{"id":"https://openalex.org/W7214765659","doi":"https://doi.org/10.48550/arxiv.2609.33338","title":"OPERA: A Unified Omnimodal Progressive Spatio-Temporal Reasoning Agent for Referring Video Segmentation","display_name":"OPERA: A Unified Omnimodal Progressive Spatio-Temporal Reasoning Agent for Referring Video Segmentation","publication_year":2026,"publication_date":"2026-09-27","ids":{"openalex":"https://openalex.org/W7214765659","doi":"https://doi.org/10.48550/arxiv.2609.33338"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.33338","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.33338","pdf_url":"https://arxiv.org/pdf/2609.33338","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/2609.33338","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113047851","display_name":"Jingchen Ni","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ni, Jingchen","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153465277","display_name":"Yuji Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Yuji","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153503441","display_name":"Shannan Yan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan, Shannan","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153548191","display_name":"Haoru Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Haoru","raw_affiliation_strings":["University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153474308","display_name":"Sitong Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Chen, Sitong","raw_affiliation_strings":["ETH Zurich {njc24 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich {njc24 ,","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153479504","display_name":"Chun Yuan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan, Chun","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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":9.999999747378752e-05,"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/multimodal-queries","display_name":"multimodal queries","score":0.8669999837875366},{"id":"https://openalex.org/keywords/spatio-temporal-reasoning","display_name":"spatio-temporal reasoning","score":0.7960000038146973},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7059999704360962},{"id":"https://openalex.org/keywords/cross-modal-understanding","display_name":"cross-modal understanding","score":0.6320000290870667},{"id":"https://openalex.org/keywords/key-frame-extraction","display_name":"key frame extraction","score":0.7689999938011169},{"id":"https://openalex.org/keywords/semantic-distillation","display_name":"semantic distillation","score":0.7310000061988831},{"id":"https://openalex.org/keywords/visual-grounding","display_name":"visual grounding","score":0.6000000238418579},{"id":"https://openalex.org/keywords/group-relative-policy-optimization","display_name":"Group Relative Policy Optimization","score":0.6159999966621399},{"id":"https://openalex.org/keywords/zero-shot-transfer","display_name":"zero-shot transfer","score":0.7229999899864197},{"id":"https://openalex.org/keywords/multimodal-video-understanding","display_name":"multimodal video understanding","score":0.37299999594688416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7409999966621399},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7001000046730042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.646399974822998},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5020999908447266},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4984999895095825},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42260000109672546},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3856000006198883},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.2815999984741211},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C74992021","wikidata":"https://www.wikidata.org/wiki/Q184876","display_name":"Frame of reference","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.33338","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.33338","pdf_url":"https://arxiv.org/pdf/2609.33338","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.2609.33338","doi":"https://doi.org/10.48550/arxiv.2609.33338","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.33338","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:2609.33338","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.33338","pdf_url":"https://arxiv.org/pdf/2609.33338","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/W7214765659.pdf","grobid_xml":"https://content.openalex.org/works/W7214765659.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W4387389147","https://openalex.org/W4390489648","https://openalex.org/W4391272787","https://openalex.org/W4401200977","https://openalex.org/W4401307635","https://openalex.org/W4403963980","https://openalex.org/W4406301628","https://openalex.org/W4406317056","https://openalex.org/W4409051416","https://openalex.org/W4415255153","https://openalex.org/W4416854066","https://openalex.org/W6948125184","https://openalex.org/W6948369276","https://openalex.org/W6967068517","https://openalex.org/W7102705475","https://openalex.org/W7111262633","https://openalex.org/W7125390417","https://openalex.org/W7138888486","https://openalex.org/W7141256605","https://openalex.org/W7163130651","https://openalex.org/W7163343312","https://openalex.org/W7172399305"],"related_works":["https://openalex.org/W4315473428","https://openalex.org/W4414603932","https://openalex.org/W7140288963","https://openalex.org/W6979246345","https://openalex.org/W3178075329","https://openalex.org/W4393178550","https://openalex.org/W7147631872","https://openalex.org/W7127647486","https://openalex.org/W6929540842","https://openalex.org/W4416257398"],"abstract_inverted_index":{"Referring":[0],"video":[1,122],"segmentation":[2,123],"with":[3,89,96],"heterogeneous":[4],"multimodal":[5],"queries---spanning":[6],"text,":[7],"audio,":[8],"and":[9,16,84,114,116],"reference":[10],"images---demands":[11],"both":[12],"robust":[13],"cross-modal":[14,81],"understanding":[15],"precise":[17],"spatio-temporal":[18],"reasoning.":[19],"We":[20],"propose":[21],"OPERA":[22,104],"(Omnimodal":[23],"Progressive":[24],"spatio-tEmporal":[25],"Reasoning":[26,52],"Agent),":[27],"a":[28,34,50,73,85,106],"unified":[29],"reasoning":[30,41],"agent":[31],"built":[32],"on":[33,112],"single":[35],"MLLM":[36],"that":[37],"performs":[38],"dual-axis":[39],"progressive":[40],"via":[42,80],"three":[43],"specialized":[44],"stages.":[45],"Along":[46,69],"the":[47,55,64,70,93,101,110],"temporal":[48],"axis,":[49,72],"Temporal":[51],"Agent":[53,75,87],"narrows":[54],"frame":[56],"search":[57],"space":[58],"through":[59],"coarse-to-fine":[60],"filtering":[61],"to":[62,78,119],"identify":[63],"most":[65],"informative":[66],"key":[67],"frame.":[68],"spatial":[71],"Distillation":[74],"establishes":[76],"what":[77],"locate":[79],"semantic":[82],"distillation,":[83],"Grounding":[86],"enhanced":[88],"GRPO":[90],"determines":[91],"where":[92],"target":[94],"appears,":[95],"dense":[97],"mask":[98],"propagation":[99],"completing":[100],"pixel-level":[102],"output.":[103],"sets":[105],"new":[107],"state":[108],"of":[109],"art":[111],"OmniAVS":[113],"Ref-AVS":[115],"transfers":[117],"zero-shot":[118],"standard":[120],"referring":[121],"benchmarks.":[124]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}