{"id":"https://openalex.org/W4393405392","doi":"https://doi.org/10.1109/tpami.2024.3383592","title":"Scalable Video Object Segmentation With Identification Mechanism","display_name":"Scalable Video Object Segmentation With Identification Mechanism","publication_year":2024,"publication_date":"2024-04-02","ids":{"openalex":"https://openalex.org/W4393405392","doi":"https://doi.org/10.1109/tpami.2024.3383592","pmid":"https://pubmed.ncbi.nlm.nih.gov/38564351"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3383592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3383592","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5020316185","display_name":"Zongxin Yang","orcid":"https://orcid.org/0000-0001-8783-8313"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zongxin Yang","raw_affiliation_strings":["ReLER, CCAI, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"ReLER, CCAI, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011439390","display_name":"Jiaxu Miao","orcid":"https://orcid.org/0000-0002-4238-8475"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxu Miao","raw_affiliation_strings":["School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087043856","display_name":"Yunchao Wei","orcid":"https://orcid.org/0000-0002-2812-8781"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunchao Wei","raw_affiliation_strings":["Institute of Information Science, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101433884","display_name":"Wenguan Wang","orcid":"https://orcid.org/0000-0002-0802-9567"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenguan Wang","raw_affiliation_strings":["ReLER, CCAI, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"ReLER, CCAI, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354377","display_name":"Xiaohan Wang","orcid":"https://orcid.org/0000-0001-6206-7911"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohan Wang","raw_affiliation_strings":["ReLER, CCAI, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"ReLER, CCAI, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005421447","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0512-880X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["ReLER, CCAI, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"ReLER, CCAI, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5020316185"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":6.98,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.97826459,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"46","issue":"9","first_page":"6247","last_page":"6262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9998999834060669,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9995999932289124,"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":0.8312278985977173},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7682245969772339},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6593693494796753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6091214418411255},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5149998664855957},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4780500531196594},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4761364758014679},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42847299575805664},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40758806467056274},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34476912021636963},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10602256655693054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8312278985977173},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7682245969772339},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6593693494796753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6091214418411255},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5149998664855957},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4780500531196594},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4761364758014679},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42847299575805664},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40758806467056274},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34476912021636963},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10602256655693054},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3383592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3383592","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:38564351","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38564351","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7235758038","display_name":null,"funder_award_id":"226-2022-00051","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8628682313","display_name":null,"funder_award_id":"T2293723","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":105,"referenced_works":["https://openalex.org/W1560354729","https://openalex.org/W1861492603","https://openalex.org/W2009874829","https://openalex.org/W2011953904","https://openalex.org/W2031489346","https://openalex.org/W2062385571","https://openalex.org/W2086161653","https://openalex.org/W2105482032","https://openalex.org/W2144794286","https://openalex.org/W2187051054","https://openalex.org/W2194775991","https://openalex.org/W2294182682","https://openalex.org/W2331143823","https://openalex.org/W2470139095","https://openalex.org/W2564998703","https://openalex.org/W2565639579","https://openalex.org/W2792215676","https://openalex.org/W2798441772","https://openalex.org/W2799157347","https://openalex.org/W2889658408","https://openalex.org/W2889986507","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2916743882","https://openalex.org/W2916797271","https://openalex.org/W2919115771","https://openalex.org/W2962677625","https://openalex.org/W2962825871","https://openalex.org/W2963091558","https://openalex.org/W2963163009","https://openalex.org/W2963253279","https