{"id":"https://openalex.org/W4415707479","doi":"https://doi.org/10.1109/tits.2025.3624821","title":"USformer: A U-Shaped Structure Transformer for RGB-Thermal Semantic Segmentation and Traffic Scene Understanding","display_name":"USformer: A U-Shaped Structure Transformer for RGB-Thermal Semantic Segmentation and Traffic Scene Understanding","publication_year":2025,"publication_date":"2025-10-30","ids":{"openalex":"https://openalex.org/W4415707479","doi":"https://doi.org/10.1109/tits.2025.3624821"},"language":null,"primary_location":{"id":"doi:10.1109/tits.2025.3624821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2025.3624821","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","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/A5056976700","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0003-4689-265X"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["Faculty of Information Science and Engineering, Ningbo University, Ningbo, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Engineering, Ningbo University, Ningbo, China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049898953","display_name":"Feng Shao","orcid":"https://orcid.org/0000-0002-2495-9924"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Shao","raw_affiliation_strings":["Faculty of Information Science and Engineering, Ningbo University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0002-2495-9924","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Engineering, Ningbo University, Ningbo, China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021988709","display_name":"Baoyang Mu","orcid":"https://orcid.org/0000-0003-2898-0461"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoyang Mu","raw_affiliation_strings":["Faculty of Information Science and Engineering, Ningbo University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0003-2898-0461","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Engineering, Ningbo University, Ningbo, China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030554236","display_name":"Xiongli Chai","orcid":"https://orcid.org/0000-0002-4245-5391"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongli Chai","raw_affiliation_strings":["Faculty of Information Science and Engineering, Ningbo University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0002-4245-5391","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Engineering, Ningbo University, Ningbo, China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000581688","display_name":"Qiuping Jiang","orcid":"https://orcid.org/0000-0002-6025-9343"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuping Jiang","raw_affiliation_strings":["Faculty of Information Science and Engineering, Ningbo University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0002-6025-9343","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Engineering, Ningbo University, Ningbo, China","institution_ids":["https://openalex.org/I109935558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I109935558"],"apc_list":null,"apc_paid":null,"fwci":2.6469,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91337178,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"27","issue":"1","first_page":"623","last_page":"638"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9818000197410583,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9818000197410583,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.004699999932199717,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/segmentation","display_name":"Segmentation","score":0.5728999972343445},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5192000269889832},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.45829999446868896},{"id":"https://openalex.org/keywords/intelligent-transportation-system","display_name":"Intelligent transportation system","score":0.4544999897480011},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.4269999861717224},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.39820000529289246},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3871999979019165},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.3650999963283539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047000169754028},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5728999972343445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5493000149726868},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5192000269889832},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.45829999446868896},{"id":"https://openalex.org/C47796450","wikidata":"https://www.wikidata.org/wiki/Q508378","display_name":"Intelligent transportation