{"id":"https://openalex.org/W4411055457","doi":"https://doi.org/10.1109/tgrs.2025.3577046","title":"Dual-Perspective Alignment Learning for Multimodal Remote Sensing Object Detection","display_name":"Dual-Perspective Alignment Learning for Multimodal Remote Sensing Object Detection","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411055457","doi":"https://doi.org/10.1109/tgrs.2025.3577046"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2025.3577046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3577046","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"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 Geoscience and Remote Sensing","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/A5100708673","display_name":"Yanfeng Liu","orcid":"https://orcid.org/0000-0002-8000-8904"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanfeng Liu","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, Wuhan, P. R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, Wuhan, P. R. China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648538","display_name":"Wei Guo","orcid":"https://orcid.org/0000-0001-8616-0221"},"institutions":[{"id":"https://openalex.org/I2802615301","display_name":"China Aerospace Science and Technology Corporation","ror":"https://ror.org/01z8tr155","country_code":"CN","type":"government","lineage":["https://openalex.org/I2802615301"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Guo","raw_affiliation_strings":["Multisensor Intelligent Detection and Recognition Technologies R&D Center, China Aerospace Science and Technology Corporation, Chengdu, China","Multisensor Intelligent Detection and Recognition Technologies R and D Center of CASC, Chengdu, P. R. China"],"affiliations":[{"raw_affiliation_string":"Multisensor Intelligent Detection and Recognition Technologies R&D Center, China Aerospace Science and Technology Corporation, Chengdu, China","institution_ids":["https://openalex.org/I2802615301"]},{"raw_affiliation_string":"Multisensor Intelligent Detection and Recognition Technologies R and D Center of CASC, Chengdu, P. R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002800252","display_name":"Chaojun Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I2802615301","display_name":"China Aerospace Science and Technology Corporation","ror":"https://ror.org/01z8tr155","country_code":"CN","type":"government","lineage":["https://openalex.org/I2802615301"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaojun Yao","raw_affiliation_strings":["Multisensor Intelligent Detection and Recognition Technologies R&D Center, China Aerospace Science and Technology Corporation, Chengdu, China","Multisensor Intelligent Detection and Recognition Technologies R and D Center of CASC, Chengdu, P. R. China"],"affiliations":[{"raw_affiliation_string":"Multisensor Intelligent Detection and Recognition Technologies R&D Center, China Aerospace Science and Technology Corporation, Chengdu, China","institution_ids":["https://openalex.org/I2802615301"]},{"raw_affiliation_string":"Multisensor Intelligent Detection and Recognition Technologies R and D Center of CASC, Chengdu, P. R. China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024278302","display_name":"Lefei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lefei Zhang","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, Wuhan, P. R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, Wuhan, P. R. China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100708673"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":21.682,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.99729593,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"63","issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13890","display_name":"Remote Sensing and Land Use","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1902","display_name":"Atmospheric Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13890","display_name":"Remote Sensing and Land Use","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1902","display_name":"Atmospheric Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.9093999862670898,"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/perspective","display_name":"Perspective (graphical)","score":0.7238092422485352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6914224624633789},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.6369560360908508},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5918752551078796},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5308642983436584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47509992122650146},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45983925461769104},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43139633536338806},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2284412980079651},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.168796569108963}],"concepts":[{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.7238092422485352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6914224624633789},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.6369560360908508},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5918752551078796},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5308642983436584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47509992122650146},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45983925461769104},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43139633536338806},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2284412980079651},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.168796569108963},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2025.3577046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3577046","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"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 