{"id":"https://openalex.org/W7163917636","doi":"https://doi.org/10.48550/arxiv.2606.06819","title":"VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation","display_name":"VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation","publication_year":2026,"publication_date":"2026-06-05","ids":{"openalex":"https://openalex.org/W7163917636","doi":"https://doi.org/10.48550/arxiv.2606.06819"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.06819","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06819","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.06819","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138142348","display_name":"Ming Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Ming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138145661","display_name":"Sen Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Sen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138148651","display_name":"Boqiang Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duan, Boqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138139987","display_name":"Boyuan Tong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong, Boyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004604326","display_name":"Jiedong Zhuang","orcid":"https://orcid.org/0000-0003-0551-5911"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Jiedong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138189480","display_name":"Wankou Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Wankou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138141972","display_name":"Jingdong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jingdong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.757099986076355,"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":0.757099986076355,"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":0.1679999977350235,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.013000000268220901,"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/segmentation","display_name":"Segmentation","score":0.6115000247955322},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5748999714851379},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5533000230789185},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5246000289916992},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5170999765396118},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42149999737739563},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.37439998984336853},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3578000068664551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7430999875068665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6563000082969666},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6115000247955322},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5748999714851379},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5533000230789185},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5246000289916992},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5170999765396118},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42149999737739563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41359999775886536},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3578000068664551},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.29580000042915344},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29100000858306885},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.27559998631477356},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26589998602867126},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C107848011","wikidata":"https://www.wikidata.org/wiki/Q4680756","display_name":"Adaptive reasoning","level":4,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.06819","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06819","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.06819","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06819","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reasoning":[0],"Video":[1],"Object":[2],"Segmentation":[3],"(RVOS)":[4],"demands":[5],"a":[6,78,130,149],"sophisticated":[7],"integration":[8],"of":[9,106],"temporal":[10],"dynamics,":[11],"spatial":[12],"details,":[13],"and":[14,32,91,143,146,159],"linguistic":[15,144],"reasoning":[16,27,138,155],"to":[17,26,36,82,94,98,134],"achieve":[18],"precise":[19],"pixel-level":[20],"localization.":[21],"Existing":[22],"methods":[23],"are":[24],"limited":[25],"over":[28],"fixed":[29],"initial":[30],"inputs":[31],"lack":[33],"the":[34,61,71,96,109,124,137],"capacity":[35],"actively":[37],"acquire":[38],"further":[39],"visual":[40],"evidence,":[41],"which":[42,117],"is":[43],"often":[44],"essential":[45],"for":[46,67],"resolving":[47],"complex":[48],"references":[49],"in":[50],"long":[51],"or":[52],"intricate":[53],"videos.":[54],"To":[55],"address":[56],"this,":[57],"we":[58,112,128],"propose":[59],"\\textbf{VideoSEG-O3},":[60],"first":[62],"multi-turn":[63],"reinforcement":[64],"learning":[65],"framework":[66],"RVOS":[68],"that":[69],"emulates":[70],"human":[72],"\\textit{``coarse-to-fine''}":[73],"cognitive":[74],"process.":[75],"It":[76],"employs":[77],"\\textit{multi-turn":[79],"temporal-spatial":[80],"chain-of-thought}":[81],"capture":[83],"fine-grained":[84],"details":[85],"by":[86],"iteratively":[87],"pinpointing":[88],"critical":[89],"intervals":[90],"keyframes.":[92],"Additionally,":[93],"enable":[95],"policy":[97],"perceive":[99],"segmentation":[100,120],"quality":[101],"beyond":[102],"mere":[103],"text":[104],"probability":[105],"\\texttt{[SEG]}":[107],"during":[108],"RL":[110],"stage,":[111],"introduce":[113],"\\textit{SEG-aware":[114],"logit":[115],"calibration},":[116],"integrates":[118],"pixel-wise":[119],"feedback":[121],"directly":[122],"into":[123,140],"token-level":[125],"logits.":[126],"Furthermore,":[127],"design":[129],"\\textit{decoupled":[131],"thinking":[132],"trace}":[133],"hierarchically":[135],"decompose":[136],"process":[139],"temporal,":[141],"spatial,":[142],"dimensions,":[145],"construct":[147],"\\textbf{VTS-CoT},":[148],"specialized":[150],"cold-start":[151],"dataset":[152],"featuring":[153],"comprehensive":[154],"trajectories.":[156],"The":[157],"code":[158],"models":[160],"will":[161],"be":[162],"released":[163],"at":[164],"https://github.com/Dmmm1997/VideoSEG-O3.":[165]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-09T00:00:00"}