{"id":"https://openalex.org/W7201854164","doi":"https://doi.org/10.1145/3767308.3835247","title":"URNet: A Unified Reparameterized Network for Efficient RGB-D Semantic Segmentation","display_name":"URNet: A Unified Reparameterized Network for Efficient RGB-D Semantic Segmentation","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7201854164","doi":"https://doi.org/10.1145/3767308.3835247"},"language":"en","primary_location":{"id":"doi:10.1145/3767308.3835247","doi":"https://doi.org/10.1145/3767308.3835247","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767308.3835247","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3767308.3835247","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133693412","display_name":"Guoan Xu","orcid":"https://orcid.org/0000-0002-0181-4140","observed_orcids":["https://orcid.org/0000-0002-0181-4140"]},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guoan Xu","raw_affiliation_strings":["University of Technology Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0181-4140","affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050214771","display_name":"Zhengxue Wang","orcid":"https://orcid.org/0000-0002-4668-2559","observed_orcids":["https://orcid.org/0000-0002-4668-2559"]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengxue Wang","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-4668-2559","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146014414","display_name":"Yang Xiao","orcid":"https://orcid.org/0009-0009-9662-7521","observed_orcids":["https://orcid.org/0009-0009-9662-7521"]},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yang Xiao","raw_affiliation_strings":["University of Technology Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0009-0009-9662-7521","affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5145981040","display_name":"Ligeng Chen","orcid":"https://orcid.org/0000-0002-0076-3708","observed_orcids":["https://orcid.org/0000-0002-0076-3708"]},"institutions":[{"id":"https://openalex.org/I4405287589","display_name":"Honor Device (China)","ror":"https://ror.org/05m3v9803","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405287589"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ligeng Chen","raw_affiliation_strings":["Honor Device Co., Ltd, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0076-3708","affiliations":[{"raw_affiliation_string":"Honor Device Co., Ltd, Beijing, China","institution_ids":["https://openalex.org/I4405287589"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038362365","display_name":"Guangwei Gao","orcid":"https://orcid.org/0000-0002-3950-1844","observed_orcids":["https://orcid.org/0000-0002-3950-1844","https://orcid.org/0009-0003-9412-4281"]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangwei Gao","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-3950-1844","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078385469","display_name":"Dongchen Zhu","orcid":"https://orcid.org/0000-0002-1579-3942","observed_orcids":["https://orcid.org/0000-0002-1579-3942"]},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongchen Zhu","raw_affiliation_strings":["Shanghai Institute of Microsystem and Information Technology, CAS, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1579-3942","affiliations":[{"raw_affiliation_string":"Shanghai Institute of Microsystem and Information Technology, CAS, Shanghai, China","institution_ids":["https://openalex.org/I4210147322"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.53285654,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12432","last_page":"12440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9839000105857849,"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":0.9839000105857849,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.006599999964237213,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.0035000001080334187,"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/rgb-d-semantic-segmentation","display_name":"RGB-D semantic segmentation","score":1.0},{"id":"https://openalex.org/keywords/reparameterization","display_name":"reparameterization","score":0.8500000238418579},{"id":"https://openalex.org/keywords/cross-modal-feature-fusion","display_name":"cross-modal feature fusion","score":0.9570000171661377},{"id":"https://openalex.org/keywords/depth-representation","display_name":"depth representation","score":0.6600000262260437},{"id":"https://openalex.org/keywords/lightweight-neural-networks","display_name":"lightweight neural networks","score":0.46000000834465027},{"id":"https://openalex.org/keywords/multiscale-feature-extraction","display_name":"multi-scale feature