{"id":"https://openalex.org/W4409154944","doi":"https://doi.org/10.1109/tpami.2025.3557841","title":"JointFormer: A Unified Framework With Joint Modeling for Video Object Segmentation","display_name":"JointFormer: A Unified Framework With Joint Modeling for Video Object Segmentation","publication_year":2025,"publication_date":"2025-04-04","ids":{"openalex":"https://openalex.org/W4409154944","doi":"https://doi.org/10.1109/tpami.2025.3557841","pmid":"https://pubmed.ncbi.nlm.nih.gov/40184296"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3557841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3557841","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/A5100453786","display_name":"Jiaming Zhang","orcid":"https://orcid.org/0009-0002-1123-8420"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Zhang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003850662","display_name":"Yutao Cui","orcid":"https://orcid.org/0000-0003-4788-9751"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutao Cui","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4788-9751","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101546753","display_name":"Gangshan Wu","orcid":"https://orcid.org/0000-0003-1391-1762"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangshan Wu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-1391-1762","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100436505","display_name":"Limin Wang","orcid":"https://orcid.org/0000-0002-3674-7718"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Limin Wang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-3674-7718","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":1.5311,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.81383953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"47","issue":"7","first_page":"6039","last_page":"6054"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9799000024795532,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9799000024795532,"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":0.9779000282287598,"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":0.9684000015258789,"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":0.7384752035140991},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7246609926223755},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.672080397605896},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6360727548599243},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6209657788276672},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5715706944465637},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4924858510494232},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.4618384540081024},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.4393559396266937},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39154136180877686},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10248413681983948}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7384752035140991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7246609926223755},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.672080397605896},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6360727548599243},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6209657788276672},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5715706944465637},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4924858510494232},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.4618384540081024},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.4393559396266937},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39154136180877686},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10248413681983948},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3557841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3557841","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:40184296","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40184296","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/G4152983559","display_name":null,"funder_award_id":"2022ZD0160900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4889781089","display_name":null,"funder_award_id":"020214380119","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"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":82,"referenced_works":["https://openalex.org/W575921498","https://openalex.org/W2294182682","https://openalex.org/W2460260369","https://openalex.org/W2470139095","https://openalex.org/W2564998703","https://openalex.org/W2740667773","https://openalex.org/W2798441772","https://openalex.org/W2799157347","https://openalex.org/W2889658408","https://openalex.org/W2889986507","https://openalex.org/W2916797271","https://openalex.org/W2950635152","https://openalex.org/W2962825871","https://openalex.org/W2962914239","https://openalex.org/W2963253279","https://openalex.org/W2963548592","https://openalex.org/W2963732700","https://openalex.org/W2963773230","https://openalex.org/W2964157492","https://openalex.org/W2964199361","https://openalex.org/W2964211168","https://openalex.org/W2964218467","https://openalex.org/W2965729941","https://openalex.org/W2989161706","https://openalex.org/W2990205821","https://openalex.org/W3034328552","https://openalex.org/W3034438741","https://openalex.org/W3094664776","https://openalex.org/W3096609285","https://openalex.org/W3108819577","https://openalex.org/W3126721948","https://openalex.org/W3131500599","https://openalex.org/W3160550216","https://openalex.org/W3170630188","https://openalex.org/W3170841864","https://openalex.org/W3175132347","https://openalex.org/W3183673520","https://openalex.org/W3188427387","https://openalex.org/W3192871594","https://openalex.org/W3200949949","https://openalex.org/W4214493665","https://openalex.org/W4309864194","https://openalex.org/W4312312588","https://openalex.org/W4312323989","https://openalex.org/W4312396403","https://openalex.org/W4312446817","https://openalex.org/W4312453657","https://openalex.org/W4312510454","https://openalex.org/W4312732475","https://openalex.org/W4312751983","https://openalex.org/W4312805142","https://openalex.org/W4313156423","https://openalex.org/W4385245566","https://openalex.org/W4386065555","https://openalex.org/W4386066071","https://openalex.org/W4386066394","https://openalex.org/W4386075958","https://openalex.org/W4390190626","https://openalex.org/W4390872599","https://openalex.org/W4390873799","https://openalex.org/W4390874144","https://openalex.org/W4390874670","https://openalex.org/W4402753923","https://openalex.org/W6631190155","https://openalex.org/W6678280073","https://openalex.org/W6735467293","https://openalex.org/W6757817989","https://openalex.org/W6759534164","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6784713722","https://openalex.org/W6796075269","https://openalex.org/W6796494063","https://openalex.org/W6796505553","https://openalex.org/W6796524941","https://openalex.org/W6797399245","https://openalex.org/W6838961708","https://openalex.org/W6839371072","https://openalex.org/W6843071136","https://openalex.org/W6846529796","https://openalex.org/W6846581650","https://openalex.org/W6852835101"],"related_works":["https://openalex.org/W3144569342","https://openalex.org/W2945274617","https://openalex.org/W1986655823","https://openalex.org/W2185902295","https://openalex.org/W2103507220","https://openalex.org/W2055202857","https://openalex.org/W4205800335","https://openalex.org/W2371519352","https://openalex.org/W2386644571","https://openalex.org/W2372421320"],"abstract_inverted_index":{"Current":[0],"prevailing":[1],"Video":[2],"Object":[3],"Segmentation":[4],"(VOS)":[5],"methods":[6],"follow":[7],"the":[8,49,99,103,107,136,168,180,189,199,243],"pipeline":[9,31],"of":[10,201],"extraction-then-matching,":[11],"which":[12,154],"first":[13],"extracts":[14],"features":[15,157],"on":[16,179,207],"current":[17,108,253],"and":[18,22,40,83,97,110,126,138,158,185,188,194,227,260,265,273,277],"reference":[19,104],"frames":[20,36],"independently,":[21],"then":[23],"performs":[24,159],"dense":[25],"matching":[26,51],"between":[27,35],"them.":[28],"This":[29],"decoupled":[30],"limits":[32],"information":[33,101,161],"propagation":[34,121,162],"to":[37,42,59,94,106,134,235],"high-level":[38,123],"features,":[39],"fails":[41],"capture":[43],"fine-grained":[44],"details":[45],"for":[46,76,216,220,224,229],"matching.":[47,278],"Furthermore,":[48],"pixel-wise":[50],"lacks":[52],"holistic":[53,139],"target":[54,100,140,156],"understanding,":[55],"making":[56],"it":[57,203],"prone":[58],"disturbance":[60],"by":[61],"similar":[62],"distractors.":[63],"To":[64,197],"address":[65,236],"these":[66,237],"issues,":[67],"we":[68,142],"propose":[69],"a":[70,84,111,144,149,164,175],"unified":[71],"VOS":[72],"framework,":[73],"coined":[74],"JointFormer,":[75,202],"jointly":[77],"modeling":[78,116,170],"feature":[79,124,130,275],"extraction,":[80],"correspondence":[81],"matching,":[82],"compressed":[85,112,145],"memory.":[86],"The":[87],"Joint":[88],"Modeling":[89],"Block":[90],"leverages":[91],"attention":[92],"operations":[93],"simultaneously":[95],"extract":[96],"propagate":[98],"from":[102],"frame":[105,109],"memory":[113,146],"token.This":[114],"joint":[115],"scheme":[117],"enables":[118,270],"extensive":[119,263],"multi-layer":[120],"beyond":[122],"space":[125],"facilitates":[127],"robust":[128],"instance-distinctive":[129],"learning.":[131],"In":[132],"addition,":[133],"incorporate":[135],"long-term":[137,230],"information,":[141],"introduce":[143],"token":[147],"with":[148,211,251],"customized":[150],"online":[151],"updating":[152],"mechanism,":[153],"aggregates":[155],"temporal":[160],"in":[163],"frame-wise":[165],"manner,":[166],"enhancing":[167],"global":[169],"consistency.":[171],"Our":[172],"JointFormer":[173,269],"achieves":[174,242],"new":[176,209],"state-of-the-art":[177],"performance":[178,245],"DAVIS":[181],"2017":[182],"val/test-dev":[183],"(89.7%":[184],"87.6%)":[186],"benchmarks":[187,210,248],"YouTube-VOS":[190],"2018/2019":[191],"val":[192],"(87.0%":[193],"87.0%)":[195],"benchmarks.":[196],"demonstrate":[198],"generalizability":[200],"is":[204],"further":[205],"evaluated":[206],"four":[208],"various":[212],"challenges,":[213],"including":[214],"MOSE":[215],"complex":[217,225],"scenes,":[218],"VISOR":[219],"egocentric":[221],"videos,":[222],"VOST":[223],"transformations,":[226],"LVOS":[228],"videos.":[231],"Without":[232],"specific":[233],"design":[234],"unusual":[238],"difficulties,":[239],"our":[240,268],"model":[241],"best":[244,254],"across":[246],"all":[247],"when":[249],"compared":[250],"several":[252],"models,":[255],"illustrating":[256],"its":[257],"excellent":[258],"generalization":[259],"robustness.":[261],"Further":[262],"ablations":[264],"visualizations":[266],"indicate":[267],"more":[271],"comprehensive":[272],"effective":[274],"learning":[276]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}