{"id":"https://openalex.org/W4406890907","doi":"https://doi.org/10.1109/tmm.2025.3535387","title":"SpliceMix: A Cross-Scale and Semantic Blending Augmentation Strategy for Multi-Label Image Classification","display_name":"SpliceMix: A Cross-Scale and Semantic Blending Augmentation Strategy for Multi-Label Image Classification","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406890907","doi":"https://doi.org/10.1109/tmm.2025.3535387"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3535387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535387","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5025684575","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0003-3860-5139"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]},{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lei Wang","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, Jiangsu Key Laboratory of Image and Video Understanding for Social Security, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0003-3860-5139","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, Jiangsu Key Laboratory of Image and Video Understanding for Social Security, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I200845125","https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074672983","display_name":"Yibing Zhan","orcid":"https://orcid.org/0000-0003-3180-0484"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibing Zhan","raw_affiliation_strings":["JD Explore Academy, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3180-0484","affiliations":[{"raw_affiliation_string":"JD Explore Academy, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040404599","display_name":"Leilei Ma","orcid":"https://orcid.org/0000-0001-8681-0765"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leilei Ma","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Heifei, China","School of Computer Science and Technology, Anhui University, Heifei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Heifei, China","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Heifei, Anhui, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067600725","display_name":"Dapeng Tao","orcid":"https://orcid.org/0000-0003-0783-5273"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dapeng Tao","raw_affiliation_strings":["FIST LAB, School of Information Science and Engineering, Yunnan University, Kunming, China","FIST LAB, School of Information Science and Engineering, Yunnan University, Kunming, Yunnan, China"],"raw_orcid":"https://orcid.org/0000-0003-0783-5273","affiliations":[{"raw_affiliation_string":"FIST LAB, School of Information Science and Engineering, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]},{"raw_affiliation_string":"FIST LAB, School of Information Science and Engineering, Yunnan University, Kunming, Yunnan, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456723","display_name":"Liang Ding","orcid":"https://orcid.org/0000-0001-8976-2084"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Ding","raw_affiliation_strings":["JD Explore Academy, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8976-2084","affiliations":[{"raw_affiliation_string":"JD Explore Academy, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030222911","display_name":"Chen Gong","orcid":"https://orcid.org/0000-0002-4092-9856"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]},{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Gong","raw_affiliation_strings":["Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, Jiangsu Key Laboratory of Image and Video Understanding for Social Security, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-4092-9856","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, Jiangsu Key Laboratory of Image and Video Understanding for Social Security, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I200845125","https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5025684575"],"corresponding_institution_ids":["https://openalex.org/I200845125","https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":13.0395,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98231137,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"27","issue":null,"first_page":"3251","last_page":"3265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9955999851226807,"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":0.9955999851226807,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9203000068664551,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9082000255584717,"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":0.8605018854141235},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5367492437362671},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5229145288467407},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47688916325569153},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4634755551815033},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4262973368167877},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3873949348926544},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3441723883152008}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8605018854141235},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5367492437362671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5229145288467407},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47688916325569153},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4634755551815033},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4262973368167877},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3873949348926544},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3441723883152008},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3535387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535387","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G351810823","display_name":null,"funder_award_id":"62336003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