{"id":"https://openalex.org/W4408353767","doi":"https://doi.org/10.1109/icassp49660.2025.10888602","title":"Text-Guided Few-Shot Semantic Segmentation with Training-Free Multimodal Feature Matching","display_name":"Text-Guided Few-Shot Semantic Segmentation with Training-Free Multimodal Feature Matching","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353767","doi":"https://doi.org/10.1109/icassp49660.2025.10888602"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5116594451","display_name":"Guillaume Buthmann","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Guillaume Buthmann","raw_affiliation_strings":["IBM Research,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Tokyo,Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068376487","display_name":"Tomoya Sakai","orcid":"https://orcid.org/0000-0003-3510-0979"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoya Sakai","raw_affiliation_strings":["IBM Research,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Tokyo,Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111270284","display_name":"Haoxiang Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haoxiang Qiu","raw_affiliation_strings":["IBM Research,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Tokyo,Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086948083","display_name":"Takayuki Katsuki","orcid":"https://orcid.org/0000-0002-3670-1138"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takayuki Katsuki","raw_affiliation_strings":["IBM Research,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Tokyo,Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047548171","display_name":"Daiki Kimura","orcid":"https://orcid.org/0000-0001-5180-1949"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daiki Kimura","raw_affiliation_strings":["IBM Research,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research,Tokyo,Japan","institution_ids":["https://openalex.org/I4210145865"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.01691092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9948999881744385,"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":0.983299970626831,"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/computer-science","display_name":"Computer science","score":0.7880801558494568},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6536523699760437},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6320217847824097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6239991188049316},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6001459956169128},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5719454288482666},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.5015161037445068},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.49634677171707153},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4360884428024292},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40461266040802},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.05822446942329407},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.057588398456573486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7880801558494568},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6536523699760437},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6320217847824097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6239991188049316},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6001459956169128},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5719454288482666},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.5015161037445068},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.49634677171707153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4360884428024292},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40461266040802},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.05822446942329407},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.057588398456573486},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/icassp49660.2025.10888602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/W1507506748","https://openalex.org/W1861492603","https://openalex.org/W2037227137","https://openalex.org/W2905544595","https://openalex.org/W2963078159","https://openalex.org/W2963383024","https://openalex.org/W2981787211","https://openalex.org/W3120644159","https://openalex.org/W4214573368","https://openalex.org/W4285604202","https://openalex.org/W4386833253","https://openalex.org/W4390874575","https://openalex.org/W4392903823","https://openalex.org/W4401023666","https://openalex.org/W4402671792","https://openalex.org/W4402715795","https://openalex.org/W4402716047","https://openalex.org/W4403990736","https://openalex.org/W4404782964","https://openalex.org/W6763578275","https://openalex.org/W6784333009","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6811433417","https://openalex.org/W6838934113","https://openalex.org/W6839650396","https://openalex.org/W6840380363","https://openalex.org/W6851800889","https://openalex.org/W6852612167","https://openalex.org/W6853557853"],"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/W2325697621"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"few-shot":[3],"semantic":[4,49],"segmentation":[5,37,50,71],"(FSS)":[6],"guided":[7],"by":[8,40,42,72],"text,":[9],"where":[10],"we":[11],"classify":[12],"unseen":[13],"novel":[14],"classes":[15],"using":[16,65],"image":[17,57,78,86],"and":[18,33,58,87,100],"text":[19,88],"references":[20],"as":[21],"in-context":[22],"examples,":[23],"without":[24],"the":[25,31,36,44,81,85,94],"need":[26],"for":[27,56],"training.":[28],"We":[29,60],"enhance":[30],"quality":[32],"stability":[34],"of":[35,46],"masks":[38],"generated":[39],"FSS":[41,99],"combining":[43],"capability":[45],"open-vocabulary":[47],"zero-shot":[48],"(ZSS)":[51],"based":[52],"on":[53],"foundation":[54],"models":[55],"text.":[59],"propose":[61],"a":[62,76],"training-free":[63],"approach":[64],"multimodal":[66],"feature":[67],"matching":[68],"that":[69,79,93],"performs":[70],"identifying":[73],"regions":[74],"in":[75],"target":[77],"match":[80],"features":[82],"from":[83],"both":[84],"references.":[89],"Experimental":[90],"results":[91],"demonstrate":[92],"proposed":[95],"method":[96],"outperforms":[97],"state-of-the-art":[98],"ZSS":[101],"methods.":[102]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}