{"id":"https://openalex.org/W7202344115","doi":"https://doi.org/10.48550/arxiv.2608.11458","title":"Multi-Agent Target-Existence Verification and Learned Mask Geometry Refinement: Winning Report of the MeViS-Text Track at the 8th LSVOS Challenge 2026","display_name":"Multi-Agent Target-Existence Verification and Learned Mask Geometry Refinement: Winning Report of the MeViS-Text Track at the 8th LSVOS Challenge 2026","publication_year":2026,"publication_date":"2026-08-11","ids":{"openalex":"https://openalex.org/W7202344115","doi":"https://doi.org/10.48550/arxiv.2608.11458"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.11458","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.11458","pdf_url":"https://arxiv.org/pdf/2608.11458","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/2608.11458","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140611882","display_name":"Jungyoon Lee","orcid":"https://orcid.org/0009-0001-0240-4741","observed_orcids":["https://orcid.org/0009-0001-0240-4741"]},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Lee, Jungyoon","raw_affiliation_strings":["Department of AI Convergence Security , Soongsil University , Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of AI Convergence Security , Soongsil University , Republic of Korea","institution_ids":["https://openalex.org/I141371507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147064885","display_name":"Gyuil Lim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Lim, Gyuil","raw_affiliation_strings":["Department of AI Convergence , Soongsil University , Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of AI Convergence , Soongsil University , Republic of Korea","institution_ids":["https://openalex.org/I141371507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147087040","display_name":"Doeon Kim","orcid":"https://orcid.org/0009-0006-3187-4503","observed_orcids":["https://orcid.org/0009-0006-3187-4503"]},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Doeon","raw_affiliation_strings":["Department of Intelligent Semiconductors , Soongsil University , Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligent Semiconductors , Soongsil University , Republic of Korea","institution_ids":["https://openalex.org/I141371507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140738613","display_name":"Seong-heum Kim","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Seong-heum","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8711000084877014,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8711000084877014,"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":0.06639999896287918,"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":0.016499999910593033,"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/referring-video-object-segmentation","display_name":"referring video object segmentation","score":0.9200000166893005},{"id":"https://openalex.org/keywords/multi-agent-reasoning","display_name":"multi-agent reasoning","score":0.8619999885559082},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9319999814033508},{"id":"https://openalex.org/keywords/segment-anything-model","display_name":"Segment Anything Model","score":0.6430000066757202}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7042999863624573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6783999800682068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6373000144958496},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6360999941825867},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.579800009727478},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5702000260353088},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.49630001187324524},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4018000066280365},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3686999976634979},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26989999413490295},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.2685999870300293},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.11458","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.11458","pdf_url":"https://arxiv.org/pdf/2608.11458","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.2608.11458","doi":"https://doi.org/10.48550/arxiv.2608.11458","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.11458","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:2608.11458","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.11458","pdf_url":"https://arxiv.org/pdf/2608.11458","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":[{"id":"https://openalex.org/G2518375081","display_name":null,"funder_award_id":"RS-2025-25441317","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3086070586","display_name":null,"funder_award_id":"IITP-2024 