extraction","score":0.4819999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7789999842643738},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7023000121116638},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6539000272750854},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6288999915122986},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6180999875068665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5756000280380249},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5324000120162964},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5270000100135803},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5192000269889832},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.477400004863739},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47040000557899475},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46779999136924744},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.44339999556541443},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.38339999318122864},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3490000069141388},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2994999885559082},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.29600000381469727},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.25519999861717224},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3767308.3835247","doi":"https://doi.org/10.1145/3767308.3835247","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767308.3835247","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.05671","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.05671","pdf_url":"https://arxiv.org/pdf/2608.05671","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.05671","doi":"https://doi.org/10.48550/arxiv.2608.05671","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.05671","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3767308.3835247","doi":"https://doi.org/10.1145/3767308.3835247","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767308.3835247","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7201854164.pdf","grobid_xml":"https://content.openalex.org/works/W7201854164.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W3094502228","https://openalex.org/W3203105104","https://openalex.org/W4399400959","https://openalex.org/W4406880412","https://openalex.org/W7140225076","https://openalex.org/W7154484183"],"related_works":["https://openalex.org/W4409562523","https://openalex.org/W4413826263","https://openalex.org/W4402818207","https://openalex.org/W7212152360","https://openalex.org/W4405001351","https://openalex.org/W4404608853","https://openalex.org/W4313000235","https://openalex.org/W4385938250","https://openalex.org/W7125927915","https://openalex.org/W4416805561"],"abstract_inverted_index":{"Previous":[0],"RGB-D":[1,60,126,147],"semantic":[2],"segmentation":[3,127,148],"methods":[4],"commonly":[5],"employ":[6],"dual":[7],"encoders":[8],"to":[9,81,103],"separately":[10],"process":[11],"RGB":[12,107],"and":[13,32,68,86,108],"depth":[14,30,109],"inputs,":[15],"followed":[16],"by":[17],"dedicated":[18],"modules":[19],"for":[20],"cross-modal":[21,36,69],"feature":[22,66,113],"fusion.":[23],"However,":[24],"such":[25],"designs":[26],"often":[27],"inadequately":[28],"capture":[29],"representations":[31],"consequently":[33],"limit":[34],"effective":[35,134],"interaction,":[37],"while":[38,156],"the":[39,83,138],"additional":[40],"encoder":[41],"branch":[42],"introduces":[43],"redundant":[44],"computation":[45],"that":[46,62,117,151],"hinders":[47],"lightweight":[48],"execution.":[49],"To":[50],"tackle":[51],"these":[52],"challenges,":[53],"we":[54,76,129],"propose":[55],"URNet,":[56],"a":[57,72,78,95,131],"Unified":[58],"Reparameterized":[59,92],"Network":[61],"performs":[63],"simultaneous":[64],"multi-modal":[65],"extraction":[67],"fusion":[70],"within":[71],"single":[73],"encoder.":[74],"Specifically,":[75],"adopt":[77],"reparameterization":[79],"strategy":[80],"compact":[82],"network":[84],"architecture":[85],"facilitate":[87],"fast":[88],"inference.":[89],"Within":[90],"each":[91],"Block":[93],"(RepBlock),":[94],"Linear":[96],"Gated":[97],"Attention":[98],"(LGA)":[99],"module":[100],"is":[101],"introduced":[102],"fully":[104],"exploit":[105],"complementary":[106],"cues":[110],"across":[111],"different":[112],"scales.":[114],"Furthermore,":[115],"considering":[116],"decoder":[118],"design":[119],"has":[120],"been":[121],"relatively":[122],"underexplored":[123],"in":[124],"existing":[125],"models,":[128],"develop":[130],"concise":[132],"yet":[133],"universal":[135],"decoder,":[136],"termed":[137],"Pyramid":[139],"Merging":[140],"Decoder":[141],"(PMD).":[142],"Extensive":[143],"experiments":[144],"on":[145],"multiple":[146],"benchmarks":[149],"demonstrate":[150],"URNet":[152],"achieves":[153],"state-of-the-art":[154],"performance":[155],"maintaining":[157],"high":[158],"efficiency.":[159],"Code":[160],"will":[161],"be":[162],"available":[163],"at":[164],"https://github.com/Wild-Stephen/URNet.":[165]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-08-08T00:00:00"}