{"id":"https://openalex.org/W4399506362","doi":"https://doi.org/10.1007/s41095-023-0382-0","title":"Cross-modal learning using privileged information for long-tailed image classification","display_name":"Cross-modal learning using privileged information for long-tailed image classification","publication_year":2024,"publication_date":"2024-06-10","ids":{"openalex":"https://openalex.org/W4399506362","doi":"https://doi.org/10.1007/s41095-023-0382-0"},"language":"en","primary_location":{"id":"doi:10.1007/s41095-023-0382-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41095-023-0382-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41095-023-0382-0.pdf","source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s41095-023-0382-0.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029698374","display_name":"Xiangxian Li","orcid":"https://orcid.org/0000-0001-6638-2361"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangxian Li","raw_affiliation_strings":["School of Software, Shandong University, Jinan 250101, China","School of Software, Shandong University, Jinan, 250101, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan 250101, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"School of Software, Shandong University, Jinan, 250101, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018130955","display_name":"Yuze Zheng","orcid":"https://orcid.org/0009-0003-5718-8366"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuze Zheng","raw_affiliation_strings":["School of Software, Shandong University, Jinan 250101, China","School of Software, Shandong University, Jinan, 250101, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan 250101, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"School of Software, Shandong University, Jinan, 250101, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006833163","display_name":"Haokai Ma","orcid":"https://orcid.org/0000-0002-4621-5213"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haokai Ma","raw_affiliation_strings":["School of Software, Shandong University, Jinan 250101, China","School of Software, Shandong University, Jinan, 250101, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan 250101, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"School of Software, Shandong University, Jinan, 250101, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079754643","display_name":"Zhuang Qi","orcid":"https://orcid.org/0000-0003-3433-7413"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuang Qi","raw_affiliation_strings":["School of Software, Shandong University, Jinan 250101, China","School of Software, Shandong University, Jinan, 250101, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan 250101, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"School of Software, Shandong University, Jinan, 250101, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101536417","display_name":"Xiangxu Meng","orcid":"https://orcid.org/0000-0001-7290-5659"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangxu Meng","raw_affiliation_strings":["School of Software, Shandong University, Jinan 250101, China","School of Software, Shandong University, Jinan, 250101, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan 250101, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"School of Software, Shandong University, Jinan, 250101, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100629169","display_name":"Lei Meng","orcid":"https://orcid.org/0000-0002-0273-5946"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lei Meng","raw_affiliation_strings":["School of Software, Shandong University, Jinan 250101, China","School of Software, Shandong University, Jinan, 250101, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan 250101, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"School of Software, Shandong University, Jinan, 250101, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100629169"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":2.5006,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.90366556,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"10","issue":"5","first_page":"981","last_page":"992"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9995999932289124,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9995999932289124,"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":0.9970999956130981,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9962000250816345,"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/modal","display_name":"Modal","score":0.7035894393920898},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5841513872146606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5751632452011108},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.558939516544342},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5462134480476379},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5326487421989441},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5260376930236816},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.492000550031662},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4900263547897339},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4785635769367218},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4767114520072937},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.47639933228492737},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4634288549423218},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.36736249923706055},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07707366347312927}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7035894393920898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5841513872