{"id":"https://openalex.org/W4393353220","doi":"https://doi.org/10.3390/rs16071216","title":"MRG-T: Mask-Relation-Guided Transformer for Remote Vision-Based Pedestrian Attribute Recognition in Aerial Imagery","display_name":"MRG-T: Mask-Relation-Guided Transformer for Remote Vision-Based Pedestrian Attribute Recognition in Aerial Imagery","publication_year":2024,"publication_date":"2024-03-29","ids":{"openalex":"https://openalex.org/W4393353220","doi":"https://doi.org/10.3390/rs16071216"},"language":"en","primary_location":{"id":"doi:10.3390/rs16071216","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs16071216","pdf_url":"https://www.mdpi.com/2072-4292/16/7/1216/pdf?version=1711727835","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2072-4292/16/7/1216/pdf?version=1711727835","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101557084","display_name":"Shun Zhang","orcid":"https://orcid.org/0000-0003-3380-8957"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shun Zhang","raw_affiliation_strings":["School of Electronic and Information, Northwestern Polytechnical University, Xi\u2019an 710129, China","School of Electronic and Information, Northwestern Polytechnical University, Xi'an 710129, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information, Northwestern Polytechnical University, Xi\u2019an 710129, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Electronic and Information, Northwestern Polytechnical University, Xi'an 710129, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032102573","display_name":"Yupeng Li","orcid":"https://orcid.org/0000-0003-1429-5009"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yupeng Li","raw_affiliation_strings":["School of Electronic and Information, Northwestern Polytechnical University, Xi\u2019an 710129, China","School of Electronic and Information, Northwestern Polytechnical University, Xi'an 710129, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information, Northwestern Polytechnical University, Xi\u2019an 710129, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Electronic and Information, Northwestern Polytechnical University, Xi'an 710129, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008792465","display_name":"Xiao Wu","orcid":"https://orcid.org/0009-0006-8617-7959"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Wu","raw_affiliation_strings":["School of Electronic and Information, Northwestern Polytechnical University, Xi\u2019an 710129, China","School of Electronic and Information, Northwestern Polytechnical University, Xi'an 710129, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information, Northwestern Polytechnical University, Xi\u2019an 710129, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Electronic and Information, Northwestern Polytechnical University, Xi'an 710129, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100587606","display_name":"Zunheng Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zunheng Chu","raw_affiliation_strings":["School of Electronic and Information, Northwestern Polytechnical University, Xi\u2019an 710129, China","School of Electronic and Information, Northwestern Polytechnical University, Xi'an 710129, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information, Northwestern Polytechnical University, Xi\u2019an 710129, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Electronic and Information, Northwestern Polytechnical University, Xi'an 710129, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100653678","display_name":"Lingfei Li","orcid":"https://orcid.org/0000-0001-5115-5166"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingfei Li","raw_affiliation_strings":["School of Electronic and Information, Northwestern Polytechnical University, Xi\u2019an 710129, China","School of Electronic and Information, Northwestern Polytechnical University, Xi'an 710129, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information, Northwestern Polytechnical University, Xi\u2019an 710129, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Electronic and Information, Northwestern Polytechnical University, Xi'an 710129, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101557084"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":{"value":2500,"currency":"CHF","value_usd":2707},"apc_paid":{"value":2500,"currency":"CHF","value_usd":2707},"fwci":0.7873,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70370509,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"16","issue":"7","first_page":"1216","last_page":"1216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8185049891471863},{"id":"https://openalex.org/keywords/pedestrian","display_name":"Pedestrian","score":0.6512892246246338},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6395905017852783},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6193528175354004},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.5302631258964539},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.46889060735702515},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.4517199993133545},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43917906284332275},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.41983309388160706},{"id":"https://openalex.org/keywords/data-redundancy","display_name":"Data