{"id":"https://openalex.org/W7155068208","doi":"https://doi.org/10.1109/icara69401.2026.11480420","title":"Zero-Shot Semantic Segmentation Research of Vision Language Models","display_name":"Zero-Shot Semantic Segmentation Research of Vision Language Models","publication_year":2026,"publication_date":"2026-02-05","ids":{"openalex":"https://openalex.org/W7155068208","doi":"https://doi.org/10.1109/icara69401.2026.11480420"},"language":null,"primary_location":{"id":"doi:10.1109/icara69401.2026.11480420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icara69401.2026.11480420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 12th International Conference on Automation, Robotics and Applications (ICARA)","raw_type":"proceedings-article"},"type":"conference-paper","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":"https://openalex.org/A5109786890","display_name":"Xinyan Tan","orcid":"https://orcid.org/0009-0004-2550-1386"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyan Tan","raw_affiliation_strings":["School of Mechatronic Engineering, Beijing Institute of Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechatronic Engineering, Beijing Institute of Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049850299","display_name":"F Li","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangxing Li","raw_affiliation_strings":["School of Mechatronic Engineering, Beijing Institute of Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechatronic Engineering, Beijing Institute of Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125349575","display_name":"Haotong He","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haotong He","raw_affiliation_strings":["School of Mechatronic Engineering, Beijing Institute of Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechatronic Engineering, Beijing Institute of Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000939047","display_name":"Zhengqing Zuo","orcid":"https://orcid.org/0009-0005-0803-7152"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqing Zuo","raw_affiliation_strings":["School of Mechatronic Engineering, Beijing Institute of Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechatronic Engineering, Beijing Institute of Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134121094","display_name":"Xiaohai He","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohai He","raw_affiliation_strings":["School of Mechatronic Engineering, Beijing Institute of Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechatronic Engineering, Beijing Institute of Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100441502","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0001-7800-3189"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weimin Zhang","raw_affiliation_strings":["School of Mechatronic Engineering, Beijing Institute of Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechatronic Engineering, Beijing Institute of Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44343518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"457","last_page":"462"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9064000248908997,"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":0.9064000248908997,"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":0.014399999752640724,"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":0.007199999876320362,"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":0.5271000266075134},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.39649999141693115},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.34060001373291016},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.311599999666214},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2912999987602234},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.2854999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6858000159263611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6287000179290771},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5715000033378601},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5271000266075134},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.28929999470710754},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icara69401.2026.11480420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icara69401.2026.11480420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 12th International Conference on Automation, Robotics and Applications (ICARA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2001992768","https://openalex.org/W2031489346","https://openalex.org/W2096579040","https://openalex.org/W2100588357","https://openalex.org/W2111052691","https://openalex.org/W2125215748","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2531409750","https://openalex.org/W2560023338","https://openalex.org/W2561196672","https://openalex.org/W2737258237","https://openalex.org/W2895340641","https://openalex.org/W2963166928","https://openalex.org/W3096609285","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3170841864","https://openalex.org/W3204255739","https://openalex.org/W4214893857","https://openalex.org/W4312815172","https://openalex.org/W4386075882","https://openalex.org/W4390874575","https://openalex.org/W4401636497","https://openalex.org/W4402916449","https://openalex.org/W4404627538","https://openalex.org/W4405197533","https://openalex.org/W7133193597"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"systematically":[4],"research":[5],"recent":[6],"based":[7],"on":[8,17],"vision":[9],"language":[10,26],"models":[11,23,69],"(VLMs)":[12],"semantic":[13,114],"segmentation":[14,59],"methods,":[15],"focusing":[16],"two":[18,42],"major":[19],"paradigms:":[20],"VLM-based":[21,67],"crossmodal":[22,68],"and":[24,35,50,56,61,64,79,87,102],"large":[25],"model":[27],"(LLM)-enhanced":[28],"interactive":[29,52],"models.":[30],"We":[31,54],"analyze":[32,57],"the":[33,97],"characteristics":[34],"strategies":[36],"of":[37,99,107],"representative":[38],"methods":[39,83],"in":[40,72,90],"these":[41],"paradigms,":[43],"covering":[44],"zero-shot":[45],"learning,":[46],"visual-language":[47],"prompting":[48],"strategies,":[49],"multi-round":[51],"reasoning.":[53,115],"summarize":[55],"their":[58,77],"accuracy":[60],"computational":[62],"performance,":[63],"show":[65,84],"that":[66],"remain":[70],"competitive":[71],"structured":[73],"datasets":[74],"due":[75],"to":[76],"efficiency":[78],"simplicity,":[80],"while":[81],"LLM-enhanced":[82],"greater":[85],"flexibility":[86],"reasoning":[88],"capabilities":[89],"complex":[91],"instruction-driven":[92],"tasks.":[93],"Our":[94],"study":[95],"highlights":[96],"advantages":[98],"both":[100],"paradigms":[101],"proposes":[103],"a":[104],"future":[105],"direction":[106],"combining":[108],"lightweight":[109],"visual":[110],"foundations":[111],"with":[112],"high-level":[113]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-04-22T00:00:00"}