146606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5751632452011108},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.558939516544342},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5462134480476379},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5326487421989441},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5260376930236816},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.492000550031662},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4900263547897339},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4785635769367218},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4767114520072937},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.47639933228492737},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4634288549423218},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36736249923706055},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07707366347312927},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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:10.1007/s41095-023-0382-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41095-023-0382-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41095-023-0382-0.pdf","source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s41095-023-0382-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41095-023-0382-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41095-023-0382-0.pdf","source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399506362.pdf"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W2007972815","https://openalex.org/W2067562626","https://openalex.org/W2194775991","https://openalex.org/W2519936666","https://openalex.org/W2526198870","https://openalex.org/W2552639984","https://openalex.org/W2583892095","https://openalex.org/W2765707332","https://openalex.org/W2962858109","https://openalex.org/W2962933664","https://openalex.org/W2963351448","https://openalex.org/W2963691377","https://openalex.org/W2963703197","https://openalex.org/W2964137095","https://openalex.org/W2964288524","https://openalex.org/W2966316879","https://openalex.org/W2981631843","https://openalex.org/W2981794866","https://openalex.org/W3010512657","https://openalex.org/W3034369739","https://openalex.org/W3034601242","https://openalex.org/W3034711780","https://openalex.org/W3047379413","https://openalex.org/W3092755432","https://openalex.org/W3092995403","https://openalex.org/W3094502228","https://openalex.org/W3095707208","https://openalex.org/W3096121526","https://openalex.org/W3096688134","https://openalex.org/W3128945844","https://openalex.org/W3135367836","https://openalex.org/W3174366534","https://openalex.org/W3175196926","https://openalex.org/W3176646400","https://openalex.org/W3179096061","https://openalex.org/W3209306061","https://openalex.org/W3215720729","https://openalex.org/W4214718285","https://openalex.org/W4285295719","https://openalex.org/W4312866014","https://openalex.org/W4312910036","https://openalex.org/W4321354006","https://openalex.org/W4385489138","https://openalex.org/W4388193335"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W2375480909","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W2353314428","https://openalex.org/W4321636575","https://openalex.org/W613940353","https://openalex.org/W1986418932","https://openalex.org/W2357796999","https://openalex.org/W2320915480"],"abstract_inverted_index":{"The":[0,148],"prevalence":[1],"of":[2,54,58,93,96,133,150,164,175],"long-tailed":[3,28,82,135,142],"distributions":[4],"in":[5,10,27,112,172,179,195],"real-world":[6],"data":[7],"often":[8,42],"results":[9],"classification":[11,30],"models":[12],"favoring":[13],"the":[14,18,25,46,59,91,104,107,120,141,151,167,180,187,196,202],"dominant":[15,49],"classes,":[16,177],"neglecting":[17],"less":[19],"frequent":[20],"ones.":[21],"Current":[22],"approaches":[23],"address":[24,62],"issues":[26],"image":[29,83],"by":[31,99,115],"rebalancing":[32],"data,":[33],"optimizing":[34],"weights,":[35],"and":[36,50,75,102,109,136,146,178],"augmenting":[37],"information.":[38],"However,":[39],"these":[40,63],"methods":[41,139],"struggle":[43],"to":[44,86,189,201],"balance":[45],"performance":[47,127],"between":[48,106],"minority":[51],"classes":[52,111],"because":[53],"inadequate":[55],"representation":[56],"learning":[57,92,138,173],"latter.":[60],"To":[61],"problems,":[64],"we":[65],"introduce":[66],"descriptional":[67],"words":[68],"into":[69],"images":[70],"as":[71,87],"cross-modal":[72,78,100,116,137,143],"privileged":[73],"information":[74],"propose":[76],"a":[77,161],"enhanced":[79],"method":[80],"for":[81],"classification,":[84],"referred":[85],"CMLTNet.":[88],"CMLTNet":[89,123,185],"improves":[90],"intraclass":[94],"similarity":[95],"tail-class":[97],"representations":[98,174],"alignment":[101],"captures":[103],"difference":[105],"head":[108],"tail":[110,176,197],"semantic":[113,203],"space":[114],"inference.":[117],"After":[118],"fusing":[119],"above":[121],"information,":[122],"achieved":[124],"an":[125],"overall":[126],"that":[128],"was":[129,154,170],"better":[130,171],"than":[131],"those":[132],"benchmark":[134],"on":[140,182],"datasets,":[144],"NUS-WIDE":[145],"VireoFood-172.":[147],"effectiveness":[149],"proposed":[152,168],"modules":[153],"further":[155],"studied":[156],"through":[157,199],"ablation":[158],"experiments.":[159],"In":[160],"case":[162],"study":[163],"feature":[165],"distribution,":[166],"model":[169,183],"experiments":[181],"attention,":[184],"has":[186],"potential":[188],"help":[190],"learn":[191],"some":[192],"rare":[193],"concepts":[194],"class":[198],"mapping":[200],"space.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}