3528468396","display_name":null,"funder_award_id":"12371510","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4140959408","display_name":null,"funder_award_id":"62076005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6000861853","display_name":null,"funder_award_id":"62172354","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2561196672","https://openalex.org/W2620998106","https://openalex.org/W2883780447","https://openalex.org/W2932399282","https://openalex.org/W2963351448","https://openalex.org/W2963676620","https://openalex.org/W2963745697","https://openalex.org/W2963875806","https://openalex.org/W2982112268","https://openalex.org/W2992308087","https://openalex.org/W2997136715","https://openalex.org/W3015233197","https://openalex.org/W3034368386","https://openalex.org/W3034410824","https://openalex.org/W3034938110","https://openalex.org/W3035452548","https://openalex.org/W3036957116","https://openalex.org/W3094502228","https://openalex.org/W3099518117","https://openalex.org/W3109067582","https://openalex.org/W3120562181","https://openalex.org/W3138516171","https://openalex.org/W3165691894","https://openalex.org/W3167456680","https://openalex.org/W3174102142","https://openalex.org/W3176136157","https://openalex.org/W3192931333","https://openalex.org/W3202858701","https://openalex.org/W3202884348","https://openalex.org/W3203879378","https://openalex.org/W4214673031","https://openalex.org/W4220813865","https://openalex.org/W4225930680","https://openalex.org/W4226426325","https://openalex.org/W4293202648","https://openalex.org/W4293584584","https://openalex.org/W4304014049","https://openalex.org/W4304080876","https://openalex.org/W4312443924","https://openalex.org/W4312777209","https://openalex.org/W4312884841","https://openalex.org/W4313118352","https://openalex.org/W4313156423","https://openalex.org/W4316661142","https://openalex.org/W4377000427","https://openalex.org/W4385245566","https://openalex.org/W4387831686","https://openalex.org/W6635446068","https://openalex.org/W6638523607","https://openalex.org/W6726873649","https://openalex.org/W6743428213","https://openalex.org/W6745136726","https://openalex.org/W6763310536","https://openalex.org/W6766978945","https://openalex.org/W6778963470","https://openalex.org/W6779348065","https://openalex.org/W6779447676","https://openalex.org/W6787536123","https://openalex.org/W6794301176","https://openalex.org/W6794559225","https://openalex.org/W6795737119","https://openalex.org/W6798617289","https://openalex.org/W6810472460","https://openalex.org/W6811007050"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2779427294","https://openalex.org/W2775347418","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W3003936178","https://openalex.org/W2145652935","https://openalex.org/W2563206327","https://openalex.org/W2546503577"],"abstract_inverted_index":{"Recently,":[0],"Mix-style":[1],"data":[2],"augmentation":[3,78],"methods":[4,21,60,234],"(<italic":[5,209],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[6,38,94,130,210],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">e.g</i>.,":[7,211],"Mixup":[8],"and":[9,34,47,136,170,179],"CutMix)":[10],"have":[11],"shown":[12],"promising":[13],"performance":[14,215],"in":[15,88,106,161,231],"various":[16,198],"visual":[17],"tasks.":[18],"However,":[19],"these":[20],"are":[22,120],"primarily":[23],"designed":[24],"for":[25,80,125],"single-label":[26],"images,":[27,36],"ignoring":[28],"the":[29,52,107,113,137,189,220,229],"considerable":[30],"discrepancies":[31],"between":[32,167],"single-":[33],"multi-label":[35,41,56,81],"<italic":[37,93,129],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">i.e</i>.,":[39],"a":[40,74,100,110,142,177,206],"image":[42,57,82,98,149],"involves":[43],"multiple":[44],"co-occurred":[45,127],"categories":[46],"fickle":[48],"object":[49,123],"scales.":[50],"On":[51],"other":[53],"hand,":[54],"previous":[55],"classification":[58],"(MLIC)":[59],"tend":[61],"to":[62,118,140,153,155,187],"design":[63],"elaborate":[64],"models,":[65],"bringing":[66],"expensive":[67],"computation.":[68],"In":[69],"this":[70],"article,":[71],"we":[72],"introduce":[73],"simple":[75,178],"but":[76],"effective":[77],"strategy":[79],"classification,":[83],"namely":[84],"SpliceMix.":[85,194,239],"The":[86],"\u201csplice\u201d":[87],"our":[89,162,193,223,238],"method":[90],"is":[91,99,225],"two-fold:":[92],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1)</i>":[95],"Each":[96],"mixed":[97,134,168],"splice":[101,133,160],"of":[102,109,115,191,222],"several":[103],"downsampled":[104],"images":[105,116,135,169],"form":[108,141],"grid,":[111],"where":[112],"semantics":[114],"attending":[117],"mixing":[119],"blended":[121],"without":[122],"deficiencies":[124],"alleviating":[126],"bias;":[128],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2)</i>":[131],"We":[132,174],"original":[138,171],"mini-batch":[139,164],"new":[143],"SpliceMixed":[144,163],"mini-batch,":[145],"which":[146],"allows":[147],"an":[148],"with":[150,205,237],"different":[151],"scales":[152],"contribute":[154],"training":[156],"together.":[157],"Furthermore,":[158],"such":[159],"enables":[165],"interactions":[166],"regular":[172],"images.":[173],"also":[175],"provide":[176],"non-parametric":[180],"extension":[181],"based":[182],"on":[183,197],"consistency":[184],"learning":[185],"(SpliceMix-CL)":[186],"show":[188],"potential":[190],"extending":[192],"Extensive":[195],"experiments":[196],"tasks":[199],"demonstrate":[200],"that":[201],"only":[202],"using":[203],"SpliceMix":[204,224],"baseline":[207],"model":[208],"ResNet)":[212],"achieves":[213],"better":[214],"than":[216],"state-of-the-art":[217],"methods.":[218],"Moreover,":[219],"generalizability":[221],"further":[226],"validated":[227],"by":[228],"improvements":[230],"current":[232],"MLIC":[233],"when":[235],"married":[236]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