redundancy","score":0.4100201725959778},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3444957733154297},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.28967753052711487},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.18421924114227295},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0893552303314209}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8185049891471863},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.6512892246246338},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6395905017852783},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6193528175354004},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.5302631258964539},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.46889060735702515},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.4517199993133545},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43917906284332275},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.41983309388160706},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.4100201725959778},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3444957733154297},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28967753052711487},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.18421924114227295},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0893552303314209},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/rs16071216","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs16071216","pdf_url":"https://www.mdpi.com/2072-4292/16/7/1216/pdf?version=1711727835","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8329b8dc16654054b6ffec2c66be5d29","is_oa":true,"landing_page_url":"https://doaj.org/article/8329b8dc16654054b6ffec2c66be5d29","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Remote Sensing, Vol 16, Iss 7, p 1216 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/rs16071216","is_oa":true,"landing_page_url":"https://doi.org/10.3390/rs16071216","pdf_url":"https://www.mdpi.com/2072-4292/16/7/1216/pdf?version=1711727835","source":{"id":"https://openalex.org/S43295729","display_name":"Remote Sensing","issn_l":"2072-4292","issn":["2072-4292"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Remote Sensing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6393876729","display_name":null,"funder_award_id":"62271409","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":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4393353220.pdf"},"referenced_works_count":72,"referenced_works":["https://openalex.org/W1999705173","https://openalex.org/W2111025459","https://openalex.org/W2194775991","https://openalex.org/W2410968923","https://openalex.org/W2412782625","https://openalex.org/W2604463754","https://openalex.org/W2618530766","https://openalex.org/W2738406610","https://openalex.org/W2739088263","https://openalex.org/W2808154247","https://openalex.org/W2867270703","https://openalex.org/W2889143500","https://openalex.org/W2890779863","https://openalex.org/W2896249043","https://openalex.org/W2898491875","https://openalex.org/W2904764169","https://openalex.org/W2905439313","https://openalex.org/W2954148997","https://openalex.org/W2962858109","https://openalex.org/W2963365374","https://openalex.org/W2963513598","https://openalex.org/W2964248351","https://openalex.org/W2968374502","https://openalex.org/W2970971581","https://openalex.org/W2972052070","https://openalex.org/W2979494843","https://openalex.org/W2998496429","https://openalex.org/W3013799809","https://openalex.org/W3034655362","https://openalex.org/W3043840704","https://openalex.org/W3088265803","https://openalex.org/W3094502228","https://openalex.org/W3094771832","https://openalex.org/W3096609285","https://openalex.org/W3100260313","https://openalex.org/W3110264553","https://openalex.org/W3132610923","https://openalex.org/W3167456680","https://openalex.org/W3174053790","https://openalex.org/W3187415662","https://openalex.org/W3200445214","https://openalex.org/W3205100603","https://openalex.org/W3210997132","https://openalex.org/W4200633401","https://openalex.org/W4206706211","https://openalex.org/W4210247145","https://openalex.org/W4210888109","https://openalex.org/W4210922240","https://openalex.org/W4212863109","https://openalex.org/W4214736485","https://openalex.org/W