/10.1109/tip.2022.3148867","title":"SST: Spatial and Semantic Transformers for Multi-Label Image Recognition","display_name":"SST: Spatial and Semantic Transformers for Multi-Label Image Recognition","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4220813865","doi":"https://doi.org/10.1109/tip.2022.3148867","pmid":"https://pubmed.ncbi.nlm.nih.gov/35275814"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2022.3148867","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3148867","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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":"Zhao-Min Chen","orcid":"https://orcid.org/0000-0001-8955-1789"},"institutions":[{"id":"https://openalex.org/I146620803","display_name":"Wenzhou University","ror":"https://ror.org/020hxh324","country_code":"CN","type":"education","lineage":["https://openalex.org/I146620803"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao-Min Chen","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8955-1789","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China","institution_ids":["https://openalex.org/I146620803"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Quan Cui","orcid":"https://orcid.org/0000-0003-3428-4913"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Quan Cui","raw_affiliation_strings":["Graduate School of Information, Production and Systems, Waseda University, Fukuoka, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3428-4913","affiliations":[{"raw_affiliation_string":"Graduate School of Information, Production and Systems, Waseda University, Fukuoka, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Borui Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726805","display_name":"Megvii (China)","ror":"https://ror.org/040b32p69","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726805"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Borui Zhao","raw_affiliation_strings":["Megvii Research Nanjing, Megvii Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Megvii Research Nanjing, Megvii Technology, Nanjing, China","institution_ids":["https://openalex.org/I4401726805"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Renjie Song","orcid":"https://orcid.org/0000-0003-3076-1786"},"institutions":[{"id":"https://openalex.org/I4401726805","display_name":"Megvii (China)","ror":"https://ror.org/040b32p69","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726805"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renjie Song","raw_affiliation_strings":["Megvii Research Nanjing, Megvii Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-3076-1786","affiliations":[{"raw_affiliation_string":"Megvii Research Nanjing, Megvii Technology, Nanjing, China","institution_ids":["https://openalex.org/I4401726805"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoqin Zhang","orcid":"https://orcid.org/0000-0003-0958-7285"},"institutions":[{"id":"https://openalex.org/I146620803","display_name":"Wenzhou University","ror":"https://ror.org/020hxh324","country_code":"CN","type":"education","lineage":["https://openalex.org/I146620803"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqin Zhang","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0958-7285","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China","institution_ids":["https://openalex.org/I146620803"]}]},{"author_position":"last","author":{"id":null,"display_name":"Osamu Yoshie","orcid":"https://orcid.org/0000-0002-4192-554X"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Osamu Yoshie","raw_affiliation_strings":["Graduate School of Information, Production and Systems, Waseda University, Fukuoka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4192-554X","affiliations":[{"raw_affiliation_string":"Graduate School of Information, Production and Systems, Waseda University, Fukuoka, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.4474,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.98347308,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"2570","last_page":"2583"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9330000281333923,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9330000281333923,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.01140000019222498,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.007400000002235174,"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/transformer","display_name":"Transformer","score":0.5572999715805054},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.5131000280380249},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4927000105381012},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.4075999855995178},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.37929999828338623},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3750999867916107},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.3499000072479248},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3449000120162964}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742900013923645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6322000026702881},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5572999715805054},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