Geoscience and Remote Sensing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G457964128","display_name":null,"funder_award_id":"62431020","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":62,"referenced_works":["https://openalex.org/W1910108985","https://openalex.org/W2176924101","https://openalex.org/W2601564443","https://openalex.org/W2884561390","https://openalex.org/W2941769495","https://openalex.org/W2963604034","https://openalex.org/W2966926453","https://openalex.org/W3035694605","https://openalex.org/W3036931590","https://openalex.org/W3092663126","https://openalex.org/W3106808132","https://openalex.org/W3136761610","https://openalex.org/W3152008128","https://openalex.org/W3154360923","https://openalex.org/W3196107618","https://openalex.org/W3207919963","https://openalex.org/W4200631567","https://openalex.org/W4205932092","https://openalex.org/W4206019878","https://openalex.org/W4214507171","https://openalex.org/W4220724622","https://openalex.org/W4224919677","https://openalex.org/W4282919254","https://openalex.org/W4285215809","https://openalex.org/W4285600783","https://openalex.org/W4293428377","https://openalex.org/W4296211836","https://openalex.org/W4312594135","https://openalex.org/W4313160378","https://openalex.org/W4317738568","https://openalex.org/W4327785494","https://openalex.org/W4365801723","https://openalex.org/W4376607793","https://openalex.org/W4382468624","https://openalex.org/W4383503565","https://openalex.org/W4384080543","https://openalex.org/W4385237236","https://openalex.org/W4385975752","https://openalex.org/W4386189887","https://openalex.org/W4386591405","https://openalex.org/W4387092712","https://openalex.org/W4387968078","https://openalex.org/W4388756945","https://openalex.org/W4388854490","https://openalex.org/W4389319234","https://openalex.org/W4389880076","https://openalex.org/W4391559729","https://openalex.org/W4392207662","https://openalex.org/W4392796741","https://openalex.org/W4394002435","https://openalex.org/W4394593074","https://openalex.org/W4394698558","https://openalex.org/W4395447471","https://openalex.org/W4396941249","https://openalex.org/W4398760112","https://openalex.org/W4401635338","https://openalex.org/W4401723130","https://openalex.org/W4401750548","https://openalex.org/W4402041007","https://openalex.org/W4402569181","https://openalex.org/W4404004775","https://openalex.org/W6618372016"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2018871932","https://openalex.org/W641279757","https://openalex.org/W370975646","https://openalex.org/W1670566515","https://openalex.org/W4242022592","https://openalex.org/W596972243","https://openalex.org/W2149537132","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Recently,":[0],"anchor-based":[1],"detectors":[2],"can":[3],"achieve":[4],"decent":[5],"performance":[6],"in":[7,32,84],"multimodal":[8,33,47,132],"remote":[9,48],"sensing":[10,49],"scenarios,":[11],"whereas":[12],"their":[13],"anchor-free":[14,125],"counterparts":[15],"fail":[16],"to":[17,78,108],"reach":[18],"comparable":[19],"results.":[20],"To":[21],"remedy":[22],"this":[23],"problem,":[24],"we":[25,53,89],"first":[26],"comprehensively":[27],"investigate":[28],"the":[29,62,81,140],"misalignment":[30,82],"issues":[31],"features":[34],"and":[35,38,66,86,113],"detection":[36,126,134],"heads,":[37,88],"present":[39],"a":[40,55,91,98,103],"dual-perspective":[41],"alignment":[42,57,68,93,123],"learning":[43],"(DPAL)":[44],"framework":[45],"for":[46,73,124],"object":[50,133],"detection.":[51],"Particularly,":[52],"design":[54],"cross-modal":[56,74],"module":[58,94],"(CMAM),":[59],"which":[60],"utilizes":[61],"multiscale":[63],"dilation":[64],"strategy":[65,107],"differentiable":[67],"function":[69],"with":[70,80,121],"channel-wise":[71],"modulation":[72],"feature":[75],"integration.":[76],"Additionally,":[77],"cope":[79],"problem":[83],"regression":[85],"classification":[87],"propose":[90],"task-head":[92],"(THAM).":[95],"It":[96],"presents":[97],"novel":[99],"pseudo-anchor":[100],"mechanism,":[101],"introduces":[102],"semi-fixed":[104],"offset":[105,117],"generation":[106],"capture":[109],"task-variant":[110],"sampling":[111],"coordinates,":[112],"ultimately":[114],"deploys":[115],"an":[116],"knowledge":[118],"transfer":[119],"mechanism":[120],"deformable":[122],"heads.":[127],"Extensive":[128],"experiments":[129],"on":[130],"four":[131],"datasets":[135],"show":[136],"impressive":[137],"results":[138],"of":[139],"proposed":[141],"DPAL":[142],"framework.":[143],"The":[144],"project":[145],"code":[146],"is":[147],"released":[148],"at":[149],"https://github.com/lyf0801/DPAL.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":12}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}