{"id":"https://openalex.org/W7161592906","doi":"https://doi.org/10.3390/computers15050318","title":"CLIP-HBD: Hierarchical Boundary-Constrained Decoding for Open-Vocabulary Semantic Segmentation","display_name":"CLIP-HBD: Hierarchical Boundary-Constrained Decoding for Open-Vocabulary Semantic Segmentation","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W7161592906","doi":"https://doi.org/10.3390/computers15050318"},"language":"en","primary_location":{"id":"doi:10.3390/computers15050318","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15050318","pdf_url":null,"source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/computers15050318","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108047889","display_name":"Yi-Xiang Wang","orcid":"https://orcid.org/0000-0001-5697-0717"},"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":"Jing Wang","raw_affiliation_strings":["School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136442116","display_name":"Quan Zhou","orcid":"https://orcid.org/0000-0002-7894-7929"},"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":"Quan Zhou","raw_affiliation_strings":["School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China"],"raw_orcid":"https://orcid.org/0000-0002-7894-7929","affiliations":[{"raw_affiliation_string":"School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134162149","display_name":"Anyi Yang","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":"Anyi Yang","raw_affiliation_strings":["School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136390349","display_name":"Junyu Lin","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":"Junyu Lin","raw_affiliation_strings":["School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.61325733,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"5","first_page":"318","last_page":"318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7398999929428101,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7398999929428101,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.14640000462532043,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.014299999922513962,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6126999855041504},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6062999963760376},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4620000123977661},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.388700008392334},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3499999940395355},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.3490999937057495},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.33709999918937683},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.33160001039505005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7407000064849854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6273999810218811},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6126999855041504},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6062999963760376},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4943999946117401},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4620000123977661},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3499999940395355},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.3490999937057495},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.32249999046325684},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.2849000096321106},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/computers15050318","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15050318","pdf_url":null,"source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6c9144d4ee3a420eaf0a0eb79601bc39","is_oa":true,"landing_page_url":"https://doaj.org/article/6c9144d4ee3a420eaf0a0eb79601bc39","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computers, Vol 15, Iss 5, p 318 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/computers15050318","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15050318","pdf_url":null,"source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2031489346","https://openalex.org/W2125215748","https://openalex.org/W2250384498","https://openalex.org/W2463955103","https://openalex.org/W2507296351","https://openalex.org/W2535388113","https://openalex.org/W2561196672","https://openalex.org/W2886641317","https://openalex.org/W2924485953","https://openalex.org/W2964309882","https://openalex.org/W2999219213","https://openalex.org/W3035358681","https://openalex.org/W3095670406","https://openalex.org/W4214893857","https://openalex.org/W4312443924","https://openalex.org/W4312458986","https://openalex.org/W4312680544","https://openalex.org/W4312689172","https://openalex.org/W4312912313","https://openalex.org/W4312935996","https://openalex.org/W4312960937","https://openalex.org/W4312980231","https://openalex.org/W4386075561","https://openalex.org/W4386075819","https://openalex.org/W4386075882","https://openalex.org/W4386076046","https://openalex.org/W4386076397","https://openalex.org/W4388283733","https://openalex.org/W4390872930","https://openalex.org/W4390874575","https://openalex.org/W4402215342","https://openalex.org/W4402673268","https://openalex.org/W4402703011","https://openalex.org/W4402715795","https://openalex.org/W4402716193","https://openalex.org/W4402716400","https://openalex.org/W4402773761","https://openalex.org/W4407590893","https://openalex.org/W4414197594","https://openalex.org/W7133196460","https://openalex.org/W7160052237"],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"semantic":[1,83,167],"segmentation":[2,9,184],"(OVSS)":[3],"aims":[4],"to":[5,85,95,110,147],"achieve":[6],"pixel-level":[7],"object":[8,172],"guided":[10],"by":[11],"arbitrary":[12],"natural":[13],"language":[14],"descriptions.":[15],"Although":[16],"pre-trained":[17],"vision\u2013language":[18],"models":[19],"(VLMs)":[20],"have":[21],"significantly":[22],"advanced":[23],"the":[24,31,44,122,137,149,162],"development":[25],"of":[26,46,124],"OVSS,":[27,76],"their":[28],"reliance":[29],"on":[30,40,133],"Vision":[32],"Transformer":[33],"(ViT)":[34],"architecture":[35],"imposes":[36],"a":[37,70,91,102,106,116],"fundamental":[38],"constraint":[39],"dense":[41],"prediction.":[42],"Specifically,":[43,99],"absence":[45],"hierarchical":[47,71,107,160],"downsampling":[48],"in":[49,53,182],"ViT-based":[50],"VLM":[51,82,113],"results":[52],"single-scale":[54],"representations":[55],"that":[56,177],"trade":[57],"spatial":[58],"localization":[59],"for":[60,75],"global":[61],"semantics.":[62],"To":[63,120],"address":[64,121],"these":[65],"issues,":[66],"this":[67],"paper":[68],"proposes":[69],"boundary-constrained":[72,92],"decoding":[73,93,163],"network":[74],"called":[77],"CLIP-HBD.":[78],"Our":[79],"approach":[80],"leverages":[81,101],"priors":[84],"reconstruct":[86],"multi-scale":[87,118,134],"features":[88],"and":[89,169,186],"introduces":[90],"strategy":[94],"refine":[96],"edge":[97],"details.":[98],"CLIP-HBD":[100,178],"ConvNeXt-based":[103],"backbone":[104],"alongside":[105],"adaptation":[108],"mechanism":[109],"fuse":[111],"multi-layer":[112],"features,":[114,161],"generating":[115],"comprehensive":[117],"representation.":[119],"issue":[123],"boundary":[125,130,139,153,187],"inaccuracy,":[126],"we":[127],"perform":[128],"explicit":[129],"prediction":[131],"based":[132],"representations,":[135],"where":[136],"resulting":[138],"maps":[140],"are":[141],"subsequently":[142],"transformed":[143],"into":[144],"structural":[145,157],"constraints":[146,158],"steer":[148],"decoder\u2019s":[150],"focus":[151],"toward":[152],"regions.":[154],"By":[155],"integrating":[156],"with":[159],"process":[164],"effectively":[165],"maintains":[166],"consistency":[168],"restores":[170],"precise":[171],"boundaries.":[173],"Extensive":[174],"experiments":[175],"demonstrate":[176],"achieves":[179],"superior":[180],"performance":[181],"both":[183],"precision":[185],"quality":[188],"across":[189],"multiple":[190],"benchmarks.":[191]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-05-19T00:00:00"}