{"id":"https://openalex.org/W4286499389","doi":"https://doi.org/10.1145/3550278","title":"Aligning Image Semantics and Label Concepts for Image Multi-Label Classification","display_name":"Aligning Image Semantics and Label Concepts for Image Multi-Label Classification","publication_year":2022,"publication_date":"2022-07-21","ids":{"openalex":"https://openalex.org/W4286499389","doi":"https://doi.org/10.1145/3550278"},"language":"en","primary_location":{"id":"doi:10.1145/3550278","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3550278","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5059433400","display_name":"Wei Zhou","orcid":"https://orcid.org/0000-0002-9237-7205"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhou","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People\u2019s Republic of China","School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People's Republic of China"],"raw_orcid":"https://orcid.org/0000-0002-9237-7205","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People\u2019s Republic of China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People's Republic of China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074820202","display_name":"Zhiwu Xia","orcid":"https://orcid.org/0000-0001-7901-0698"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwu Xia","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People\u2019s Republic of China","School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People's Republic of China"],"raw_orcid":"https://orcid.org/0000-0001-7901-0698","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People\u2019s Republic of China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People's Republic of China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016700932","display_name":"Peng Dou","orcid":"https://orcid.org/0000-0002-9802-1226"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Dou","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People\u2019s Republic of China","School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People's Republic of China"],"raw_orcid":"https://orcid.org/0000-0002-9802-1226","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People\u2019s Republic of China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People's Republic of China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001383559","display_name":"Tao Su","orcid":"https://orcid.org/0000-0001-5227-1337"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Su","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People\u2019s Republic of China","School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People's Republic of China"],"raw_orcid":"https://orcid.org/0000-0001-5227-1337","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People\u2019s Republic of China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People's Republic of China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056953478","display_name":"Haifeng Hu","orcid":"https://orcid.org/0000-0002-4884-323X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Hu","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People\u2019s Republic of China","School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People's Republic of China"],"raw_orcid":"https://orcid.org/0000-0002-4884-323X","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People\u2019s Republic of China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangdong, People's Republic of China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":2.132,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.88623857,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"19","issue":"2","first_page":"1","last_page":"23"},"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":0.9991999864578247,"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":0.9991999864578247,"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":0.9983000159263611,"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":0.9976999759674072,"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":0.8692545294761658},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6782137155532837},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6094909906387329},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4837234318256378},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4627205729484558},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4552764296531677},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44069233536720276},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4353069067001343},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4331076443195343},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4310012757778168},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.42405837774276733},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4096677005290985},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1174858808517456},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10211130976676941}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8692545294761658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6782137155532837},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6094909906387329},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4837234318256378},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4627205729484558},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4552764296531677},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44069233536720276},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4353069067001343},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4331076443195343},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4310012757778168},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42405837774276733},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4096677005290985},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1174858808517456},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10211130976676941},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3550278","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3550278","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1404993191","display_name":null,"funder_award_id":"62076262, 