{"id":"https://openalex.org/W7125367639","doi":"https://doi.org/10.1109/tip.2025.3649360","title":"Video Decoupling Networks for Accurate, Efficient, Generalizable, and Robust Video Object Segmentation","display_name":"Video Decoupling Networks for Accurate, Efficient, Generalizable, and Robust Video Object Segmentation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7125367639","doi":"https://doi.org/10.1109/tip.2025.3649360","pmid":"https://pubmed.ncbi.nlm.nih.gov/41564046"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3649360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3649360","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","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/A5123554063","display_name":"Jisheng Dang","orcid":null},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jisheng Dang","raw_affiliation_strings":["School of Information Science and Engineering, Lanzhou University, Lanzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5378-6225","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Lanzhou University, Lanzhou, China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123584278","display_name":"Huicheng Zheng","orcid":null},"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":"Huicheng Zheng","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6729-4176","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123577939","display_name":"Yulan Guo","orcid":null},"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":"Yulan Guo","raw_affiliation_strings":["School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0952-476X","affiliations":[{"raw_affiliation_string":"School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123595946","display_name":"Jianhuang Lai","orcid":null},"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":"Jianhuang Lai","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3883-2024","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380066","display_name":"Bin Hu","orcid":"https://orcid.org/0000-0003-3514-5413"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Hu","raw_affiliation_strings":["School of Medical Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3514-5413","affiliations":[{"raw_affiliation_string":"School of Medical Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123554097","display_name":"Tat-Seng Chua","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["School of Computing, National University of Singapore, Queenstown, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Queenstown, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5123554063"],"corresponding_institution_ids":["https://openalex.org/I76214153"],"apc_list":null,"apc_paid":null,"fwci":62.6908,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.99709698,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"35","issue":null,"first_page":"1218","last_page":"1230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.808899998664856,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.808899998664856,"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":0.07119999825954437,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.02410000003874302,"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/robustness","display_name":"Robustness (evolution)","score":0.7422999739646912},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5891000032424927},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5005999803543091},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.48420000076293945},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.41839998960494995},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.40639999508857727},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.3481999933719635},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.33889999985694885},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3353999853134155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817300021648407},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7422999739646912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7408999800682068},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.670799970626831},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5891000032424927},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5005999803543091},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.48420000076293945},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.40639999508857727},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.31220000982284546},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30410000681877136},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.26460000872612},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.2578999996185303},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.25769999623298645},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2025.3649360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3649360","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:41564046","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41564046","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1056251607","display_name":null,"funder_award_id":"62227807","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5872406435","display_name":null,"funder_award_id":"62301601","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G622858442","display_name":null,"funder_award