system","level":2,"score":0.4544999897480011},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.4269999861717224},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28029999136924744},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27469998598098755},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.25769999623298645},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2025.3624821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2025.3624821","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1436512708","display_name":null,"funder_award_id":"62271277","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4827762829","display_name":null,"funder_award_id":"2024Z113","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W1910108985","https://openalex.org/W1923184257","https://openalex.org/W2117539524","https://openalex.org/W2412782625","https://openalex.org/W2560023338","https://openalex.org/W2565639579","https://openalex.org/W2774839435","https://openalex.org/W2799166040","https://openalex.org/W2884822772","https://openalex.org/W2921749009","https://openalex.org/W2962914239","https://openalex.org/W2963881378","https://openalex.org/W2963890956","https://openalex.org/W2965391153","https://openalex.org/W2990479855","https://openalex.org/W2993470448","https://openalex.org/W2996106355","https://openalex.org/W3033020497","https://openalex.org/W3091001089","https://openalex.org/W3096609285","https://openalex.org/W3138511503","https://openalex.org/W3138516171","https://openalex.org/W3166016280","https://openalex.org/W3170841864","https://openalex.org/W3182674219","https://openalex.org/W3206439726","https://openalex.org/W3214829036","https://openalex.org/W4225487034","https://openalex.org/W4225531230","https://openalex.org/W4226213342","https://openalex.org/W4226245048","https://openalex.org/W4284892523","https://openalex.org/W4296473479","https://openalex.org/W4296913506","https://openalex.org/W4312812783","https://openalex.org/W4312815172","https://openalex.org/W4313139043","https://openalex.org/W4313639507","https://openalex.org/W4318033725","https://openalex.org/W4319866558","https://openalex.org/W4321483876","https://openalex.org/W4366147345","https://openalex.org/W4367663172","https://openalex.org/W4376464632","https://openalex.org/W4379209584","https://openalex.org/W4381198666","https://openalex.org/W4386071839","https://openalex.org/W4386179772","https://openalex.org/W4386275800","https://openalex.org/W4386737248","https://openalex.org/W4388076873","https://openalex.org/W4388191449","https://openalex.org/W4389252765","https://openalex.org/W4390489106","https://openalex.org/W4391020313","https://openalex.org/W4392607696","https://openalex.org/W4394593166","https://openalex.org/W4400111301","https://openalex.org/W4405096695","https://openalex.org/W4406757300","https://openalex.org/W4408378466"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2],"multimodal":[3],"approaches,":[4],"particularly":[5],"RGB-thermal":[6],"(RGB-T)":[7],"segmentation,":[8],"have":[9],"significantly":[10],"promote":[11],"the":[12,30,42,53,83,104,119,164,169,177],"development":[13],"of":[14,33,56,86],"Intelligent":[15],"Transportation":[16],"Systems":[17],"(ITS).":[18],"However,":[19],"existing":[20,57],"methods":[21,58],"still":[22],"encounter":[23],"challenges":[24],"related":[25],"to":[26,127,167],"modality":[27,126],"discrepancy":[28],"and":[29,70,89,106,116,143,159,175,183],"effective":[31],"integration":[32],"multi-scale":[34],"features.":[35,92],"To":[36],"address":[37],"these":[38],"issues,":[39],"we":[40,162],"propose":[41],"U-shaped":[43,63,150],"Structure":[44],"Transformer":[45],"(USformer)":[46],"for":[47],"RGB-T":[48,190],"semantic":[49,88],"segmentation.":[50],"We":[51],"improve":[52,176],"feature":[54,131,157],"flow":[55],"by":[59,133],"designing":[60],"a":[61,135],"novel":[62],"encoding":[64,151],"network":[65],"that":[66,81,193],"integrates":[67],"inter-layer":[68,78],"fusion":[69,85,97],"cross-modal":[71],"fusion.":[72,160],"Specifically,":[73],"our":[74,96,149,194],"method":[75],"introduces":[76],"an":[77],"interaction":[79],"mechanism":[80],"facilitates":[82],"iterative":[84],"high-level":[87],"low-level":[90],"detail":[91],"For":[93],"each":[94,125],"layer,":[95],"process":[98],"is":[99],"divided":[100],"into":[101,148],"two":[102],"stages:":[103],"Cross-Modal":[105],"-Scale":[107],"Auxiliary":[108],"(CMSA)":[109],"module":[110],"enforces":[111],"distribution":[112],"alignment":[113,158],"across":[114,179],"modalities":[115],"scales,":[117],"while":[118],"Cross-Attention":[120],"Feature":[121],"Merger":[122],"(CAFM)":[123],"allows":[124],"refine":[128],"its":[129],"own":[130],"selection":[132],"employing":[134],"multi-head":[136],"cross-attention":[137],"mechanism.":[138],"These":[139],"modules":[140],"effectively":[141],"adapt":[142],"integrate":[144],"well-established":[145],"attention":[146],"designs":[147],"architecture,":[152],"thereby":[153],"achieving":[154],"efficient":[155],"multi-modal":[156],"Finally,":[161],"utilize":[163],"Mask2Former":[165],"decoder":[166],"aggregate":[168],"fused":[170],"features":[171],"from":[172],"multiple":[173],"layers":[174],"segmentation":[178],"various":[180],"object":[181],"sizes":[182],"complex":[184],"scenes.":[185],"Extensive":[186],"experiments":[187],"on":[188],"four":[189],"datasets":[191],"demonstrate":[192],"proposed":[195],"USformer":[196],"achieves":[197],"state-of-the-art":[198],"performance.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-30T00:00:00"}