{"id":"https://openalex.org/W4402916053","doi":"https://doi.org/10.1109/icip51287.2024.10647683","title":"Multimodal Transformer Using Cross-Channel Attention For Object Detection In Remote Sensing Images","display_name":"Multimodal Transformer Using Cross-Channel Attention For Object Detection In Remote Sensing Images","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402916053","doi":"https://doi.org/10.1109/icip51287.2024.10647683"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10647683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10647683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-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/A5093123104","display_name":"Bissmella Bahaduri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091279","display_name":"Universit\u00e9 Sorbonne Paris Nord","ror":"https://ror.org/0199hds37","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210091279"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Bissmella Bahaduri","raw_affiliation_strings":["University Sorbonne Paris Nord,L2TI Laboratory,Villetaneuse,France"],"affiliations":[{"raw_affiliation_string":"University Sorbonne Paris Nord,L2TI Laboratory,Villetaneuse,France","institution_ids":["https://openalex.org/I4210091279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006810592","display_name":"Zuheng Ming","orcid":"https://orcid.org/0000-0002-1094-3112"},"institutions":[{"id":"https://openalex.org/I4210091279","display_name":"Universit\u00e9 Sorbonne Paris Nord","ror":"https://ror.org/0199hds37","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210091279"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Zuheng Ming","raw_affiliation_strings":["University Sorbonne Paris Nord,L2TI Laboratory,Villetaneuse,France"],"affiliations":[{"raw_affiliation_string":"University Sorbonne Paris Nord,L2TI Laboratory,Villetaneuse,France","institution_ids":["https://openalex.org/I4210091279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104180799","display_name":"Fangchen Feng","orcid":"https://orcid.org/0000-0002-3158-3443"},"institutions":[{"id":"https://openalex.org/I4210091279","display_name":"Universit\u00e9 Sorbonne Paris Nord","ror":"https://ror.org/0199hds37","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210091279"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fangchen Feng","raw_affiliation_strings":["University Sorbonne Paris Nord,L2TI Laboratory,Villetaneuse,France"],"affiliations":[{"raw_affiliation_string":"University Sorbonne Paris Nord,L2TI Laboratory,Villetaneuse,France","institution_ids":["https://openalex.org/I4210091279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035263631","display_name":"Anissa Mokraoui","orcid":"https://orcid.org/0000-0001-6447-8722"},"institutions":[{"id":"https://openalex.org/I4210091279","display_name":"Universit\u00e9 Sorbonne Paris Nord","ror":"https://ror.org/0199hds37","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210091279"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Anissa Mokraoui","raw_affiliation_strings":["University Sorbonne Paris Nord,L2TI Laboratory,Villetaneuse,France"],"affiliations":[{"raw_affiliation_string":"University Sorbonne Paris Nord,L2TI Laboratory,Villetaneuse,France","institution_ids":["https://openalex.org/I4210091279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5093123104"],"corresponding_institution_ids":["https://openalex.org/I4210091279"],"apc_list":null,"apc_paid":null,"fwci":5.775,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.96410756,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2620","last_page":"2626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9987000226974487,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9944999814033508,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6552220582962036},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6192491054534912},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.538649320602417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5124828815460205},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4965558648109436},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.48744964599609375},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.29353243112564087},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.17812910676002502},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16183507442474365},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16155675053596497},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12896424531936646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6552220582962036},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6192491054534912},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.538649320602417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5124828815460205},