{"id":"https://openalex.org/W4404627538","doi":"https://doi.org/10.1109/tcsvt.2024.3504816","title":"Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation","display_name":"Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation","publication_year":2024,"publication_date":"2024-11-22","ids":{"openalex":"https://openalex.org/W4404627538","doi":"https://doi.org/10.1109/tcsvt.2024.3504816"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3504816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3504816","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":"Zicheng Zhang","orcid":"https://orcid.org/0009-0001-3986-5576"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zicheng Zhang","raw_affiliation_strings":["School of Software Engineering, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0009-0001-3986-5576","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101867597","display_name":"Wei Ke","orcid":"https://orcid.org/0000-0002-2899-0371"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Ke","raw_affiliation_strings":["School of Software Engineering, Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-2899-0371","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434324","display_name":"Yi Zhu","orcid":"https://orcid.org/0000-0003-3000-3918"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["CN","SE"],"is_corresponding":false,"raw_author_name":"Yi Zhu","raw_affiliation_strings":["Noah’s Ark Laboratory, Huawei Technologies, Shenzhen, China","Noah’s Ark Lab, Huawei Technologies, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Noah’s Ark Laboratory, Huawei Technologies, Shenzhen, China","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Noah’s Ark Lab, Huawei Technologies, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047878798","display_name":"Xiaodan Liang","orcid":"https://orcid.org/0000-0003-3213-3062"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Liang","raw_affiliation_strings":["School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China","School of Intelligent Systems Engineering, Sun Yat-sen University, GuangZhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3213-3062","affiliations":[{"raw_affiliation_string":"School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Intelligent Systems Engineering, Sun Yat-sen University, GuangZhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039205892","display_name":"Jianzhuang Liu","orcid":"https://orcid.org/0000-0002-7960-9382"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["CN","SE"],"is_corresponding":false,"raw_author_name":"Jianzhuang Liu","raw_affiliation_strings":["Noah’s Ark Laboratory, Huawei Technologies, Shenzhen, China","Noah’s Ark Lab, Huawei Technologies, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-7960-9382","affiliations":[{"raw_affiliation_string":"Noah’s Ark Laboratory, Huawei Technologies, Shenzhen, China","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Noah’s Ark Lab, Huawei Technologies, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015317495","display_name":"Qixiang Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qixiang Ye","raw_affiliation_strings":["School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1215-6259","affiliations":[{"raw_affiliation_string":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100602481","display_name":"Tong Zhang","orcid":"https://orcid.org/0000-0002-8838-4963"},"institutions":[{"id":"https://openalex.org/I4210133377","display_name":"Centre d'Imagerie BioMedicale","ror":"https://ror.org/03fw2bn12","country_code":"CH","type":"facility","lineage":["https://openalex.org/I4210133377"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Tong Zhang","raw_affiliation_strings":["Image and Visual Representation Laboratory, École Polytechnique fédérale de Lausanne, Lausanne, Switzerland","Image and Visual Representation Lab, École polytechnique fédérale de Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Image and Visual Representation Laboratory, École Polytechnique fédérale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I4210133377"]},{"raw_affiliation_string":"Image and Visual Representation Lab, École polytechnique fédérale de Lausanne, Switzerland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8393,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.86969242,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"35","issue":"4","first_page":"3185","last_page":"3195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9988999962806702,"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":0.9988999962806702,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9842000007629395,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9833999872207642,"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/computer-science","display_name":"Computer science","score":0.6997900009155273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5948978662490845},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5701572299003601},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.518731415271759},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4911665618419647},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.47028210759162903},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4498330056667328},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38108304142951965},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13899588584899902}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6997900009155273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5948978662490845},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5701572299003601},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.518731415271759},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