{"id":"https://openalex.org/W7123356656","doi":"https://doi.org/10.1109/tcsvt.2026.3652185","title":"Vision-Language-Driven Prompt Learning for Weakly Supervised Semantic Segmentation","display_name":"Vision-Language-Driven Prompt Learning for Weakly Supervised Semantic Segmentation","publication_year":2026,"publication_date":"2026-01-12","ids":{"openalex":"https://openalex.org/W7123356656","doi":"https://doi.org/10.1109/tcsvt.2026.3652185"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3652185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3652185","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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":null,"display_name":"Junxia Li","orcid":"https://orcid.org/0000-0001-8488-1981"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junxia Li","raw_affiliation_strings":["CICAEET and Engineering Research Center of Digital Forensics, Ministry of Education, School of Computer, Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-8488-1981","affiliations":[{"raw_affiliation_string":"CICAEET and Engineering Research Center of Digital Forensics, Ministry of Education, School of Computer, Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu Zhang","orcid":"https://orcid.org/0009-0005-9303-2080"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["CICAEET and Engineering Research Center of Digital Forensics, Ministry of Education, School of Computer, Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0005-9303-2080","affiliations":[{"raw_affiliation_string":"CICAEET and Engineering Research Center of Digital Forensics, Ministry of Education, School of Computer, Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122849955","display_name":"Ying Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Cui","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8209-2679","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yubao Sun","orcid":"https://orcid.org/0000-0002-0462-3729"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yubao Sun","raw_affiliation_strings":["CICAEET and Engineering Research Center of Digital Forensics, Ministry of Education, School of Computer, Nanjing University of Information Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0462-3729","affiliations":[{"raw_affiliation_string":"CICAEET and Engineering Research Center of Digital Forensics, Ministry of Education, School of Computer, Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122228145","display_name":"Qingshan 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":"Qingshan Liu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-5512-6984","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05314956,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"5","first_page":"7223","last_page":"7235"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5080000162124634,"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":0.5080000162124634,"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":0.2955999970436096,"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":0.13179999589920044,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5507000088691711},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.48980000615119934},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.4844000041484833},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.47350001335144043},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46549999713897705},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.45010000467300415},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.43869999051094055},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4366999864578247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202999830245972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6628000140190125},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5507000088691711},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.4844000041484833},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.47350001335144043},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.45010000467300415},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.43869999051094055},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.37929999828338623},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3693000078201294},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.36000001430511475},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31869998574256897},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3109000027179718},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29409998655319214},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2939000129699707},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.263700008392334}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3652185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3652185","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.42180636525154114,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2037785589","display_name":null,"funder_award_id":"U21B2044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2694229652","display_name":null,"funder_award_id":"62272235","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3561553163","display_name":null,"funder_award_id":"62572438","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6671792466","display_name":null,"funder_award_id":"BG2024042","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G6862892202","display_name":null,"funder_award_id":"U24B20155","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8701145552","display_name":null,"funder_award_id":"BE2023016-3","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,97,114],"primary":[1],"challenges":[2,78],"in":[3,11,24,79],"image-level":[4],"weakly":[5],"supervised":[6],"semantic":[7,47,84,95,141],"segmentation":[8],"(WSSS)":[9],"lie":[10],"addressing":[12],"the":[13,21,144,181],"under-activation":[14],"issue":[15],"of":[16,101,159],"target":[17,133,169],"pixels":[18],"and":[19,89,109,128,150,172,185],"mitigating":[20,136],"co-occurrence":[22,137],"phenomenon":[23],"class":[25],"activation":[26,134],"maps.":[27],"In":[28],"recent":[29],"years,":[30],"Vision-Language":[31,68],"Models":[32],"(VLM)":[33],"have":[34],"demonstrated":[35],"exceptional":[36],"performance":[37,178],"across":[38],"various":[39],"vision":[40],"tasks,":[41],"\u200cprimarily":[42],"attributed":[43],"to":[44,58],"their":[45],"cross-modal":[46],"alignment":[48,125],"capabilities":[49],"achieved":[50],"through":[51,123],"contrastive":[52],"learning":[53],"mechanisms\u200c.":[54],"Leveraging":[55],"VLM\u2019s":[56],"capability":[57],"capture":[59],"fine-grained":[60],"visual-textual":[61],"correspondences,":[62],"this":[63],"paper":[64],"proposes":[65],"a":[66],"novel":[67],"Driven":[69],"Prompt":[70],"Learning":[71],"(VLD-PL)":[72],"framework":[73,99],"that":[74],"addresses":[75],"two":[76,102],"fundamental":[77],"WSSS":[80],"by":[81,139],"establishing":[82],"explicit":[83],"correspondences":[85],"between":[86,126],"textual":[87,129],"descriptors":[88],"visual":[90],"components,":[91],"ultimately":[92],"enabling":[93],"efficient":[94],"segmentation.":[96],"VLD-PL":[98],"consists":[100],"core":[103],"components":[104],"Auxiliary":[105],"Class":[106,111],"Matching":[107],"(ACM)":[108],"Background":[110],"Filtering":[112],"(BCF).":[113],"ACM":[115],"module":[116],"dynamically":[117],"identifies":[118],"semantically":[119],"relevant":[120],"auxiliary":[121],"classes":[122],"feature":[124,154],"image":[127],"embeddings,":[130],"effectively":[131],"enlarging":[132],"while":[135],"interference":[138],"expanding":[140],"coverage.":[142],"Simultaneously,":[143],"BCF":[145],"constructs":[146],"image-specific":[147],"background":[148,153,161,173],"prompts":[149],"adaptively":[151],"refines":[152],"representations,":[155],"achieving":[156,176],"precise":[157],"suppression":[158],"irrelevant":[160],"regions.":[162],"These":[163],"dual":[164],"mechanisms":[165],"synergistically":[166],"address":[167],"both":[168,180],"localization":[170],"accuracy":[171],"noise":[174],"suppression,":[175],"state-of-the-art":[177],"on":[179],"PASCAL":[182],"VOC":[183],"2012":[184],"MS":[186],"COCO":[187],"2014":[188],"benchmarks.":[189]},"counts_by_year":[],"updated_date":"2026-05-08T13:12:06.581006","created_date":"2026-01-14T00:00:00"}