4223502405","https://openalex.org/W4229014680","https://openalex.org/W4283075695","https://openalex.org/W4283216168","https://openalex.org/W4285207098","https://openalex.org/W4289913092","https://openalex.org/W4300981332","https://openalex.org/W4313156423","https://openalex.org/W4313825591","https://openalex.org/W4367281558","https://openalex.org/W4380303606","https://openalex.org/W4380680196","https://openalex.org/W4386185338","https://openalex.org/W4388740367","https://openalex.org/W6631190155","https://openalex.org/W6757023456","https://openalex.org/W6757308525","https://openalex.org/W6762537594","https://openalex.org/W6772617318","https://openalex.org/W6778883912","https://openalex.org/W6796761347","https://openalex.org/W6858118161"],"related_works":["https://openalex.org/W2392100589","https://openalex.org/W2512789322","https://openalex.org/W3122828758","https://openalex.org/W2101960027","https://openalex.org/W4205958986","https://openalex.org/W2197846993","https://openalex.org/W49697837","https://openalex.org/W2586575957","https://openalex.org/W2170799233","https://openalex.org/W2800592953"],"abstract_inverted_index":{"Nowadays,":[0],"with":[1,177,205],"the":[2,61,100,112,119,126,151,184,213,228,267,279,285],"rapid":[3],"development":[4],"of":[5,25,44,91,114,121,138,187,270,281],"consumer":[6],"Unmanned":[7],"Aerial":[8],"Vehicles":[9],"(UAVs),":[10],"utilizing":[11,84],"UAV":[12],"platforms":[13],"for":[14],"visual":[15],"surveillance":[16,51],"has":[17],"become":[18],"very":[19],"attractive,":[20],"and":[21,53,73,87,97,103,108,147,201,221,234,249,251,277],"a":[22,45,130,159,192,219,255],"key":[23],"part":[24],"this":[26],"is":[27,37],"remote":[28,286],"vision-based":[29,287],"pedestrian":[30,47],"attribute":[31,42,207],"recognition.":[32],"Pedestrian":[33],"Attribute":[34,194,222],"Recognition":[35],"(PAR)":[36],"dedicated":[38],"to":[39,66,95,118,143,165,172,198,226,274],"predicting":[40],"multiple":[41],"labels":[43],"single":[46],"image":[48],"extracted":[49],"from":[50],"videos":[52],"aerial":[54],"imagery,":[55],"which":[56],"presents":[57],"significant":[58],"challenges":[59],"in":[60,83,111,150,284],"computer":[62],"vision":[63],"community":[64],"due":[65],"factors":[67],"such":[68,245],"as":[69,246],"poor":[70],"imaging":[71],"quality":[72],"substantial":[74],"pose":[75],"variations.":[76],"Despite":[77],"recent":[78],"studies":[79],"demonstrating":[80],"impressive":[81],"advancements":[82],"complicated":[85],"architectures":[86],"exploring":[88],"relations,":[89],"most":[90],"them":[92],"may":[93],"fail":[94],"fully":[96,144],"systematically":[98],"consider":[99],"inter-region,":[101],"inter-attribute,":[102],"region-attribute":[104],"mapping":[105],"relations":[106,149,204],"simultaneously":[107],"be":[109],"stuck":[110],"dilemma":[113],"information":[115],"redundancy,":[116],"leading":[117],"degradation":[120],"recognition":[122],"accuracy.":[123],"To":[124,182],"address":[125],"issues,":[127],"we":[128,156,189,216],"construct":[129],"novel":[131],"Mask-Relation-Guided":[132],"Transformer":[133],"(MRG-T)":[134],"framework":[135],"that":[136],"consists":[137],"three":[139,242],"relation":[140],"modeling":[141,283],"modules":[142],"exploit":[145],"spatial":[146,169,232],"semantic":[148,185,202,235],"model":[152],"learning":[153],"process.":[154],"Specifically,":[155],"first":[157],"propose":[158],"Masked":[160,193],"Region":[161,220],"Relation":[162,195],"Module":[163,196,224],"(MRRM)":[164],"focus":[166],"on":[167,212,241,254],"precise":[168],"attention":[170],"regions":[171,233],"extract":[173,199],"more":[174],"robust":[175],"features":[176],"masked":[178],"random":[179],"patch":[180],"training.":[181],"explore":[183],"association":[186],"attributes,":[188],"further":[190],"present":[191],"(MARM)":[197],"intrinsic":[200],"inter-attribute":[203],"an":[206],"label":[208],"masking":[209],"strategy.":[210],"Based":[211],"cross-attention":[214],"mechanism,":[215],"finally":[217],"design":[218],"Mapping":[223],"(RAMM)":[225],"learn":[227],"cross-modal":[229],"alignment":[230],"between":[231],"attributes.":[236],"We":[237],"conduct":[238,252],"comprehensive":[239],"experiments":[240],"public":[243],"benchmarks":[244],"PETA,":[247],"PA-100K,":[248],"RAPv1,":[250],"inference":[253],"large-scale":[256],"airborne":[257],"person":[258],"dataset":[259],"named":[260],"PRAI-1581.":[261],"The":[262],"extensive":[263],"experimental":[264],"results":[265],"demonstrate":[266],"superior":[268],"performance":[269],"our":[271],"method":[272],"compared":[273],"state-of-the-art":[275],"approaches":[276],"validate":[278],"effectiveness":[280],"mask-relation-guided":[282],"PAR":[288],"task.":[289]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-01-22T23:29:09.771500","created_date":"2025-10-10T00:00:00"}