{"id":"https://openalex.org/W7151380282","doi":"https://doi.org/10.1007/s11263-026-02742-1","title":"Domain Generalization for Multiple Video Object Segmentation and Tracking Using Transformers and Smart Memory","display_name":"Domain Generalization for Multiple Video Object Segmentation and Tracking Using Transformers and Smart Memory","publication_year":2026,"publication_date":"2026-04-07","ids":{"openalex":"https://openalex.org/W7151380282","doi":"https://doi.org/10.1007/s11263-026-02742-1"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-026-02742-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02742-1","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s11263-026-02742-1","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102596874","display_name":"Elham Soltani Kazemi","orcid":null},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Elham Soltani Kazemi","raw_affiliation_strings":["Dept. of Electrical Engineering and Computer Science, University of Missouri, Columbia, 65211, MO, USA"],"raw_orcid":"https://orcid.org/0009-0009-0861-0552","affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering and Computer Science, University of Missouri, Columbia, 65211, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006780186","display_name":"Imad Eddine Toubal","orcid":"https://orcid.org/0000-0003-1754-0823"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Imad Eddine Toubal","raw_affiliation_strings":["Dept. of Electrical Engineering and Computer Science, University of Missouri, Columbia, 65211, MO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering and Computer Science, University of Missouri, Columbia, 65211, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035597471","display_name":"Gani Rahmon","orcid":"https://orcid.org/0000-0002-4961-8229"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gani Rahmon","raw_affiliation_strings":["Dept. of Electrical Engineering and Computer Science, University of Missouri, Columbia, 65211, MO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering and Computer Science, University of Missouri, Columbia, 65211, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038196081","display_name":"Juan Mogollon","orcid":null},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Mogollon","raw_affiliation_strings":["Dept. of Electrical Engineering and Computer Science, University of Missouri, Columbia, 65211, MO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering and Computer Science, University of Missouri, Columbia, 65211, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133106067","display_name":"Kannappan Palaniappan","orcid":null},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kannappan Palaniappan","raw_affiliation_strings":["Dept. of Electrical Engineering and Computer Science, University of Missouri, Columbia, 65211, MO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering and Computer Science, University of Missouri, Columbia, 65211, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102596874"],"corresponding_institution_ids":["https://openalex.org/I76835614"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57595141,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"134","issue":"5","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.2687999904155731,"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":0.2687999904155731,"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":0.2680000066757202,"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":0.1679999977350235,"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/video-tracking","display_name":"Video tracking","score":0.6360999941825867},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6279000043869019},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5414000153541565},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4487999975681305},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.43309998512268066},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43149998784065247},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41670000553131104},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4077000021934509},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3668999969959259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7997999787330627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7766000032424927},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7093999981880188},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.6360999941825867},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6279000043869019},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5414000153541565},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43149998784065247},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41670000553131104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3668999969959259},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