{"id":"https://openalex.org/W4407168545","doi":"https://doi.org/10.1109/tro.2025.3539198","title":"ZISVFM: Zero-Shot Object Instance Segmentation in Indoor Robotic Environments With Vision Foundation Models","display_name":"ZISVFM: Zero-Shot Object Instance Segmentation in Indoor Robotic Environments With Vision Foundation Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4407168545","doi":"https://doi.org/10.1109/tro.2025.3539198"},"language":"en","primary_location":{"id":"doi:10.1109/tro.2025.3539198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tro.2025.3539198","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-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/A5048357136","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0001-8982-8223"},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["School of Electrical Engineering, Yanshan University, Qinhuangdao, China"],"raw_orcid":"https://orcid.org/0000-0001-8982-8223","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Yanshan University, Qinhuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062723492","display_name":"Maoliang Yin","orcid":"https://orcid.org/0009-0003-8106-7521"},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maoliang Yin","raw_affiliation_strings":["School of Electrical Engineering, Yanshan University, Qinhuangdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Yanshan University, Qinhuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100577002","display_name":"Wenfu Bi","orcid":"https://orcid.org/0009-0002-4292-3287"},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenfu Bi","raw_affiliation_strings":["School of Electrical Engineering, Yanshan University, Qinhuangdao, China"],"raw_orcid":"https://orcid.org/0009-0002-4292-3287","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Yanshan University, Qinhuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haibao Yan","orcid":"https://orcid.org/0009-0004-4272-9980"},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibao Yan","raw_affiliation_strings":["School of Electrical Engineering, Yanshan University, Qinhuangdao, China"],"raw_orcid":"https://orcid.org/0009-0004-4272-9980","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Yanshan University, Qinhuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109790753","display_name":"Shaohan Bian","orcid":"https://orcid.org/0009-0008-4452-0389"},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohan Bian","raw_affiliation_strings":["School of Electrical Engineering, Yanshan University, Qinhuangdao, China"],"raw_orcid":"https://orcid.org/0009-0008-4452-0389","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Yanshan University, Qinhuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015343493","display_name":"Cuihua Zhang","orcid":"https://orcid.org/0000-0003-2275-4578"},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cui-Hua Zhang","raw_affiliation_strings":["School of Electrical Engineering, Yanshan University, Qinhuangdao, China"],"raw_orcid":"https://orcid.org/0000-0003-2275-4578","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Yanshan University, Qinhuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100380201","display_name":"Changchun Hua","orcid":"https://orcid.org/0000-0001-6311-2112"},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changchun Hua","raw_affiliation_strings":["School of Electrical Engineering, Yanshan University, Qinhuangdao, China"],"raw_orcid":"https://orcid.org/0000-0001-6311-2112","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Yanshan University, Qinhuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5048357136"],"corresponding_institution_ids":["https://openalex.org/I39333907"],"apc_list":null,"apc_paid":null,"fwci":12.4657,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.98701391,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"41","issue":null,"first_page":"1568","last_page":"1580"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9959999918937683,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9959999918937683,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9926000237464905,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7439095973968506},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7331222295761108},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5935050249099731},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5698257684707642},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5432094931602478},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.5049143433570862},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4976086914539337},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4861857295036316},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.47882989048957825},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.46946823596954346},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4324427843093872},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3824918866157532},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.12559977173805237}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7439095973968506},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7331222295761108},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5935050249099731},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5698257684707642},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5432094931602478},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5049143433570862},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4976086914539337},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4861857295036316},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.47882989048957825},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.46946823596954346},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4324427843093872},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3824918866157532},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.12559977173805237},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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/tro.2025.3539198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tro.2025.3539198","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G1438256657","display_name":null,"funder_award_id":"F2024203115","funder_id":"https://openalex.org/F4320322163","funder_display_name":"Natural