2024-RS-2024-00426853","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G7348717967","display_name":null,"funder_award_id":"RS-2024-00426853","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321681","display_name":"Ministry of Trade, Industry and Energy","ror":"https://ror.org/008nkqk13"},{"id":"https://openalex.org/F4320322064","display_name":"Korea Institute for Advancement of Technology","ror":"https://ror.org/015w1qa96"},{"id":"https://openalex.org/F4320322065","display_name":"National IT Industry Promotion Agency","ror":"https://ror.org/026v53e29"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7202344115.pdf","grobid_xml":"https://content.openalex.org/works/W7202344115.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W4413344259","https://openalex.org/W4415250007","https://openalex.org/W6910554155","https://openalex.org/W7140288963","https://openalex.org/W7148504510"],"related_works":["https://openalex.org/W7202213665","https://openalex.org/W7148504510","https://openalex.org/W7147125555","https://openalex.org/W2912290468","https://openalex.org/W4402698545","https://openalex.org/W2793407941","https://openalex.org/W7212028458","https://openalex.org/W7204214343","https://openalex.org/W4409603708","https://openalex.org/W7203449210"],"abstract_inverted_index":{"We":[0],"present":[1],"the":[2,6,10,37,79,101,129,145,158,205,217,232,238,256],"first-place":[3],"solution":[4],"to":[5],"MeViS-Text":[7],"track":[8],"of":[9,108,157,204,220,237,253],"8th":[11],"Large-scale":[12],"Video":[13],"Object":[14],"Segmentation":[15],"(LSVOS)":[16],"Challenge":[17],"2026:":[18],"referring":[19],"video":[20,38],"object":[21,35,124],"segmentation":[22,198],"guided":[23],"by":[24,180,227],"written":[25],"motion":[26,178],"expressions,":[27],"including":[28],"deceptive":[29],"no-target":[30,97,110,193,207],"expressions":[31],"that":[32,104,118,170,230],"match":[33],"no":[34],"in":[36,44,99],"and":[39,63,125,136,167,183],"must":[40],"yield":[41],"empty":[42],"masks":[43],"every":[45,68,96,224],"frame.":[46],"Our":[47],"pipeline,":[48],"SSUPER,":[49],"resolves":[50],"each":[51],"expression":[52,98],"into":[53,152],"a":[54,84,105,122,141,192,250],"visual":[55],"concept,":[56],"generates":[57],"full-video":[58],"candidate":[59],"masklets":[60],"with":[61,216],"SAM~3.1,":[62],"selects":[64],"target":[65],"IDs.":[66],"At":[67],"reasoning":[69],"stage,":[70],"three":[71],"heterogeneous":[72],"multimodal":[73],"large":[74],"language":[75],"models":[76],"independently":[77],"execute":[78],"same":[80],"stage-specific":[81],"prompt":[82],"before":[83],"single":[85],"synthesis":[86],"pass":[87],"commits":[88],"one":[89],"schema-validated":[90],"verdict.":[91,146,194],"Although":[92],"this":[93,200],"system":[94,248],"rejects":[95],"validation,":[100],"leaderboard":[102],"reveals":[103],"substantial":[106],"share":[107],"test":[109],"cases":[111],"still":[112],"slips":[113],"through.":[114],"The":[115,246],"reason":[116],"is":[117,241],"hard":[119],"negatives":[120],"name":[121],"plausible":[123],"fail":[126],"only":[127],"under":[128],"complete":[130,247],"temporal":[131],"predicate,":[132],"so":[133],"when":[134],"selection":[135],"existence":[137,150],"are":[138,234],"decided":[139],"together,":[140],"category-plausible":[142],"masklet":[143],"anchors":[144],"Hence,":[147],"we":[148],"decouple":[149],"verification":[151],"an":[153],"independent":[154],"multi-agent":[155],"audit":[156,201],"full":[159],"predicate":[160],"(category,":[161],"count,":[162],"action,":[163],"trajectory,":[164],"event":[165],"order,":[166],"semantic":[168],"role)":[169],"distinguishes":[171],"absence":[172],"from":[173],"temporary":[174],"invisibility,":[175],"discounts":[176],"apparent":[177],"caused":[179],"camera":[181],"movement,":[182],"requires":[184],"contradicting":[185],"evidence":[186],"rather":[187,243],"than":[188,244],"mere":[189],"uncertainty":[190],"for":[191],"Without":[195],"any":[196],"new":[197],"call,":[199],"recovers":[202],"most":[203],"residual":[206],"errors.":[208],"A":[209],"training-data-only":[210],"StyleRefiner":[211],"then":[212],"aligns":[213],"mask":[214],"geometry":[215],"annotation":[218],"style":[219],"MeViSv2":[221],"while":[222],"preserving":[223],"presence":[225],"decision":[226],"construction,":[228],"showing":[229],"once":[231],"semantics":[233],"fixed,":[235],"part":[236],"remaining":[239],"error":[240],"stylistic":[242],"semantic.":[245],"reaches":[249],"Final":[251],"score":[252],"0.9081339614":[254],"on":[255],"official":[257],"challenge":[258],"leaderboard.":[259]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-14T00:00:00"}