.358599990606308},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.28690001368522644},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.2556999921798706},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-026-02742-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02742-1","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11263-026-02742-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02742-1","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1543512389","https://openalex.org/W1901129140","https://openalex.org/W1964127768","https://openalex.org/W2016589492","https://openalex.org/W2027105670","https://openalex.org/W2093986007","https://openalex.org/W2124857421","https://openalex.org/W2134262590","https://openalex.org/W2470139095","https://openalex.org/W2498644384","https://openalex.org/W2618743635","https://openalex.org/W2889986507","https://openalex.org/W2962825871","https://openalex.org/W2963150697","https://openalex.org/W2964137095","https://openalex.org/W2990205821","https://openalex.org/W3013092451","https://openalex.org/W3034798428","https://openalex.org/W3037464854","https://openalex.org/W3094664776","https://openalex.org/W3159481202","https://openalex.org/W3174415351","https://openalex.org/W3183673520","https://openalex.org/W4214759957","https://openalex.org/W4247552850","https://openalex.org/W4309864194","https://openalex.org/W4312510454","https://openalex.org/W4312708384","https://openalex.org/W4312751983","https://openalex.org/W4377019739","https://openalex.org/W4381803887","https://openalex.org/W4386065555","https://openalex.org/W4387704620","https://openalex.org/W4390190497","https://openalex.org/W4390872599","https://openalex.org/W4390873799","https://openalex.org/W4390874025","https://openalex.org/W4390874144","https://openalex.org/W4390874575","https://openalex.org/W4390874670","https://openalex.org/W4391827404","https://openalex.org/W4393405392","https://openalex.org/W4402727420","https://openalex.org/W4402753923","https://openalex.org/W4402754082","https://openalex.org/W4403842231","https://openalex.org/W4404612908","https://openalex.org/W4415798746","https://openalex.org/W7133224883"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Video":[1,180],"Object":[2],"Segmentation":[3],"(VOS)":[4],"is":[5],"a":[6,70,103,110],"key":[7,76,106],"component":[8],"in":[9,48,93],"computer":[10],"vision":[11],"applications,":[12],"including":[13],"surveillance,":[14],"autonomous":[15],"driving,":[16],"and":[17,43,53,62,119,123,147,182,184,192,198],"robotics.":[18],"However,":[19],"existing":[20],"VOS":[21,61,169,200],"models":[22],"often":[23],"struggle":[24],"with":[25,30,81,117,156],"generalization":[26,162],"to":[27,87,163],"new":[28],"videos":[29],"complex,":[31],"topologically":[32],"transforming":[33],"deformable":[34],"objects":[35],"(eg.":[36],"cooking,":[37],"assembling,":[38],"state":[39],"change),":[40],"degraded":[41],"environments":[42],"long":[44],"video":[45],"sequences,":[46],"resulting":[47,92],"tracking":[49,63],"drift,":[50,141],"low":[51],"recall":[52],"memory":[54,100,138],"saturation.":[55],"We":[56],"developed":[57],"Mu":[58],"ltiple":[59],"object":[60,95,144],"S":[64],"mart":[65],"Mem":[66],"ory":[67],"architecture":[68],"(MuSMem),":[69],"generalizable":[71],"approach":[72],"that":[73,101,173],"incorporates":[74],"three":[75],"innovations:":[77],"(i)":[78],"fusing":[79],"SAM":[80],"High-Quality":[82],"masks":[83],"alongside":[84],"appearance-based":[85],"candidate-selection":[86],"refine":[88],"coarse":[89],"segmentation":[90],"masks,":[91],"improved":[94],"boundaries;":[96],"(ii)":[97],"dynamic":[98],"smart":[99],"manages":[102],"history":[104],"of":[105,128],"frames":[107],"based":[108],"on":[109,177,186],"novel":[111],"information":[112],"preserving":[113],"gain":[114],",":[115],"combined":[116],"relevance":[118],"freshness":[120],"spatio-temporal":[121],"criteria;":[122],"(iii)":[124],"explores":[125],"the":[126,189],"use":[127],"monocular":[129],"depth":[130],"maps":[131],"for":[132,160],"occlusion":[133],"robustness.":[134],"MuSMem":[135,152,174],"significantly":[136],"reduces":[137,140],"usage,":[139],"tracks":[142],"complex":[143,199],"topological":[145],"changes":[146],"improves":[148],"long-term":[149],"prediction":[150],"performance.":[151],"can":[153],"be":[154],"integrated":[155],"Vision-Language":[157],"Models":[158],"(VLMs)":[159],"zero-shot":[161],"unseen":[164],"visual":[165],"domains.":[166],"Experiments":[167],"using":[168],"benchmark":[170],"datasets":[171],"show":[172],"ranks":[175],"first":[176],"VOTSt-2024,":[178],"Long":[179],"Dataset":[181],"LVOS,":[183],"second":[185],"VOTS-2024,":[187],"demonstrating":[188],"best":[190],"generalizability":[191],"state-of-the-art":[193],"performance":[194],"across":[195],"single-,":[196],"multi-,":[197],"tasks.":[201]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-04-08T00:00:00"}