{"id":"https://openalex.org/W7161138516","doi":"https://doi.org/10.1109/lsp.2026.3693589","title":"APNet: Accurate Prompting Network With Modality Guidance and Structural Awareness for RGB-D Semantic Segmentation","display_name":"APNet: Accurate Prompting Network With Modality Guidance and Structural Awareness for RGB-D Semantic Segmentation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7161138516","doi":"https://doi.org/10.1109/lsp.2026.3693589"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2026.3693589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3693589","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.lancs.ac.uk/id/eprint/238136/1/SPL.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136183071","display_name":"Junzhe Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junzhe Zhao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0006-1956-2275","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068040780","display_name":"Jintao Su","orcid":"https://orcid.org/0000-0002-2755-5909"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jintao Su","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136184955","display_name":"Jun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["School of Computing and Communications, Lancaster University, Lancaster, U.K"],"raw_orcid":"https://orcid.org/0000-0002-4365-4165","affiliations":[{"raw_affiliation_string":"School of Computing and Communications, Lancaster University, Lancaster, U.K","institution_ids":["https://openalex.org/I67415387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080596209","display_name":"Miaohui Wang","orcid":"https://orcid.org/0000-0003-1125-9299"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miaohui Wang","raw_affiliation_strings":["Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1125-9299","affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136139723","display_name":"Ye Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Liu","raw_affiliation_strings":["College of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-2686-3002","affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.59239385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"2131","last_page":"2135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7099000215530396,"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":0.7099000215530396,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.05990000069141388,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.0333000011742115,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5898000001907349},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5841000080108643},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.45249998569488525},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3702999949455261},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.35519999265670776},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3246000111103058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706999778747559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6550999879837036},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5898000001907349},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5841000080108643},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4887000024318695},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.45249998569488525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31049999594688416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28870001435279846},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2815000116825104},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.2644999921321869},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2026.3693589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3693589","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:eprints.lancs.ac.uk:238136","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.lancs.ac.uk/id/eprint/238136/1/SPL.pdf","source":{"id":"https://openalex.org/S4306401916","display_name":"Lancaster EPrints (Lancaster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67415387","host_organization_name":"Lancaster University","host_organization_lineage":["https://openalex.org/I67415387"],"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":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:eprints.lancs.ac.uk:238136","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.lancs.ac.uk/id/eprint/238136/1/SPL.pdf","source":{"id":"https://openalex.org/S4306401916","display_name":"Lancaster EPrints (Lancaster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67415387","host_organization_name":"Lancaster University","host_organization_lineage":["https://openalex.org/I67415387"],"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":"Journal Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7161138516.pdf","grobid_xml":"https://content.openalex.org/works/W7161138516.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Parameter-efficient":[0],"fine-tuning":[1,25],"(PEFT)":[2],"is":[3],"promising":[4],"for":[5,73,87],"RGB-D":[6,29,186],"semantic":[7,147],"segmentation,":[8],"as":[9],"lightweight":[10],"prompters":[11],"enable":[12],"frozen":[13,92,178],"pre-trained":[14],"RGB":[15,20,47],"backbones":[16,93],"to":[17,53,145,176],"leverage":[18],"massive":[19],"pretraining":[21],"knowledge":[22,174],"without":[23],"full":[24],"on":[26,182],"limited":[27],"paired":[28],"data.":[30],"However,":[31],"existing":[32],"PEFT":[33],"methods":[34],"have":[35],"two":[36,95],"critical":[37],"limitations:":[38],"static":[39],"modal":[40,105,162],"fusion":[41],"ignores":[42],"the":[43,65,82,177],"dynamic":[44,161],"reliability":[45,106],"of":[46,67,193],"and":[48,69,108,142,151,165,171,184,195,209],"depth":[49],"across":[50],"scenes,":[51],"leading":[52],"suboptimal":[54],"performance":[55],"in":[56,91],"complex":[57],"environments;":[58],"conventional":[59],"prompts":[60,132,138],"lack":[61],"structural":[62,129,166],"awareness,":[63],"causing":[64],"loss":[66],"edge":[68,141],"texture":[70,120,143],"details":[71],"essential":[72],"dense":[74],"prediction.":[75],"To":[76],"solve":[77],"these":[78],"problems,":[79],"we":[80],"propose":[81],"Accurate":[83],"Prompting":[84],"Network":[85],"(APNet)":[86],"precise":[88,156],"prompt":[89],"injection":[90],"with":[94,139,197],"core":[96],"modules.":[97],"A":[98,122],"Modality":[99],"Effectiveness":[100],"Guider":[101],"(MEG)":[102],"conducts":[103],"input-level":[104],"assessment":[107],"dynamically":[109],"generates":[110],"scene-adaptive":[111],"modality":[112],"weights":[113],"by":[114],"capturing":[115],"scene":[116],"characteristics":[117],"(e.g.,":[118],"illumination,":[119],"richness).":[121],"Structural":[123],"Awareness":[124],"Prompter":[125],"(SAP)":[126],"injects":[127],"directional":[128],"priors":[130],"into":[131],"via":[133],"multi-directional":[134],"gating":[135],"convolution,":[136],"endowing":[137],"explicit":[140],"information":[144],"match":[146],"segmentation":[148,207],"demands.":[149],"MEG":[150],"SAP":[152],"collaboratively":[153],"form":[154],"a":[155,203],"prompting":[157],"mechanism":[158],"that":[159,188],"realizes":[160],"contribution":[163],"allocation":[164],"detail":[167],"preservation,":[168],"facilitating":[169],"efficient":[170],"accurate":[172],"cross-modal":[173],"transfer":[175],"backbone.":[179],"Extensive":[180],"experiments":[181],"NYUDv2":[183],"SUN":[185],"show":[187],"APNet":[189],"achieves":[190],"state-of-the-art":[191],"mIoU":[192],"59.6%":[194],"52.6%":[196],"only":[198],"6.2M":[199],"trainable":[200],"parameters,":[201],"realizing":[202],"superior":[204],"trade-off":[205],"between":[206],"accuracy":[208],"parameter":[210],"efficiency.":[211]},"counts_by_year":[],"updated_date":"2026-06-06T06:22:57.294733","created_date":"2026-05-15T00:00:00"}