4911665618419647},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.47028210759162903},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4498330056667328},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38108304142951965},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13899588584899902},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3504816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3504816","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":[],"awards":[{"id":"https://openalex.org/G5013919688","display_name":null,"funder_award_id":"xtr072024017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6630003392","display_name":null,"funder_award_id":"62476293","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6735075065","display_name":null,"funder_award_id":"62225208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G918142972","display_name":null,"funder_award_id":"62376209","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2108598243","https://openalex.org/W2561196672","https://openalex.org/W2734349601","https://openalex.org/W2924485953","https://openalex.org/W2943070176","https://openalex.org/W2963351448","https://openalex.org/W3049293589","https://openalex.org/W3096609285","https://openalex.org/W3170841864","https://openalex.org/W3174770825","https://openalex.org/W3176777339","https://openalex.org/W3198377975","https://openalex.org/W3201755784","https://openalex.org/W3202717607","https://openalex.org/W4205991051","https://openalex.org/W4214893857","https://openalex.org/W4226058394","https://openalex.org/W4229453513","https://openalex.org/W4311967393","https://openalex.org/W4312310776","https://openalex.org/W4312458986","https://openalex.org/W4312651322","https://openalex.org/W4312815172","https://openalex.org/W4312935996","https://openalex.org/W4312960937","https://openalex.org/W4312980231","https://openalex.org/W4321021726","https://openalex.org/W4383112592","https://openalex.org/W4384787981","https://openalex.org/W4386065512","https://openalex.org/W4386065874","https://openalex.org/W4386066500","https://openalex.org/W4386071547","https://openalex.org/W4386075714","https://openalex.org/W4386075882","https://openalex.org/W4386076084","https://openalex.org/W4386076400","https://openalex.org/W4386794361","https://openalex.org/W4388266798","https://openalex.org/W4390871743","https://openalex.org/W4390872306","https://openalex.org/W4390872930","https://openalex.org/W4390873537","https://openalex.org/W4390873714","https://openalex.org/W4390874575","https://openalex.org/W4390874585","https://openalex.org/W4390889734","https://openalex.org/W4391468487","https://openalex.org/W4393148303","https://openalex.org/W4402671847","https://openalex.org/W4402716397","https://openalex.org/W6677258307","https://openalex.org/W6757817989","https://openalex.org/W6763578275","https://openalex.org/W6778883912","https://openalex.org/W6780226713","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6798837711","https://openalex.org/W6802625470","https://openalex.org/W6811433417","https://openalex.org/W6842162983","https://openalex.org/W6846529796","https://openalex.org/W6846835116","https://openalex.org/W6849202153","https://openalex.org/W6851592950","https://openalex.org/W6851618819","https://openalex.org/W6855350031","https://openalex.org/W6856853793","https://openalex.org/W6857606325","https://openalex.org/W6857661428","https://openalex.org/W6862308860","https://openalex.org/W6862797136","https://openalex.org/W6868539980","https://openalex.org/W6870464448","https://openalex.org/W6876177771"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W1522196789"],"abstract_inverted_index":{"The":[0],"pre-trained":[1],"vision-language":[2,118],"model,":[3],"exemplified":[4],"by":[5,11],"CLIP,":[6],"advances":[7],"zero-shot":[8],"semantic":[9,24,109],"segmentation":[10,45,129],"aligning":[12],"visual":[13,65,82,93,105],"features":[14,83],"with":[15,116,162],"class":[16,70,85],"embeddings":[17,71],"through":[18],"a":[19,53,90,117],"transformer":[20,101],"decoder":[21,102],"to":[22,75,88,103],"generate":[23],"masks.":[25,46],"Despite":[26],"its":[27],"effectiveness,":[28],"prevailing":[29],"methods":[30],"within":[31,111],"this":[32],"paradigm":[33],"encounter":[34],"challenges,":[35],"including":[36],"overfitting":[37],"on":[38,147,154],"seen":[39],"classes":[40,160],"and":[41,64,78,152],"small":[42],"fragmentation":[43],"in":[44],"To":[47],"mitigate":[48],"these":[49],"issues,":[50],"we":[51,68,95],"propose":[52],"Language-Driven":[54],"Visual":[55],"Consensus":[56],"(LDVC)":[57],"approach,":[58,141],"fostering":[59],"improved":[60],"alignment":[61],"of":[62,128,139,145],"linguistic":[63],"information.":[66],"Specifically,":[67],"leverage":[69],"as":[72],"anchors":[73],"due":[74],"their":[76],"discrete":[77],"abstract":[79],"nature,":[80],"steering":[81],"toward":[84],"embeddings.":[86],"Moreover,":[87],"achieve":[89],"more":[91],"compact":[92],"space,":[94],"introduce":[96],"route":[97],"attention":[98],"into":[99],"the":[100,112,125,137,148,155,163],"find":[104],"consensus,":[106],"thereby":[107],"enhancing":[108],"consistency":[110],"same":[113],"object.":[114],"Equipped":[115],"prompting":[119],"strategy,":[120],"our":[121,140],"approach":[122],"significantly":[123],"boosts":[124],"generalization":[126],"capacity":[127],"models":[130],"for":[131,158],"unseen":[132,159],"classes.":[133],"Experimental":[134],"results":[135],"underscore":[136],"effectiveness":[138],"showcasing":[142],"mIoU":[143],"gains":[144],"4.5%":[146],"PASCAL":[149],"VOC":[150],"2012":[151],"3.6%":[153],"COCO-Stuff":[156],"164K":[157],"compared":[161],"state-of-the-art":[164],"methods.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}