_id":"62372491","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6414949351","display_name":null,"funder_award_id":"U24B20186","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6790872277","display_name":null,"funder_award_id":"61972435","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6977730487","display_name":null,"funder_award_id":"61976231","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8252004906","display_name":null,"funder_award_id":"U20A20185","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W2082627290","https://openalex.org/W2194775991","https://openalex.org/W2294182682","https://openalex.org/W2463175074","https://openalex.org/W2470139095","https://openalex.org/W2740667773","https://openalex.org/W2799157347","https://openalex.org/W2889986507","https://openalex.org/W2963091558","https://openalex.org/W2963131444","https://openalex.org/W2963253279","https://openalex.org/W2965729941","https://openalex.org/W2989161706","https://openalex.org/W2990205821","https://openalex.org/W3034438741","https://openalex.org/W3034538699","https://openalex.org/W3094797876","https://openalex.org/W3104487525","https://openalex.org/W3117097536","https://openalex.org/W3160550216","https://openalex.org/W3175373394","https://openalex.org/W3182541239","https://openalex.org/W3183673520","https://openalex.org/W4220784021","https://openalex.org/W4283827327","https://openalex.org/W4312271117","https://openalex.org/W4312293671","https://openalex.org/W4312396403","https://openalex.org/W4312510454","https://openalex.org/W4312732475","https://openalex.org/W4313171270","https://openalex.org/W4382461844","https://openalex.org/W4383899959","https://openalex.org/W4385801279","https://openalex.org/W4386065582","https://openalex.org/W4386065828","https://openalex.org/W4386065959","https://openalex.org/W4386075877","https://openalex.org/W4386076383","https://openalex.org/W4386076516","https://openalex.org/W4387929770","https://openalex.org/W4390017901","https://openalex.org/W4390190670","https://openalex.org/W4390872599","https://openalex.org/W4390872946","https://openalex.org/W4390873799","https://openalex.org/W4390874144","https://openalex.org/W4391547535","https://openalex.org/W4393305204","https://openalex.org/W4393405392","https://openalex.org/W4400410003","https://openalex.org/W4400579078","https://openalex.org/W4401023587","https://openalex.org/W4401990337","https://openalex.org/W4402944023","https://openalex.org/W4403599994","https://openalex.org/W4404895558","https://openalex.org/W4406657543","https://openalex.org/W4407638878","https://openalex.org/W4409263620","https://openalex.org/W4414360088","https://openalex.org/W4414360705","https://openalex.org/W7123347303","https://openalex.org/W7124431042"],"related_works":[],"abstract_inverted_index":{"Video":[0,52],"object":[1],"segmentation":[2],"(VOS)":[3],"is":[4,64],"a":[5,51,57,105,164,169],"fundamental":[6,82],"task":[7,122],"in":[8,36,104,139],"video":[9,21,79],"analysis,":[10],"aiming":[11],"to":[12,29,136,173],"accurately":[13],"recognize":[14],"and":[15,39,75,86,132,156,168,189],"segment":[16],"objects":[17],"of":[18,70,117,158],"interest":[19],"within":[20],"sequences.":[22],"Conventional":[23],"methods,":[24],"relying":[25],"on":[26,121,146,177],"memory":[27,59],"networks":[28],"store":[30],"single-frame":[31],"appearance":[32],"features,":[33],"face":[34],"challenges":[35],"computational":[37],"efficiency":[38],"capturing":[40],"dynamic":[41],"visual":[42,73],"information":[43,130],"effectively.":[44],"To":[45],"address":[46],"these":[47],"limitations,":[48],"we":[49],"present":[50],"Decoupling":[53],"Network":[54],"(VDN)":[55],"with":[56],"per-clip":[58],"updating":[60],"mechanism.":[61],"Our":[62],"approach":[63],"inspired":[65],"by":[66],"the":[67,71,90,151],"dual-stream":[68],"hypothesis":[69],"human":[72],"cortex":[74],"decomposes":[76],"multiple":[77,99,147,178],"previous":[78,174],"frames":[80,100],"into":[81,101],"elements:":[83],"scene,":[84],"motion,":[85],"instance.":[87],"We":[88],"propose":[89],"Unified":[91],"Prior-based":[92],"Spatio-temporal":[93],"Decoupler":[94],"(UPSD)":[95],"algorithm,":[96],"which":[97],"parses":[98],"basic":[102],"elements":[103,111],"unified":[106],"manner.":[107],"UPSD":[108],"continuously":[109],"stores":[110],"over":[112],"time,":[113],"enabling":[114],"adaptive":[115],"integration":[116],"different":[118],"cues":[119],"based":[120],"requirements.":[123],"This":[124],"decomposition":[125],"mechanism":[126],"facilitates":[127],"comprehensive":[128],"spatial-temporal":[129],"capture":[131],"rapid":[133],"updating,":[134],"leading":[135],"notable":[137],"enhancements":[138],"overall":[140],"VOS":[141,148,179],"performance.":[142],"Extensive":[143],"experiments":[144],"conducted":[145],"benchmarks":[149],"validate":[150],"state-of-the-art":[152,175],"accuracy,":[153],"efficiency,":[154],"generalizability,":[155],"robustness":[157,190],"our":[159],"approach.":[160],"Remarkably,":[161],"VDN":[162],"demonstrates":[163],"significant":[165],"performance":[166],"improvement":[167],"substantial":[170],"speed-up":[171],"compared":[172],"methods":[176],"benchmarks.":[180],"It":[181],"also":[182],"exhibits":[183],"excellent":[184],"generalizability":[185],"under":[186],"domain":[187],"shift":[188],"against":[191],"various":[192],"noise":[193],"types.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2026-01-23T00:00:00"}