{"id":"https://openalex.org/W7138251283","doi":"https://doi.org/10.1609/aaai.v40i31.39822","title":"X-SAM: From Segment Anything to Any Segmentation","display_name":"X-SAM: From Segment Anything to Any Segmentation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138251283","doi":"https://doi.org/10.1609/aaai.v40i31.39822"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i31.39822","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39822","pdf_url":null,"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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i31.39822","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Limeng Qiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Limeng Qiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zequn Jie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zequn Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhijian Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhijian Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chengjian Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengjian Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Qingfang Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingfang Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lin Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xiangyuan Lan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangyuan Lan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Xiaodan Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaodan Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"31","first_page":"26187","last_page":"26196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7670000195503235,"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":0.7670000195503235,"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":0.05559999868273735,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.04780000075697899,"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":0.7962999939918518},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.5131000280380249},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5030999779701233},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4740000069141388},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.4499000012874603},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.39649999141693115},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.36980000138282776},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3644999861717224}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7962999939918518},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7391999959945679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6550999879837036},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.5131000280380249},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5030999779701233},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4740000069141388},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.4499000012874603},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3862999975681305},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31520000100135803},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.28940001130104065},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.26440000534057617}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i31.39822","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39822","pdf_url":null,"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"},{"id":"pmh:oai:ojs.aaai.org:article/39822","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/39822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i31.39822","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39822","pdf_url":null,"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":[{"id":"https://openalex.org/G2236135741","display_name":null,"funder_award_id":"2024YFE0203100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3953017609","display_name":null,"funder_award_id":"62536003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5578921854","display_name":null,"funder_award_id":"62402252","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6630003392","display_name":null,"funder_award_id":"62476293","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321160","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0,67],"Language":[1,68],"Models":[2],"(LLMs)":[3],"demonstrate":[4,151],"strong":[5],"capabilities":[6],"in":[7,16,30,38],"broad":[8],"knowledge":[9],"representation,":[10],"yet":[11],"they":[12],"are":[13],"inherently":[14],"deficient":[15],"pixel-level":[17,94,170],"perceptual":[18,95],"understanding.":[19,172],"Although":[20],"the":[21,74],"Segment":[22],"Anything":[23],"Model":[24,69],"(SAM)":[25],"represents":[26],"a":[27,53,64,86,102,139,158],"significant":[28],"advancement":[29],"visual-prompt-driven":[31],"image":[32,162],"segmentation,":[33,110],"it":[34,46],"exhibits":[35],"notable":[36],"limitations":[37],"multi-mask":[39],"prediction":[40],"and":[41,45,120],"category-specific":[42],"segmentation":[43,50,75,104,163],"tasks,":[44],"cannot":[47],"integrate":[48],"all":[49,113],"tasks":[51],"within":[52],"unified":[54,88,140],"model":[55],"architecture.":[56],"To":[57,129],"address":[58],"these":[59],"limitations,":[60],"we":[61,84,100,137],"present":[62,138],"X-SAM,":[63],"streamlined":[65],"Multimodal":[66],"(MLLM)":[70],"framework":[71,89],"that":[72,90,143,152],"extends":[73],"paradigm":[76],"from":[77],"segment":[78],"anything":[79],"to":[80],"any":[81],"segmentation.":[82],"Specifically,":[83],"introduce":[85],"novel":[87],"enables":[91],"more":[92],"advanced":[93],"comprehension":[96],"for":[97,168],"MLLMs.":[98],"Furthermore,":[99],"propose":[101],"new":[103],"task,":[105],"termed":[106],"Visual":[107],"GrounDed":[108],"(VGD)":[109],"which":[111],"segments":[112],"instance":[114],"objects":[115],"with":[116,123],"interactive":[117],"visual":[118,124,171],"prompts":[119],"empowers":[121],"MLLMs":[122],"grounded,":[125],"pixel-wise":[126],"interpretative":[127],"capabilities.":[128],"enable":[130],"effective":[131],"training":[132,141],"on":[133,157],"diverse":[134],"data":[135],"sources,":[136],"strategy":[142],"supports":[144],"co-training":[145],"across":[146],"multiple":[147],"datasets.":[148],"Experimental":[149],"results":[150],"X-SAM":[153],"achieves":[154],"state-of-the-art":[155],"performance":[156],"wide":[159],"range":[160],"of":[161],"benchmarks,":[164],"highlighting":[165],"its":[166],"efficiency":[167],"multimodal,":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-02T00:00:00"}