://openalex.org/W2963732700","https://openalex.org/W2964157492","https://openalex.org/W2964218467","https://openalex.org/W2986050084","https://openalex.org/W2990205821","https://openalex.org/W2995131893","https://openalex.org/W3034538699","https://openalex.org/W3035502324","https://openalex.org/W3094664776","https://openalex.org/W3096609285","https://openalex.org/W3106773277","https://openalex.org/W3108819577","https://openalex.org/W3110030584","https://openalex.org/W3117097536","https://openalex.org/W3119686997","https://openalex.org/W3126721948","https://openalex.org/W3128990302","https://openalex.org/W3138516171","https://openalex.org/W3149936330","https://openalex.org/W3158120491","https://openalex.org/W3160550216","https://openalex.org/W3167536469","https://openalex.org/W3170630188","https://openalex.org/W3171516518","https://openalex.org/W3179869055","https://openalex.org/W3182236906","https://openalex.org/W3192871594","https://openalex.org/W3200949949","https://openalex.org/W3214586131","https://openalex.org/W4200631531","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4220784021","https://openalex.org/W4225495512","https://openalex.org/W4239147634","https://openalex.org/W4250482878","https://openalex.org/W4294691145","https://openalex.org/W4312271117","https://openalex.org/W4312295067","https://openalex.org/W4312396403","https://openalex.org/W4312465615","https://openalex.org/W4312510454","https://openalex.org/W4312560592","https://openalex.org/W4312567319","https://openalex.org/W4312732475","https://openalex.org/W4312845411","https://openalex.org/W4312868348","https://openalex.org/W4313044016","https://openalex.org/W4376312146","https://openalex.org/W4382461844","https://openalex.org/W4385245566","https://openalex.org/W4385269064","https://openalex.org/W4385768066","https://openalex.org/W4386065582","https://openalex.org/W4386065815","https://openalex.org/W4386066071","https://openalex.org/W4386076516","https://openalex.org/W4390872484","https://openalex.org/W4390872946","https://openalex.org/W4394597470","https://openalex.org/W6741753902","https://openalex.org/W6755977528","https://openalex.org/W6757036269","https://openalex.org/W6757817989","https://openalex.org/W6759534164","https://openalex.org/W6763509872","https://openalex.org/W6770506093","https://openalex.org/W6780226713","https://openalex.org/W6784333009","https://openalex.org/W6784713722","https://openalex.org/W6796505553","https://openalex.org/W6796524941","https://openalex.org/W6846581650","https://openalex.org/W6852629184"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574","https://openalex.org/W4246352526","https://openalex.org/W2121910908"],"abstract_inverted_index":{"This":[0,103,151],"paper":[1],"delves":[2],"into":[3],"the":[4,30,57,92,106,110,118,131,159,169,188,229,247,251],"challenges":[5],"of":[6,32,122,133,171],"achieving":[7],"scalable":[8,139,145],"and":[9,39,55,78,120,147,162,200,208,224,232,236],"effective":[10,87],"multi-object":[11,33,45,88,178],"modeling":[12],"for":[13,158,174],"semi-supervised":[14],"Video":[15,184,255],"Object":[16,185,256],"Segmentation":[17,186,257],"(VOS).":[18],"Previous":[19],"VOS":[20,157,175,212],"methods":[21],"decode":[22],"features":[23],"with":[24,75,81],"a":[25,100,125,172,182],"single":[26,126],"positive":[27],"object,":[28],"limiting":[29],"learning":[31],"representation":[34,166],"as":[35],"they":[36],"must":[37],"match":[38],"segment":[40],"each":[41,98],"target":[42],"separately":[43],"under":[44],"scenarios.":[46],"Additionally,":[47],"earlier":[48],"techniques":[49],"catered":[50],"to":[51,59,96,108,192],"specific":[52],"application":[53],"objectives":[54],"lacked":[56],"flexibility":[58],"fulfill":[60],"different":[61],"speed-accuracy":[62],"requirements.":[63],"To":[64,129],"address":[65,130],"these":[66],"problems,":[67],"we":[68,180,244],"present":[69],"two":[70],"innovative":[71],"approaches,":[72],"Associating":[73,79],"Objects":[74,80],"Transformers":[76,83],"(AOT)":[77],"Scalable":[82],"(AOST).":[84],"In":[85],"pursuing":[86],"modeling,":[89],"AOT":[90,199],"introduces":[91],"IDentification":[93],"(ID)":[94],"mechanism":[95],"allocate":[97],"object":[99],"unique":[101],"identity.":[102],"approach":[104],"enables":[105,152],"network":[107,127],"model":[109],"associations":[111],"among":[112],"all":[113,240],"objects":[114,123],"simultaneously,":[115],"thus":[116],"facilitating":[117],"tracking":[119],"segmentation":[121],"in":[124,156,187,250],"pass.":[128],"challenge":[132],"inflexible":[134],"deployment,":[135],"AOST":[136,201],"further":[137],"integrates":[138],"long":[140],"short-term":[141],"transformers":[142],"that":[143],"incorporate":[144],"supervision":[146],"layer-wise":[148],"ID-based":[149],"attention.":[150],"online":[153],"architecture":[154],"scalability":[155,237],"first":[160],"time":[161],"overcomes":[163],"ID":[164],"embeddings'":[165],"limitations.":[167],"Given":[168],"absence":[170],"benchmark":[173,191],"involving":[176],"densely":[177],"annotations,":[179],"propose":[181],"challenging":[183],"Wild":[189],"(VOSW)":[190],"validate":[193],"our":[194],"approaches.":[195],"We":[196],"evaluated":[197],"various":[198],"variants":[202],"using":[203],"extensive":[204],"experiments":[205],"across":[206,239],"VOSW":[207],"five":[209],"commonly":[210],"used":[211],"benchmarks,":[213],"including":[214],"YouTube-VOS":[215],"2018":[216],"&":[217,222],"2019":[218],"Val,":[219],"DAVIS-2017":[220],"Val":[221],"Test,":[223],"DAVIS-2016.":[225],"Our":[226],"approaches":[227],"surpass":[228],"state-of-the-art":[230],"competitors":[231],"display":[233],"exceptional":[234],"efficiency":[235],"consistently":[238],"six":[241],"benchmarks.":[242],"Moreover,":[243],"notably":[245],"achieved":[246],"1<sup>st</sup>":[248],"position":[249],"3":[252],"rd":[253],"Large-scale":[254],"Challenge.":[258]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}