.5131000280380249},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4927000105381012},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.3499000072479248},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3264999985694885},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.29760000109672546},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2840000092983246},{"id":"https://openalex.org/C2986522900","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relationship","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2556999921798706},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2022.3148867","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3148867","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:35275814","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35275814","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G133414184","display_name":null,"funder_award_id":"U2033210","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3796144338","display_name":null,"funder_award_id":"61922064","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8626015724","display_name":"\u57fa\u4e8e\u957f\u5c3e\u5206\u5e03\u7684\u591a\u6807\u7b7e\u56fe\u50cf\u8bc6\u522b\u7b97\u6cd5\u7814\u7a76","funder_award_id":"LQ22F020006","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G8954100782","display_name":null,"funder_award_id":"62101387","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/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1567302070","https://openalex.org/W1861492603","https://openalex.org/W2007972815","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2295107390","https://openalex.org/W2410641892","https://openalex.org/W2521365688","https://openalex.org/W2560096627","https://openalex.org/W2605572715","https://openalex.org/W2736688973","https://openalex.org/W2788361849","https://openalex.org/W2798405286","https://openalex.org/W2885073348","https://openalex.org/W2932399282","https://openalex.org/W2957702778","https://openalex.org/W2963052338","https://openalex.org/W2963300078","https://openalex.org/W2963513598","https://openalex.org/W2963676620","https://openalex.org/W2963697527","https://openalex.org/W2963745697","https://openalex.org/W2963875806","https://openalex.org/W2982112268","https://openalex.org/W2996683351","https://openalex.org/W3036328963","https://openalex.org/W3096609285","https://openalex.org/W3099518117","https://openalex.org/W3121523901","https://openalex.org/W3161417137","https://openalex.org/W3172509117","https://openalex.org/W6630792627","https://openalex.org/W6637373629","https://openalex.org/W6674330103","https://openalex.org/W6726873649","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6763701032","https://openalex.org/W6771497439"],"related_works":[],"abstract_inverted_index":{"Multi-label":[0],"image":[1,28,160],"recognition":[2],"has":[3],"attracted":[4],"considerable":[5],"research":[6],"attention":[7],"and":[8,41,73,81,101,146,152,188],"achieved":[9],"great":[10,61],"success":[11,62],"in":[12,45,84,158],"recent":[13],"years.":[14],"Capturing":[15],"label":[16,33],"correlations":[17,34,83,103,114,148],"is":[18,89,109,125],"an":[19],"effective":[20],"manner":[21],"to":[22,77,97,111,127,154,167,192],"advance":[23],"the":[24,39,46,60,71,99,113,122,129,164,194],"performance":[25],"of":[26,32,53,63,92,131,197],"multi-label":[27,85,159,180],"recognition.":[29,161],"Two":[30],"types":[31],"were":[35],"principally":[36],"studied,":[37],"i.e.,":[38],"spatial":[40,80,100,119,145],"semantic":[42,82,102,147],"correlations.":[43],"However,":[44],"literature,":[47],"previous":[48],"methods":[49,176],"considered":[50],"only":[51],"either":[52],"them.":[54],"In":[55,183],"this":[56],"work,":[57],"inspired":[58],"by":[59],"Transformer,":[64],"we":[65,141],"propose":[66],"a":[67],"plug-and-play":[68],"module,":[69],"named":[70],"Spatial":[72,107],"Semantic":[74,123],"Transformers":[75],"(SST),":[76],"simultaneously":[78,157],"capture":[79,98,128,168],"images.":[86],"Our":[87],"proposal":[88],"mainly":[90],"comprised":[91],"two":[93],"independent":[94],"transformers,":[95],"aiming":[96],"respectively.":[104],"Specifically,":[105],"our":[106,171,198],"Transformer":[108,124],"designed":[110],"model":[112],"between":[115],"features":[116],"from":[117,163],"different":[118],"positions,":[120],"while":[121],"leveraged":[126,156],"co-existence":[130],"labels":[132],"without":[133],"manually":[134],"defined":[135],"rules.":[136],"Other":[137],"than":[138],"methodological":[139],"contributions,":[140],"also":[142],"prove":[143],"that":[144],"complement":[149],"each":[150],"other":[151],"deserve":[153],"be":[155],"Benefitting":[162],"Transformer's":[165],"ability":[166],"long-range":[169],"correlations,":[170],"method":[172],"remarkably":[173],"outperforms":[174],"state-of-the-art":[175],"on":[177],"four":[178],"popular":[179],"benchmark":[181],"datasets.":[182],"addition,":[184],"extensive":[185],"ablation":[186],"studies":[187],"visualizations":[189],"are":[190],"provided":[191],"validate":[193],"essential":[195],"components":[196],"method.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2022-04-03T00:00:00"}