Science Foundation of Hebei Province"},{"id":"https://openalex.org/G1530245929","display_name":null,"funder_award_id":"62203377","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2840487366","display_name":null,"funder_award_id":"62073279","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4605569144","display_name":null,"funder_award_id":"F2024203051","funder_id":"https://openalex.org/F4320322163","funder_display_name":"Natural Science Foundation of Hebei Province"},{"id":"https://openalex.org/G4674858220","display_name":null,"funder_award_id":"F2024203036","funder_id":"https://openalex.org/F4320322163","funder_display_name":"Natural Science Foundation of Hebei Province"},{"id":"https://openalex.org/G5760530916","display_name":null,"funder_award_id":"62203378","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/F4320322163","display_name":"Natural Science Foundation of Hebei Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W1972630525","https://openalex.org/W2011301426","https://openalex.org/W2068127265","https://openalex.org/W2083620785","https://openalex.org/W2117539524","https://openalex.org/W2896457183","https://openalex.org/W2963150697","https://openalex.org/W2966885779","https://openalex.org/W2967153639","https://openalex.org/W2993182889","https://openalex.org/W2999219213","https://openalex.org/W3001586682","https://openalex.org/W3003224579","https://openalex.org/W3094502228","https://openalex.org/W3132455321","https://openalex.org/W3137905681","https://openalex.org/W3145450063","https://openalex.org/W3156988133","https://openalex.org/W3159481202","https://openalex.org/W3200139538","https://openalex.org/W3207187156","https://openalex.org/W4206755693","https://openalex.org/W4283721125","https://openalex.org/W4312615341","https://openalex.org/W4313156423","https://openalex.org/W4376481256","https://openalex.org/W4383108475","https://openalex.org/W4385245566","https://openalex.org/W4385430481","https://openalex.org/W4390190260","https://openalex.org/W4390754102","https://openalex.org/W4390873795","https://openalex.org/W4390874575","https://openalex.org/W4395015601","https://openalex.org/W4401413773","https://openalex.org/W4406208390","https://openalex.org/W6766284323","https://openalex.org/W6781542114","https://openalex.org/W6796761347","https://openalex.org/W6798280791","https://openalex.org/W6799515669","https://openalex.org/W6811470611","https://openalex.org/W6851607685","https://openalex.org/W6851800889","https://openalex.org/W6851932778","https://openalex.org/W6852629184","https://openalex.org/W6852846236","https://openalex.org/W6856857450","https://openalex.org/W6858236115"],"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/W1522196789"],"abstract_inverted_index":{"Service":[0],"robots":[1],"operating":[2],"in":[3,35,103,163],"unstructured":[4],"environments":[5],"must":[6],"effectively":[7],"recognize":[8],"and":[9,89,132,153,173],"segment":[10,85],"unknown":[11],"objects":[12,33],"to":[13,45,54,56,128,136],"enhance":[14],"their":[15],"functionality.":[16],"Traditional":[17],"supervised":[18],"learning-based":[19],"segmentation":[20,41],"techniques":[21],"require":[22],"extensive":[23],"annotated":[24],"datasets,":[25],"which":[26],"are":[27],"impractical":[28],"for":[29,74],"the":[30,64,79,84,104,125,158],"diversity":[31],"of":[32,83,161],"encountered":[34],"real-world":[36],"scenarios.":[37],"Unseen":[38],"object":[39,145],"instance":[40],"(UOIS)":[42],"methods":[43],"aim":[44],"address":[46],"this":[47],"by":[48,77],"training":[49],"models":[50],"on":[51,149],"synthetic":[52],"data":[53],"generalize":[55],"novel":[57,71],"objects,":[58],"but":[59],"they":[60],"often":[61],"suffer":[62],"from":[63,93,112,124],"simulation-to-reality":[65],"gap.":[66],"This":[67],"article":[68],"proposes":[69],"a":[70,94,154],"approach":[72],"(ZISVFM)":[73],"solving":[75],"UOIS":[76],"leveraging":[78],"powerful":[80],"zero-shot":[81],"capability":[82],"anything":[86],"model":[87],"(SAM)":[88],"explicit":[90],"visual":[91],"representations":[92],"self-supervised":[95,126],"vision":[96],"transformer":[97],"(ViT).":[98],"The":[99],"proposed":[100],"framework":[101],"operates":[102],"following":[105],"three":[106],"stages:":[107],"generating":[108],"object-agnostic":[109],"mask":[110],"proposals":[111,120],"colorized":[113],"depth":[114],"images":[115],"using":[116,121],"SAM,":[117],"refining":[118],"these":[119],"attention-based":[122],"features":[123],"ViT":[127],"filter":[129],"nonobject":[130],"masks,":[131],"applying":[133],"K-Medoids":[134],"clustering":[135],"generate":[137],"point":[138],"prompts":[139],"that":[140],"guide":[141],"SAM":[142],"toward":[143],"precise":[144],"segmentation.":[146],"Experimental":[147],"validation":[148],"two":[150],"benchmark":[151],"datasets":[152],"self-collected":[155],"dataset":[156],"demonstrates":[157],"superior":[159],"performance":[160],"ZISVFM":[162],"complex":[164],"environments,":[165],"including":[166],"hierarchical":[167],"settings":[168],"such":[169],"as":[170],"cabinets,":[171],"drawers,":[172],"handheld":[174],"objects.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":5}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
