{"id":"https://openalex.org/W4408354978","doi":"https://doi.org/10.1109/icassp49660.2025.10889359","title":"Rethinking Early-Fusion Strategies for Improved Multimodal Image Segmentation","display_name":"Rethinking Early-Fusion Strategies for Improved Multimodal Image Segmentation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354978","doi":"https://doi.org/10.1109/icassp49660.2025.10889359"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5054023409","display_name":"Zhengwen Shen","orcid":"https://orcid.org/0009-0007-9840-6242"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhengwen Shen","raw_affiliation_strings":["China University of Mining and Technology,School of Information and Control Engineering,Xuzhou,China,221116"],"affiliations":[{"raw_affiliation_string":"China University of Mining and Technology,School of Information and Control Engineering,Xuzhou,China,221116","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085600894","display_name":"Yulian Li","orcid":"https://orcid.org/0000-0002-7314-6399"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulian Li","raw_affiliation_strings":["China University of Mining and Technology,School of Information and Control Engineering,Xuzhou,China,221116"],"affiliations":[{"raw_affiliation_string":"China University of Mining and Technology,School of Information and Control Engineering,Xuzhou,China,221116","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399265","display_name":"Han Zhang","orcid":"https://orcid.org/0000-0001-8498-3451"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Zhang","raw_affiliation_strings":["China University of Mining and Technology,School of Information and Control Engineering,Xuzhou,China,221116"],"affiliations":[{"raw_affiliation_string":"China University of Mining and Technology,School of Information and Control Engineering,Xuzhou,China,221116","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101527944","display_name":"Yuchen Weng","orcid":"https://orcid.org/0009-0005-4219-3108"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Weng","raw_affiliation_strings":["China University of Mining and Technology,School of Information and Control Engineering,Xuzhou,China,221116"],"affiliations":[{"raw_affiliation_string":"China University of Mining and Technology,School of Information and Control Engineering,Xuzhou,China,221116","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100384686","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-1305-5735"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["China University of Mining and Technology,School of Information and Control Engineering,Xuzhou,China,221116"],"affiliations":[{"raw_affiliation_string":"China University of Mining and Technology,School of Information and Control Engineering,Xuzhou,China,221116","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5054023409"],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":null,"apc_paid":null,"fwci":1.3104,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77913386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.2329999953508377,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.2329999953508377,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.2012999951839447,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/artificial-intelligence","display_name":"Artificial intelligence","score":0.665885329246521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6571077108383179},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.6160289645195007},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6132180094718933},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.5523310303688049},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5128829479217529},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5011019706726074},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.44637003540992737},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4086461663246155}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.665885329246521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6571077108383179},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6160289645195007},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6132180094718933},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.5523310303688049},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5128829479217529},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5011019706726074},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.44637003540992737},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4086461663246155},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323154","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2412782625","https://openalex.org/W2774839435","https://openalex.org/W2921749009","https://openalex.org/W3091001089","https://openalex.org/W3166016280","https://openalex.org/W3198062544","https://openalex.org/W3211490618","https://openalex.org/W4200635035","https://openalex.org/W4225487034","https://openalex.org/W4296913506","https://openalex.org/W4312530435","https://openalex.org/W4312847199","https://openalex.org/W4313639507","https://openalex.org/W4366147345","https://openalex.org/W4367663172","https://openalex.org/W4376464632","https://openalex.org/W4381300351","https://openalex.org/W4386179772","https://openalex.org/W4390873110","https://openalex.org/W4396920227","https://openalex.org/W4398224523","https://openalex.org/W4401593054"],"related_works":["https://openalex.org/W1986655823","https://openalex.org/W2788731446","https://openalex.org/W2204403038","https://openalex.org/W3152170969","https://openalex.org/W2185902295","https://openalex.org/W2103507220","https://openalex.org/W2379054866","https://openalex.org/W3144569342","https://openalex.org/W3011384228","https://openalex.org/W2124969951"],"abstract_inverted_index":{"RGB":[0],"and":[1,28,38,51,58,78,98,118,126],"thermal":[2],"image":[3],"fusion":[4,32,39,69,76],"have":[5],"great":[6],"potential":[7],"to":[8,34],"exhibit":[9],"improved":[10],"semantic":[11,42,89],"segmentation":[12],"in":[13],"low-illumination":[14],"conditions.":[15],"Existing":[16],"methods":[17,46,122],"typically":[18],"employ":[19],"a":[20,66,79,96],"two-branch":[21],"encoder":[22],"framework":[23],"for":[24,40,85],"multimodal":[25,41,68],"feature":[26,31,36,56,83,101],"extraction":[27,37,57],"design":[29],"complicated":[30],"strategies":[33],"achieve":[35],"segmentation.":[43,90],"However,":[44],"these":[45],"require":[47],"massive":[48],"parameter":[49],"updates":[50],"computational":[52],"effort":[53],"during":[54],"the":[55,110],"fusion.":[59],"To":[60],"address":[61],"this":[62],"issue,":[63],"we":[64,93],"propose":[65,95],"novel":[67],"network":[70],"(EFNet)":[71],"based":[72,104],"on":[73,105,115],"an":[74],"early":[75],"strategy":[77],"simple":[80],"but":[81],"effective":[82],"clustering":[84],"training":[86],"efficient":[87,99],"RGB-T":[88],"In":[91],"addition,":[92],"also":[94],"lightweight":[97],"multi-scale":[100],"aggregation":[102],"decoder":[103],"Euclidean":[106],"distance.":[107],"We":[108],"validate":[109],"effectiveness":[111],"of":[112],"our":[113],"method":[114],"different":[116],"datasets":[117],"outperform":[119],"previous":[120],"state-of-the-art":[121],"with":[123],"lower":[124],"parameters":[125],"computation.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}