{"id":"https://openalex.org/W7140329774","doi":"https://doi.org/10.1007/s00521-026-11920-8","title":"Parvelous: pedestrian attribute recognition using a vision encoder for multi-task learning on unbalanced sample distributions","display_name":"Parvelous: pedestrian attribute recognition using a vision encoder for multi-task learning on unbalanced sample distributions","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7140329774","doi":"https://doi.org/10.1007/s00521-026-11920-8"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-026-11920-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-026-11920-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-026-11920-8.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","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":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-026-11920-8.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130549480","display_name":"Antonio Greco","orcid":null},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Antonio Greco","raw_affiliation_strings":["Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Salerno, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128687515","display_name":"Andrea Vincenzo Ricciardi","orcid":null},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Vincenzo Ricciardi","raw_affiliation_strings":["Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Salerno, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092302658","display_name":"Bruno Vento","orcid":"https://orcid.org/0009-0006-7687-4929"},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Bruno Vento","raw_affiliation_strings":["Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Naples, Italy"],"raw_orcid":"https://orcid.org/0009-0006-7687-4929","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Naples, Italy","institution_ids":["https://openalex.org/I71267560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130582970","display_name":"Antonio Vitale","orcid":null},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Antonio Vitale","raw_affiliation_strings":["Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Salerno, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5092302658"],"corresponding_institution_ids":["https://openalex.org/I71267560"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30137383,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"7","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.36149999499320984,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.36149999499320984,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.17299999296665192,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.11940000206232071,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6850000023841858},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6545000076293945},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6486999988555908},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6237000226974487},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5810999870300293},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48590001463890076},{"id":"https://openalex.org/keywords/pedestrian","display_name":"Pedestrian","score":0.44769999384880066},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.43309998512268066},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.38749998807907104},{"id":"https://openalex.org/keywords/pedestrian-detection","display_name":"Pedestrian detection","score":0.37400001287460327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8551999926567078},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6850000023841858},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6545000076293945},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6486999988555908},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6237000226974487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6179999709129333},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5810999870300293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5195000171661377},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48590001463890076},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.44769999384880066},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.37400001287460327},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.35120001435279846},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34310001134872437},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C132900626","wikidata":"https://www.wikidata.org/wiki/Q7534733","display_name":"Sketch recognition","level":4,"score":0.31630000472068787},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3116999864578247},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C2781121602","wikidata":"https://www.wikidata.org/wiki/Q3504403","display_name":"Modular neural network","level":4,"score":0.25589999556541443},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00521-026-11920-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-026-11920-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-026-11920-8.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","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":"Neural Computing and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s00521-026-11920-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-026-11920-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-026-11920-8.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","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":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309590","display_name":"Universit\u00e0 degli Studi di Napoli Federico II","ror":"https://ror.org/05290cv24"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140329774.pdf","grobid_xml":"https://content.openalex.org/works/W7140329774.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1907729166","https://openalex.org/W2083501693","https://openalex.org/W2132083787","https://openalex.org/W2740096464","https://openalex.org/W2752782242","https://openalex.org/W2766111649","https://openalex.org/W2954148997","https://openalex.org/W2960230137","https://openalex.org/W2962800562","https://openalex.org/W2963007689","https://openalex.org/W3138516171","https://openalex.org/W3168100094","https://openalex.org/W3168997536","https://openalex.org/W3187415662","https://openalex.org/W4200476711","https://openalex.org/W4213019189","https://openalex.org/W4214673031","https://openalex.org/W4229439898","https://openalex.org/W4281965046","https://openalex.org/W4285169157","https://openalex.org/W4285207098","https://openalex.org/W4312221821","https://openalex.org/W4312881242","https://openalex.org/W4320484936","https://openalex.org/W4380303606","https://openalex.org/W4385384893","https://openalex.org/W4386075535","https://openalex.org/W4386870064","https://openalex.org/W4386870075","https://openalex.org/W4390873312","https://openalex.org/W4401990996","https://openalex.org/W4404740668","https://openalex.org/W4408112786","https://openalex.org/W4408336101","https://openalex.org/W4409368333","https://openalex.org/W4412345671","https://openalex.org/W4414250408","https://openalex.org/W4414250417","https://openalex.org/W4414250427","https://openalex.org/W4414250512","https://openalex.org/W7114905920"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Pedestrian":[1],"attribute":[2,115],"recognition":[3,116],"(PAR)":[4],"is":[5],"a":[6,81,119,156,161,191],"critical":[7],"task":[8,93],"for":[9,42,66,196],"real-time":[10],"video":[11],"surveillance":[12],"and":[13,35,55,69,80,91,113,185,193],"person":[14],"re-identification":[15],"in-the-wild.":[16],"While":[17],"modern":[18],"vision\u2013language":[19],"models":[20],"pre-trained":[21,65],"on":[22,60,123,145],"billions":[23],"of":[24,111,164,183],"image\u2013text":[25,67],"pairs":[26],"have":[27],"recently":[28],"achieved":[29],"outstanding":[30],"accuracy,":[31],"their":[32],"substantial":[33],"latency":[34],"high":[36],"memory":[37],"requirements":[38],"make":[39],"them":[40],"impractical":[41],"real-world":[43,197],"deployments.":[44],"To":[45],"overcome":[46],"these":[47],"limitations,":[48],"we":[49],"present":[50],"Parvelous":[51,154,189],",":[52],"an":[53,61,171],"efficient":[54],"versatile":[56],"multi-task":[57,120],"framework":[58,87],"built":[59],"optimized":[62],"vision":[63,178],"encoder":[64],"matching":[68],"specifically":[70],"adapted":[71],"to":[72,106,170,176],"the":[73,108,128,146,165],"PAR":[74,135,149,198],"domain.":[75],"Through":[76],"targeted":[77],"architectural":[78],"refinements":[79],"selective":[82],"layer-wise":[83],"fine-tuning":[84],"strategy,":[85],"our":[86],"ensures":[88],"both":[89],"efficiency":[90,187],"strong":[92],"specialization.":[94],"Modular":[95],"task-specific":[96],"branches":[97],"equipped":[98],"with":[99],"channel-wise":[100],"attention":[101],"are":[102],"tailored":[103],"in":[104,133],"depth":[105],"address":[107],"varying":[109],"complexity":[110],"binary":[112],"multi-class":[114],"tasks.":[117],"Additionally,":[118],"loss":[121,125],"based":[122],"asymmetric":[124],"functions":[126],"mitigates":[127],"severe":[129],"class":[130],"imbalance":[131],"inherent":[132],"standard":[134],"datasets,":[136],"fostering":[137],"robust":[138],"learning":[139],"across":[140],"diverse":[141],"attributes.":[142],"Extensive":[143],"evaluations":[144],"public":[147],"MIVIA":[148],"KD":[150],"benchmark":[151],"demonstrate":[152],"that":[153],"achieves":[155],"0.957":[157],"accuracy":[158,184],"rate,":[159],"setting":[160],"new":[162],"state":[163],"art,":[166],"while":[167],"delivering":[168],"up":[169],"80-fold":[172],"inference":[173],"speedup":[174],"compared":[175],"competing":[177],"language":[179],"models.":[180],"This":[181],"combination":[182],"computational":[186],"positions":[188],"as":[190],"practical":[192],"deployable":[194],"solution":[195],"applications.":[199]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-26T00:00:00"}