{"id":"https://openalex.org/W7203885342","doi":"https://doi.org/10.48550/arxiv.2608.18640","title":"SAM2Dual: Training-Free, Dual Memory for Long-Term Video Object Segmentation","display_name":"SAM2Dual: Training-Free, Dual Memory for Long-Term Video Object Segmentation","publication_year":2026,"publication_date":"2026-08-19","ids":{"openalex":"https://openalex.org/W7203885342","doi":"https://doi.org/10.48550/arxiv.2608.18640"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.18640","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18640","pdf_url":"https://arxiv.org/pdf/2608.18640","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.18640","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147588309","display_name":"Jeongrae Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, JeongRae","raw_affiliation_strings":["Department of Applied Statistics , Chung-Ang University , Seoul 06974 , Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Statistics , Chung-Ang University , Seoul 06974 , Republic of Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047491479","display_name":"Changwon Lim","orcid":"https://orcid.org/0000-0002-3182-8420","observed_orcids":["https://orcid.org/0000-0002-3182-8420"]},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Lim, Changwon","raw_affiliation_strings":["Department of Applied Statistics , Chung-Ang University , Seoul 06974 , Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Statistics , Chung-Ang University , Seoul 06974 , Republic of Korea","institution_ids":["https://openalex.org/I67900169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I67900169"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.4758000075817108,"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":0.4758000075817108,"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":0.31790000200271606,"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":0.1062999963760376,"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/sam2","display_name":"SAM2","score":0.7839999794960022},{"id":"https://openalex.org/keywords/identity-preservation","display_name":"identity preservation","score":0.6499999761581421},{"id":"https://openalex.org/keywords/occlusion-robustness","display_name":"occlusion robustness","score":0.5569999814033508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473000288009644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6466000080108643},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6173999905586243},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5910999774932861},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.501800000667572},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4489000141620636},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4392000138759613},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3725999891757965},{"id":"https://openalex.org/C58632812","wikidata":"https://www.wikidata.org/wiki/Q7936625","display_name":"Visual short-term memory","level":4,"score":0.36250001192092896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C178278151","wikidata":"https://www.wikidata.org/wiki/Q7936607","display_name":"Visual memory","level":3,"score":0.33489999175071716},{"id":"https://openalex.org/C74426580","wikidata":"https://www.wikidata.org/wiki/Q719484","display_name":"Memory map","level":3,"score":0.3330000042915344},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C48455012","wikidata":"https://www.wikidata.org/wiki/Q2892593","display_name":"Memory consolidation","level":3,"score":0.29589998722076416},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.28690001368522644},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2687000036239624},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.2687000036239624}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.18640","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18640","pdf_url":"https://arxiv.org/pdf/2608.18640","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.18640","doi":"https://doi.org/10.48550/arxiv.2608.18640","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.18640","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.18640","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.18640","pdf_url":"https://arxiv.org/pdf/2608.18640","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203885342.pdf","grobid_xml":"https://content.openalex.org/works/W7203885342.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W4401307635","https://openalex.org/W4405354512","https://openalex.org/W4414271568","https://openalex.org/W4415250007","https://openalex.org/W7122474438","https://openalex.org/W7123905231"],"related_works":["https://openalex.org/W4404089453","https://openalex.org/W7204176378","https://openalex.org/W4412094182","https://openalex.org/W4414768931","https://openalex.org/W7128541684","https://openalex.org/W4416058268","https://openalex.org/W4387227326","https://openalex.org/W4400524898","https://openalex.org/W4415254644","https://openalex.org/W7151380282"],"abstract_inverted_index":{"Long-term":[0],"video":[1],"object":[2],"segmentation":[3],"(VOS)":[4],"remains":[5],"challenging":[6],"due":[7],"to":[8,81,112,144],"error":[9],"accumulation":[10],"under":[11],"extended":[12],"occlusions,":[13],"re-appearance,":[14],"and":[15,73,108,148],"scene":[16],"changes.":[17],"Although":[18],"SAM2":[19],"provides":[20],"strong":[21],"zero-shot":[22],"performance,":[23],"its":[24],"streaming":[25],"memory":[26,39,68,76,114],"can":[27],"amplify":[28],"drift":[29],"over":[30],"long":[31,138],"horizons":[32],"when":[33,123],"recent,":[34],"unreliable":[35],"predictions":[36],"dominate":[37],"the":[38],"state.":[40],"We":[41],"propose":[42],"SAM2Dual,":[43],"a":[44,59,88,101],"training-free,":[45],"plug-and-play":[46],"inference-time":[47],"enhancement":[48],"that":[49,63],"improves":[50,135],"long-video":[51],"robustness":[52],"without":[53],"updating":[54],"model":[55],"weights.":[56],"SAM2Dual":[57,133],"introduces":[58],"Dual":[60],"Memory":[61,97],"design":[62],"explicitly":[64],"separates":[65],"(i)":[66],"short-term":[67],"for":[69],"rapid":[70],"local":[71],"adaptation":[72],"(ii)":[74],"long-term":[75,131],"built":[77],"via":[78],"interval-based":[79],"sampling":[80],"preserve":[82],"global":[83],"identity":[84,121],"cues,":[85],"combined":[86],"through":[87],"gated":[89],"fusion":[90],"strategy.":[91],"In":[92],"addition,":[93],"we":[94],"present":[95],"Text-Aware":[96],"(TAM),":[98],"which":[99],"extracts":[100],"compact":[102],"word-level":[103],"cue":[104],"from":[105,142],"early":[106],"frames":[107],"uses":[109],"text":[110],"embeddings":[111],"reweight":[113],"contributions":[115],"based":[116],"on":[117,137,146,152],"semantic":[118],"compatibility,":[119],"supporting":[120],"preservation":[122],"visual":[124],"evidence":[125],"becomes":[126],"weak":[127],"or":[128],"ambiguous.":[129],"Across":[130],"benchmarks,":[132],"consistently":[134],"stability":[136],"videos,":[139],"raising":[140],"J&F":[141],"49.33":[143],"50.65":[145],"MOSEv2":[147],"achieving":[149],"consistent":[150],"gains":[151],"LVOSv2.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-22T00:00:00"}