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4965558648109436},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.48744964599609375},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29353243112564087},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.17812910676002502},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16183507442474365},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16155675053596497},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12896424531936646}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icip51287.2024.10647683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10647683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04761614v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04761614","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP), Oct 2024, Abu Dhabi, France. pp.2620-2626, ⟨10.1109/ICIP51287.2024.10647683⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1994616650","https://openalex.org/W2176924101","https://openalex.org/W2587989515","https://openalex.org/W2752782242","https://openalex.org/W2775906317","https://openalex.org/W2953127297","https://openalex.org/W3002271958","https://openalex.org/W3008115128","https://openalex.org/W3018757597","https://openalex.org/W3035356612","https://openalex.org/W3047401433","https://openalex.org/W3094502228","https://openalex.org/W3106808132","https://openalex.org/W3122028341","https://openalex.org/W3138516171","https://openalex.org/W3173882198","https://openalex.org/W3174906557","https://openalex.org/W3209478434","https://openalex.org/W4214493665","https://openalex.org/W4221167490","https://openalex.org/W4293584584","https://openalex.org/W4327785494","https://openalex.org/W4362470050","https://openalex.org/W4366999445","https://openalex.org/W6725448924","https://openalex.org/W6750227808","https://openalex.org/W6777046832","https://openalex.org/W6797613833","https://openalex.org/W6852824773"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Object":[0],"detection":[1,21,26,229],"in":[2,14,22,27,102,153,230],"Remote":[3],"Sensing":[4],"Images":[5],"(RSI)":[6],"is":[7,93,236],"a":[8,47,123,142],"critical":[9],"task":[10],"for":[11,128],"numerous":[12],"applications":[13],"Earth":[15],"Observation":[16],"(EO).":[17],"Differing":[18],"from":[19,62],"object":[20,25,208,228],"natural":[23],"images,":[24],"remote":[28],"sensing":[29],"images":[30],"faces":[31],"challenges":[32],"of":[33,35,41,81,98,105,108,113,141,189,215],"scarcity":[34],"annotated":[36],"data":[37,61],"and":[38,71,110,168,221],"the":[39,57,79,84,96,103,106,111,118,135,139,147,154,179,187,195,213,216,222],"presence":[40],"small":[42,207],"objects":[43],"represented":[44],"by":[45,59,90,145,182],"only":[46],"few":[48],"pixels.":[49],"Multi-modal":[50],"fusion":[51,80,126,152,219],"has":[52],"been":[53],"determined":[54],"to":[55,159,173,198,227],"enhance":[56,178],"accuracy":[58],"fusing":[60],"multiple":[63],"modalities":[64,109],"such":[65],"as":[66,157],"RGB,":[67],"infrared":[68],"(IR),":[69],"lidar,":[70],"synthetic":[72],"aperture":[73],"radar":[74],"(SAR).":[75],"To":[76],"this":[77],"end,":[78],"representations":[82],"at":[83,134,238],"mid":[85,160],"or":[86,161],"late":[87],"stage,":[88,137,156],"produced":[89],"parallel":[91],"subnetworks,":[92],"dominant,":[94],"with":[95],"disadvantages":[97],"increasing":[99],"computational":[100],"complexity":[101],"order":[104],"number":[107],"creation":[112],"additional":[114],"engineering":[115],"obstacles.":[116],"Using":[117],"cross-attention":[119],"mechanism,":[120],"we":[121,177],"propose":[122],"novel":[124],"multi-modal":[125],"strategy":[127],"mapping":[129],"relationships":[130],"between":[131],"different":[132,148],"channels":[133],"early":[136,155],"enabling":[138],"construction":[140],"coherent":[143],"input":[144],"aligning":[146],"modalities.":[149],"By":[150],"addressing":[151],"opposed":[158],"late-stage":[162],"methods,":[163],"our":[164],"method":[165],"achieves":[166],"competitive":[167],"even":[169],"superior":[170],"performance":[171],"compared":[172],"existing":[174],"techniques.":[175],"Additionally,":[176],"SWIN":[180],"transformer":[181],"integrating":[183],"convolution":[184],"layers":[185],"into":[186],"feed-forward":[188],"non-shifting":[190],"blocks.":[191],"This":[192],"augmentation":[193],"strengthens":[194],"model\u2019s":[196],"capacity":[197],"merge":[199],"separated":[200],"windows":[201],"through":[202],"local":[203],"attention,":[204],"thereby":[205],"improving":[206],"detection.":[209],"Extensive":[210],"experiments":[211],"prove":[212],"effectiveness":[214],"proposed":[217],"multimodal":[218,231],"module":[220],"architecture,":[223],"demonstrating":[224],"their":[225],"applicability":[226],"aerial":[232],"imagery.":[233],"Our":[234],"code":[235],"available":[237],"here.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}