{"id":"https://openalex.org/W4402218353","doi":"https://doi.org/10.1109/tpami.2024.3454647","title":"TagCLIP: Improving Discrimination Ability of Zero-Shot Semantic Segmentation","display_name":"TagCLIP: Improving Discrimination Ability of Zero-Shot Semantic Segmentation","publication_year":2024,"publication_date":"2024-09-04","ids":{"openalex":"https://openalex.org/W4402218353","doi":"https://doi.org/10.1109/tpami.2024.3454647","pmid":"https://pubmed.ncbi.nlm.nih.gov/39231046"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3454647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3454647","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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":"Jingyao Li","orcid":"https://orcid.org/0000-0002-5121-1153"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jingyao Li","raw_affiliation_strings":["Department of Computer Science and Engineering, Chinese University of Hong Kong (CUHK), Hong Kong","Department of Computer Science and Engineering, the Chinese University of Hong Kong (CUHK), Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-5121-1153","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chinese University of Hong Kong (CUHK), Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, the Chinese University of Hong Kong (CUHK), Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013384457","display_name":"Pengguang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengguang Chen","raw_affiliation_strings":["SmartMore, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0004-1746-5127","affiliations":[{"raw_affiliation_string":"SmartMore, Hong Kong","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034240662","display_name":"Shengju Qian","orcid":"https://orcid.org/0000-0002-3386-0336"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shengju Qian","raw_affiliation_strings":["Department of Computer Science and Engineering, Chinese University of Hong Kong (CUHK), Hong Kong","Department of Computer Science and Engineering, the Chinese University of Hong Kong (CUHK), Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-3386-0336","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chinese University of Hong Kong (CUHK), Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, the Chinese University of Hong Kong (CUHK), Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064499660","display_name":"Shu Liu","orcid":"https://orcid.org/0000-0002-2903-9270"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shu Liu","raw_affiliation_strings":["SmartMore, Hong Kong","Department of Computer Science and Engineering, the Chinese University of Hong Kong (CUHK), Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-2903-9270","affiliations":[{"raw_affiliation_string":"SmartMore, Hong Kong","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science and Engineering, the Chinese University of Hong Kong (CUHK), Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052856441","display_name":"Jiaya Jia","orcid":"https://orcid.org/0000-0002-1246-553X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaya Jia","raw_affiliation_strings":["SmartMore, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-1246-553X","affiliations":[{"raw_affiliation_string":"SmartMore, Hong Kong","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2228,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89445929,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"46","issue":"12","first_page":"11287","last_page":"11297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9944000244140625,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9944000244140625,"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/T10028","display_name":"Topic Modeling","score":0.989799976348877,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9448000192642212,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.6888988018035889},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6610661149024963},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6132804155349731},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5269896388053894},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5066631436347961},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4928452968597412},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.47843649983406067},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.443353533744812},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3239978551864624},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08511504530906677}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6888988018035889},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6610661149024963},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6132804155349731},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5269896388053894},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5066631436347961},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4928452968597412},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.47843649983406067},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.443353533744812},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3239978551864624},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08511504530906677},{"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":3,"locations":[{"id":"doi:10.1109/tpami.2024.3454647","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3454647","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:39231046","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39231046","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-157591","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-157591","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2896457183","https://openalex.org/W2924485953","https://openalex.org/W2962914239","https://openalex.org/W2963351448","https://openalex.org/W2963727650","https://openalex.org/W3039695075","https://openalex.org/W3049293589","https://openalex.org/W3170841864","https://openalex.org/W3176777339","https://openalex.org/W3201755784","https://openalex.org/W3202473909","https://openalex.org/W3203247393","https://openalex.org/W3216551675","https://openalex.org/W4214893857","https://openalex.org/W4312747482","https://openalex.org/W4312815172","https://openalex.org/W4312912313","https://openalex.org/W4312935996","https://openalex.org/W4386065874","https://openalex.org/W4386066643","https://openalex.org/W4386075561","https://openalex.org/W4386075882","https://openalex.org/W4390120054","https://openalex.org/W4390873343","https://openalex.org/W4399527506","https://openalex.org/W6640295612","https://openalex.org/W6682691769","https://openalex.org/W6731031554","https://openalex.org/W6739696289","https://openalex.org/W6763578275","https://openalex.org/W6767211374","https://openalex.org/W6767279747","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6797399245","https://openalex.org/W6798837711","https://openalex.org/W6802517928","https://openalex.org/W6805244352","https://openalex.org/W6810596876","https://openalex.org/W6811109880","https://openalex.org/W6846087911","https://openalex.org/W6846529796","https://openalex.org/W6860419850"],"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":{"Contrastive":[0],"Language-Image":[1],"Pre-training":[2],"(CLIP)":[3],"has":[4],"recently":[5],"shown":[6],"great":[7],"promise":[8],"in":[9,88,107],"pixel-level":[10],"zero-shot":[11],"learning":[12],"tasks.":[13],"However,":[14],"existing":[15],"approaches":[16],"utilizing":[17],"CLIP's":[18],"text":[19],"and":[20,40,74,123,143],"patch":[21],"embeddings":[22],"to":[23,35,56],"generate":[24],"semantic":[25,70],"masks":[26],"often":[27],"misidentify":[28],"input":[29],"pixels":[30],"from":[31,104],"unseen":[32,139],"classes,":[33],"leading":[34],"confusion":[36],"between":[37],"novel":[38,50,102],"classes":[39,103,140],"semantically":[41],"similar":[42],"ones.":[43],"In":[44],"this":[45,58],"work,":[46],"we":[47,94,113],"propose":[48],"a":[49,96],"approach,":[51,112],"TagCLIP":[52,131],"(Trusty-aware":[53],"guided":[54],"CLIP),":[55],"address":[57],"issue.":[59],"We":[60],"disentangle":[61],"the":[62,83,133],"ill-posed":[63],"optimization":[64],"problem":[65],"into":[66],"two":[67,117],"parallel":[68],"processes:":[69],"matching":[71],"performed":[72],"individually":[73],"reliability":[75],"judgment":[76],"for":[77],"improving":[78],"discrimination":[79],"ability.":[80],"Building":[81],"on":[82,116],"idea":[84],"of":[85,138],"special":[86],"tokens":[87],"language":[89],"modeling":[90],"representing":[91],"sentence-level":[92],"embeddings,":[93],"introduce":[95],"trusty":[97],"token":[98],"that":[99,130],"enables":[100],"distinguishing":[101],"known":[105],"ones":[106],"prediction.":[108],"To":[109],"evaluate":[110],"our":[111],"conduct":[114],"experiments":[115],"benchmark":[118],"datasets,":[119],"PASCAL":[120],"VOC":[121],"2012":[122],"COCO-Stuff":[124],"164":[125],"K.":[126],"Our":[127],"results":[128],"show":[129],"improves":[132],"Intersection":[134],"over":[135],"Union":[136],"(IoU)":[137],"by":[141],"7.4%":[142],"1.7%,":[144],"respectively,":[145],"with":[146],"negligible":[147],"overheads.":[148],"The":[149],"code":[150],"is":[151],"available":[152],"at":[153],"here.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
