{"id":"https://openalex.org/W4409369924","doi":"https://doi.org/10.1609/aaai.v39i3.32347","title":"Boosting Segment Anything Model Towards Open-Vocabulary Learning","display_name":"Boosting Segment Anything Model Towards Open-Vocabulary Learning","publication_year":2025,"publication_date":"2025-04-11","ids":{"openalex":"https://openalex.org/W4409369924","doi":"https://doi.org/10.1609/aaai.v39i3.32347"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v39i3.32347","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i3.32347","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32347/34502","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32347/34502","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086353603","display_name":"Xumeng Han","orcid":"https://orcid.org/0000-0002-1636-463X"},"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":true,"raw_author_name":"Xumeng Han","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050660610","display_name":"Longhui Wei","orcid":"https://orcid.org/0000-0001-6916-3009"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Longhui Wei","raw_affiliation_strings":["Huawei Inc"],"affiliations":[{"raw_affiliation_string":"Huawei Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075555724","display_name":"Xuehui Yu","orcid":"https://orcid.org/0000-0001-9058-0480"},"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":"Xuehui Yu","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059487131","display_name":"Zhiyang Dou","orcid":"https://orcid.org/0000-0003-0186-8269"},"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":"Zhiyang Dou","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101370062","display_name":"Xin He","orcid":"https://orcid.org/0000-0002-2275-5215"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin He","raw_affiliation_strings":["Huawei Inc"],"affiliations":[{"raw_affiliation_string":"Huawei Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017479013","display_name":"Kuiran Wang","orcid":"https://orcid.org/0000-0003-4891-4752"},"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":"Kuiran Wang","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103211417","display_name":"Yingfei Sun","orcid":"https://orcid.org/0000-0003-0615-2569"},"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":"Yingfei Sun","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000034551","display_name":"Zhenjun Han","orcid":"https://orcid.org/0000-0002-9970-5152"},"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":"Zhenjun Han","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111172356","display_name":"Qi Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Huawei Inc"],"affiliations":[{"raw_affiliation_string":"Huawei Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5086353603"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":2.0638,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88149883,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"39","issue":"3","first_page":"3356","last_page":"3365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9440000057220459,"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/T12031","display_name":"Speech and dialogue systems","score":0.9440000057220459,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9416000247001648,"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/boosting","display_name":"Boosting (machine learning)","score":0.8373934626579285},{"id":"https://openalex.org/keywords/vocabulary-learning","display_name":"Vocabulary learning","score":0.5211860537528992},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5049768090248108},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.41631245613098145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4109499454498291},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33090901374816895},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1776227056980133},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.128024160861969}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8373934626579285},{"id":"https://openalex.org/C2984601542","wikidata":"https://www.wikidata.org/wiki/Q48842322","display_name":"Vocabulary learning","level":3,"score":0.5211860537528992},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5049768090248108},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.41631245613098145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4109499454498291},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33090901374816895},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1776227056980133},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.128024160861969}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v39i3.32347","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i3.32347","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32347/34502","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v39i3.32347","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i3.32347","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32347/34502","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409369924.pdf","grobid_xml":"https://content.openalex.org/works/W4409369924.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3019875293","https://openalex.org/W2351746492","https://openalex.org/W3204019825","https://openalex.org/W2367621846","https://openalex.org/W2394096350","https://openalex.org/W2091742426","https://openalex.org/W2365662948","https://openalex.org/W1988910916","https://openalex.org/W2380430606","https://openalex.org/W4360597343"],"abstract_inverted_index":{"The":[0],"recent":[1],"Segment":[2],"Anything":[3],"Model":[4],"(SAM)":[5],"has":[6],"emerged":[7],"as":[8,173],"a":[9,94,174],"new":[10],"paradigmatic":[11],"vision":[12,193],"foundation":[13,194],"model,":[14],"showcasing":[15],"potent":[16],"zero-shot":[17,151],"generalization":[18],"and":[19,26,107,144,157,185],"flexible":[20],"prompting.":[21],"Despite":[22],"SAM":[23,51,89,101,123,179],"finding":[24,128],"applications":[25],"adaptations":[27],"in":[28,35,57,127,177],"various":[29],"domains,":[30],"its":[31],"primary":[32],"limitation":[33],"lies":[34],"the":[36,53,64,88,134,190],"inability":[37],"to":[38,48,68,73,99,125,137,171,180],"grasp":[39],"object":[40,55,183],"semantics.":[41],"In":[42,114],"this":[43,169],"paper,":[44],"we":[45,70,92,116],"present":[46],"Sambor":[47,132],"seamlessly":[49],"integrate":[50],"with":[52,189],"open-vocabulary":[54,135,187],"detector":[56,136],"an":[58,118],"end-to-end":[59],"framework.":[60],"While":[61],"retaining":[62],"all":[63],"remarkable":[65],"capabilities":[66],"inherent":[67],"SAM,":[69],"boost":[71],"it":[72],"detect":[74],"arbitrary":[75],"objects":[76,106],"from":[77],"human":[78],"inputs":[79],"like":[80],"category":[81],"names":[82],"or":[83],"reference":[84],"expressions.":[85],"Building":[86],"upon":[87],"image":[90],"encoder,":[91],"introduce":[93],"novel":[95],"SideFormer":[96],"module":[97],"designed":[98],"acquire":[100],"features":[102],"adept":[103],"at":[104],"perceiving":[105],"inject":[108],"comprehensive":[109],"semantic":[110],"information":[111],"for":[112,168],"recognition.":[113],"addition,":[115],"devise":[117],"Open-set":[119],"RPN":[120],"that":[121],"leverages":[122],"proposals":[124],"assist":[126],"potential":[129],"objects.":[130],"Consequently,":[131],"enables":[133],"equally":[138],"focus":[139],"on":[140],"generalizing":[141],"both":[142],"localization":[143],"classification":[145],"sub-tasks.":[146],"Our":[147],"approach":[148],"demonstrates":[149],"superior":[150],"performance":[152],"across":[153],"benchmarks,":[154],"including":[155],"COCO":[156],"LVIS,":[158],"proving":[159],"highly":[160],"competitive":[161],"against":[162],"previous":[163],"state-of-the-art":[164],"methods.":[165],"We":[166],"aspire":[167],"work":[170],"serve":[172],"meaningful":[175],"endeavor":[176],"endowing":[178],"recognize":[181],"diverse":[182],"categories":[184],"advancing":[186],"learning":[188],"support":[191],"of":[192],"models.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}