{"id":"https://openalex.org/W7160326536","doi":"https://doi.org/10.1109/wacv61042.2026.00630","title":"Training-Free Few-Shot Segmentation via Vision-Language Guided Prompting","display_name":"Training-Free Few-Shot Segmentation via Vision-Language Guided Prompting","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160326536","doi":"https://doi.org/10.1109/wacv61042.2026.00630"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-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":"https://openalex.org/A5113307449","display_name":"Euihyun Yoon","orcid":null},"institutions":[{"id":"https://openalex.org/I110273157","display_name":"Kookmin University","ror":"https://ror.org/0049erg63","country_code":"KR","type":"education","lineage":["https://openalex.org/I110273157"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Euihyun Yoon","raw_affiliation_strings":["Kookmin University,College of Computer Science,Seoul,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kookmin University,College of Computer Science,Seoul,Korea","institution_ids":["https://openalex.org/I110273157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101511624","display_name":"Taejin Park","orcid":"https://orcid.org/0000-0003-2040-5884"},"institutions":[{"id":"https://openalex.org/I110273157","display_name":"Kookmin University","ror":"https://ror.org/0049erg63","country_code":"KR","type":"education","lineage":["https://openalex.org/I110273157"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taejin Park","raw_affiliation_strings":["Kookmin University,College of Computer Science,Seoul,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kookmin University,College of Computer Science,Seoul,Korea","institution_ids":["https://openalex.org/I110273157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011313652","display_name":"Jaekoo Lee","orcid":"https://orcid.org/0000-0002-5947-5487"},"institutions":[{"id":"https://openalex.org/I110273157","display_name":"Kookmin University","ror":"https://ror.org/0049erg63","country_code":"KR","type":"education","lineage":["https://openalex.org/I110273157"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaekoo Lee","raw_affiliation_strings":["Kookmin University,College of Computer Science,Seoul,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kookmin University,College of Computer Science,Seoul,Korea","institution_ids":["https://openalex.org/I110273157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113307449"],"corresponding_institution_ids":["https://openalex.org/I110273157"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93543349,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6517","last_page":"6526"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2782000005245209,"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":0.2782000005245209,"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":0.1467999964952469,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.12430000305175781,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.43549999594688416},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3215999901294708},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3183000087738037},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3052999973297119},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.30320000648498535}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6116999983787537},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5710999965667725},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5543000102043152},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.43549999594688416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3183000087738037},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.30320000648498535},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.24050000309944153},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.23589999973773956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321253","display_name":"Kookmin University","ror":"https://ror.org/0049erg63"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2031489346","https://openalex.org/W2194775991","https://openalex.org/W2519623608","https://openalex.org/W2623808523","https://openalex.org/W2908320224","https://openalex.org/W2948672349","https://openalex.org/W2963078159","https://openalex.org/W2963150697","https://openalex.org/W2981787211","https://openalex.org/W2983943451","https://openalex.org/W3110908156","https://openalex.org/W4221153269","https://openalex.org/W4312688875","https://openalex.org/W4386066138","https://openalex.org/W4390874575","https://openalex.org/W4391454478","https://openalex.org/W4401725766","https://openalex.org/W4402557624","https://openalex.org/W4402753685","https://openalex.org/W4402781012","https://openalex.org/W4402915908","https://openalex.org/W4404612908","https://openalex.org/W4409257893","https://openalex.org/W4417273915","https://openalex.org/W7133193691","https://openalex.org/W7133236164"],"related_works":[],"abstract_inverted_index":{"Object":[0],"segmentation":[1],"relies":[2],"heavily":[3],"on":[4,146,166],"costly":[5],"pixel-level":[6],"annotations":[7],"and":[8,48,80,102,117,126,158],"struggles":[9],"to":[10,12,50,68,105,129],"generalize":[11],"unseen":[13],"domains.":[14],"The":[15],"recent":[16],"introduction":[17],"of":[18],"the":[19,77,110,123],"Segment":[20],"Anything":[21],"Model":[22],"(SAM),":[23],"a":[24,30,65,95],"foundation":[25],"model":[26],"for":[27,109],"segmentation,":[28],"offers":[29],"prompt-driven,":[31],"zero-shot":[32],"capability":[33],"that":[34,99],"has":[35],"been":[36],"applied":[37],"in":[38],"various":[39],"domains":[40],"(e.g.,":[41],"autonomous":[42],"driving,":[43],"satellite":[44],"imagery,":[45],"medical":[46],"imaging)":[47],"extended":[49],"Few-Shot":[51],"Segmentation":[52],"(FSS)":[53],"tasks.":[54],"However,":[55],"existing":[56],"SAM-based":[57],"FSS":[58,97,144],"methods":[59,145],"typically":[60],"generate":[61,106],"prompts":[62,108],"by":[63],"using":[64],"vision":[66,116],"encoder":[67],"measure":[69],"support\u2013query":[70,86,124],"image":[71],"similarity,":[72],"which":[73],"often":[74],"biases":[75],"towards":[76],"support":[78],"images":[79],"fails":[81],"when":[82],"there":[83],"are":[84],"significant":[85],"context":[87],"shifts.":[88],"To":[89],"address":[90],"this":[91],"limitation,":[92],"we":[93],"propose":[94],"training-free":[96],"approach":[98,121],"combines":[100],"visual":[101],"textual":[103],"cues":[104],"effective":[107],"target":[111],"class.":[112],"By":[113],"leveraging":[114],"both":[115],"language":[118],"information,":[119],"our":[120,139],"bridges":[122],"gap":[125],"guides":[127],"SAM":[128],"segment":[130],"novel":[131],"objects":[132],"more":[133],"reliably.":[134],"Without":[135],"any":[136],"additional":[137],"training,":[138],"method":[140],"outperforms":[141],"previous":[142],"state-of-the-art":[143],"established":[147],"benchmarks":[148],"(COCO-20<sup":[149],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[150,153],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">i</sup>,":[151],"Pascal-5<sup":[152],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">i</sup>),":[154],"demonstrating":[155],"its":[156],"effectiveness":[157],"robust":[159],"generalization.":[160],"Our":[161],"code":[162],"is":[163],"publicly":[164],"available":[165],"GitHub.":[167]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2026-05-06T00:00:00"}