61673402, 61273270, 60802069","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2007972815","https://openalex.org/W2031489346","https://openalex.org/W2108598243","https://openalex.org/W2186222003","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2395325225","https://openalex.org/W2549139847","https://openalex.org/W2560096627","https://openalex.org/W2604292070","https://openalex.org/W2738853914","https://openalex.org/W2782482721","https://openalex.org/W2912083425","https://openalex.org/W2912238929","https://openalex.org/W2912423076","https://openalex.org/W2921251850","https://openalex.org/W2932399282","https://openalex.org/W2957702778","https://openalex.org/W2962858109","https://openalex.org/W2963091558","https://openalex.org/W2963300078","https://openalex.org/W2963322224","https://openalex.org/W2963745697","https://openalex.org/W2963875806","https://openalex.org/W2982112268","https://openalex.org/W2997383919","https://openalex.org/W2999565440","https://openalex.org/W3028151507","https://openalex.org/W3041730883","https://openalex.org/W3089555680","https://openalex.org/W3092779813","https://openalex.org/W3093048820","https://openalex.org/W3093484105","https://openalex.org/W3095907242","https://openalex.org/W3109067582","https://openalex.org/W3109958243","https://openalex.org/W3112165001","https://openalex.org/W3136416617","https://openalex.org/W3151762391","https://openalex.org/W3154314403","https://openalex.org/W3162529291","https://openalex.org/W3165181705","https://openalex.org/W3167051144","https://openalex.org/W3170841864","https://openalex.org/W3174320978","https://openalex.org/W3174396085","https://openalex.org/W3183768965","https://openalex.org/W3188283811","https://openalex.org/W3211407538","https://openalex.org/W4206286055","https://openalex.org/W4221079634","https://openalex.org/W4234552385","https://openalex.org/W4248927948"],"related_works":["https://openalex.org/W2329500892","https://openalex.org/W28991112","https://openalex.org/W2370726991","https://openalex.org/W2369710579","https://openalex.org/W2560215812","https://openalex.org/W4327728159","https://openalex.org/W4394266730","https://openalex.org/W1990856605","https://openalex.org/W2053783616","https://openalex.org/W2545348020"],"abstract_inverted_index":{"Image":[0],"multi-label":[1,121,132,245],"classification":[2,122,133],"task":[3],"is":[4,49,110],"mainly":[5],"to":[6,27,37,91,115,137,157,173,189,199,227],"correctly":[7],"predict":[8],"multiple":[9],"object":[10,68,160],"categories":[11],"in":[12,162,170,186],"the":[13,17,30,43,59,65,71,76,86,93,101,113,117,163,167,176,183,201,212,216,229],"images.":[14],"To":[15,124],"capture":[16,100,175],"correlation":[18,102,177],"between":[19,103,178],"labels,":[20,104],"graph":[21,41,46],"convolution":[22],"network":[23],"based":[24],"methods":[25,61],"have":[26],"manually":[28],"count":[29],"label":[31,72,195],"co-occurrence":[32],"probability":[33],"from":[34],"training":[35],"data":[36],"construct":[38],"a":[39,129,154],"pre-defined":[40],"as":[42,198,249],"input":[44],"of":[45,58,79,97,112,119,215,219],"network,":[47],"which":[48,135],"inflexible":[50],"and":[51,99,105,165,222,256,262],"may":[52,81],"degrade":[53],"model":[54,80,205,238],"generalizability.":[55],"Moreover,":[56],"most":[57],"current":[60],"cannot":[62],"effectively":[63,107],"align":[64,108,138,190],"learned":[66],"salient":[67,94,159],"features":[69,96,161,193,214],"with":[70,85,143,194,208,258],"concepts,":[73,196],"so":[74,197],"that":[75],"predicted":[77,203],"results":[78],"not":[82],"be":[83],"consistent":[84,207],"image":[87,120,131,191,209,246],"content.":[88,210],"Therefore,":[89],"how":[90],"learn":[92,158],"semantic":[95,192],"images":[98],"then":[106],"them":[109],"one":[111],"key":[114],"improve":[116],"performance":[118,241],"task.":[123],"this":[125],"end,":[126],"we":[127,152,181],"propose":[128,153],"novel":[130],"framework":[134],"aims":[136],"I":[139],"mage":[140],"S":[141],"emantics":[142],"L":[144],"abel":[145],"C":[146],"oncepts":[147],"(":[148],"ISLC":[149,237],").":[150],"Specifically,":[151],"residual":[155,220],"encoder":[156,221],"images,":[164],"exploit":[166],"self-attention":[168],"layer":[169,218],"aligned":[171,187,223],"decoder":[172,188,224],"automatically":[174],"labels.":[179],"Then,":[180],"leverage":[182],"cross-attention":[184],"layers":[185],"make":[200],"labels":[202],"by":[204],"more":[206],"Finally,":[211],"output":[213,231],"last":[217],"are":[225],"fused":[226],"obtain":[228],"final":[230],"feature":[232],"for":[233],"classification.":[234],"The":[235],"proposed":[236],"achieves":[239],"good":[240],"on":[242],"various":[243],"prevalent":[244],"datasets":[247],"such":[248],"MS-COCO":[250],"2014,":[251],"PASCAL":[252],"VOC":[253],"2007,":[254],"VG-500,":[255],"NUS-WIDE":[257],"87.2%,":[259],"96.9%,":[260],"39.4%,":[261],"64.2%,":[263],"respectively.":[264]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
