{"id":"https://openalex.org/W4415708247","doi":"https://doi.org/10.1109/icme59968.2025.11208926","title":"Rethinking Cross-Modality Fusion Mamba from a Frequency Domain Perspective","display_name":"Rethinking Cross-Modality Fusion Mamba from a Frequency Domain Perspective","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708247","doi":"https://doi.org/10.1109/icme59968.2025.11208926"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11208926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100379691","display_name":"Zeyu Wang","orcid":"https://orcid.org/0000-0002-1223-1661"},"institutions":[{"id":"https://openalex.org/I135237710","display_name":"Zhejiang Normal University","ror":"https://ror.org/01vevwk45","country_code":"CN","type":"education","lineage":["https://openalex.org/I135237710"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Wang","raw_affiliation_strings":["Zhejiang Normal University,Computer Science and Technology,JinHua,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Normal University,Computer Science and Technology,JinHua,China","institution_ids":["https://openalex.org/I135237710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080753121","display_name":"Huiying Xu","orcid":"https://orcid.org/0000-0002-6704-0301"},"institutions":[{"id":"https://openalex.org/I135237710","display_name":"Zhejiang Normal University","ror":"https://ror.org/01vevwk45","country_code":"CN","type":"education","lineage":["https://openalex.org/I135237710"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiying Xu","raw_affiliation_strings":["Zhejiang Normal University,Computer Science and Technology,JinHua,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Normal University,Computer Science and Technology,JinHua,China","institution_ids":["https://openalex.org/I135237710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054138565","display_name":"Yun Liu","orcid":"https://orcid.org/0000-0003-3593-2011"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Liu","raw_affiliation_strings":["Nankai University,College of Computer Science,TianJin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,College of Computer Science,TianJin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054589801","display_name":"Chen Li","orcid":"https://orcid.org/0000-0002-1544-8487"},"institutions":[{"id":"https://openalex.org/I135237710","display_name":"Zhejiang Normal University","ror":"https://ror.org/01vevwk45","country_code":"CN","type":"education","lineage":["https://openalex.org/I135237710"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Li","raw_affiliation_strings":["Zhejiang Normal University,Computer Science and Technology,JinHua,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Normal University,Computer Science and Technology,JinHua,China","institution_ids":["https://openalex.org/I135237710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671239","display_name":"Xinzhong Zhu","orcid":"https://orcid.org/0000-0002-0033-5260"},"institutions":[{"id":"https://openalex.org/I135237710","display_name":"Zhejiang Normal University","ror":"https://ror.org/01vevwk45","country_code":"CN","type":"education","lineage":["https://openalex.org/I135237710"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinzhong Zhu","raw_affiliation_strings":["Zhejiang Normal University,Computer Science and Technology,JinHua,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Normal University,Computer Science and Technology,JinHua,China","institution_ids":["https://openalex.org/I135237710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450120","display_name":"Xiaolei Zhang","orcid":"https://orcid.org/0000-0003-3701-2032"},"institutions":[{"id":"https://openalex.org/I135237710","display_name":"Zhejiang Normal University","ror":"https://ror.org/01vevwk45","country_code":"CN","type":"education","lineage":["https://openalex.org/I135237710"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolei Zhang","raw_affiliation_strings":["Zhejiang Normal University,JinHua,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Normal University,JinHua,China","institution_ids":["https://openalex.org/I135237710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022509104","display_name":"Hongbo Li","orcid":"https://orcid.org/0000-0003-1662-8815"},"institutions":[{"id":"https://openalex.org/I4210137038","display_name":"Geological Exploration Technology Institute of Jiangsu Province","ror":"https://ror.org/03md1xx44","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210137038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbo Li","raw_affiliation_strings":["Geekplus Technology,BeiJing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Geekplus Technology,BeiJing,China","institution_ids":["https://openalex.org/I4210137038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11659","display_name":"Advanced Image Fusion Techniques","score":0.6607000231742859,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.6607000231742859,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.23319999873638153,"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":0.015799999237060547,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5837000012397766},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5577999949455261},{"id":"https://openalex.org/keywords/multispectral-image","display_name":"Multispectral image","score":0.51419997215271},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.5045999884605408},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4636000096797943},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4593999981880188},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4526999890804291},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.44859999418258667},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.4397999942302704},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.43160000443458557}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6107000112533569},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5837000012397766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5728999972343445},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5577999949455261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5350000262260437},{"id":"https://openalex.org/C173163844","wikidata":"https://www.wikidata.org/wiki/Q1761440","display_name":"Multispectral image","level":2,"score":0.51419997215271},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.5045999884605408},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4636000096797943},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4526999890804291},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.44859999418258667},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.4397999942302704},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43130001425743103},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.41850000619888306},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4178999960422516},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C121927907","wikidata":"https://www.wikidata.org/wiki/Q1952516","display_name":"Multiresolution analysis","level":5,"score":0.40689998865127563},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.38440001010894775},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.37299999594688416},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35010001063346863},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.29600000381469727},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C100921725","wikidata":"https://www.wikidata.org/wiki/Q1650811","display_name":"Spatial frequency","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26330000162124634},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11208926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1910108985","https://openalex.org/W2194775991","https://openalex.org/W2963188557","https://openalex.org/W2980088508","https://openalex.org/W3036931590","https://openalex.org/W3118570274","https://openalex.org/W3154706820","https://openalex.org/W3213472242","https://openalex.org/W4200631567","https://openalex.org/W4308310215","https://openalex.org/W4312832682","https://openalex.org/W4385801610","https://openalex.org/W4386189887","https://openalex.org/W4391849436","https://openalex.org/W4402754006","https://openalex.org/W4403770406","https://openalex.org/W4403887646","https://openalex.org/W4410915127"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,57],"Cross-Modality":[4],"Fusion":[5],"method":[6,60,89],"for":[7],"multispectral":[8],"object":[9],"detection":[10],"(MSOD),":[11],"which":[12],"is":[13],"based":[14,61],"on":[15,62],"State":[16],"Space":[17],"Model":[18],"(SSM)":[19],"and":[20,44,94],"frequency":[21,36],"modeling.":[22],"The":[23],"approach":[24],"benefits":[25],"from":[26,51],"efficient":[27],"long-range":[28],"dependency":[29],"modeling":[30],"by":[31],"processing":[32],"the":[33,39,69],"perceptually":[34],"significant":[35],"information":[37,81],"within":[38],"complex":[40],"coupling":[41],"of":[42,72],"RGB":[43],"infrared":[45],"(IR)":[46],"images,":[47],"integrating":[48],"global":[49],"context":[50],"different":[52],"modalities.":[53],"Additionally,":[54],"we":[55],"propose":[56],"novel":[58],"down-sampling":[59],"wavelet":[63],"transform":[64],"(WT),":[65],"designed":[66],"to":[67],"reduce":[68],"spatial":[70],"resolution":[71],"feature":[73],"maps":[74],"while":[75],"filtering":[76],"out":[77],"as":[78,82],"much":[79],"redundant":[80],"possible.":[83],"Experimental":[84],"results":[85],"demonstrate":[86],"that":[87],"our":[88],"achieves":[90],"state-of-the-art":[91],"(SOTA)":[92],"performance":[93],"faster":[95],"inference":[96],"in":[97],"MSOD.":[98]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}