{"id":"https://openalex.org/W7133357273","doi":"https://doi.org/10.1109/tpami.2026.3669976","title":"Causal Prompts for Open-Vocabulary Video Instance Segmentation","display_name":"Causal Prompts for Open-Vocabulary Video Instance Segmentation","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133357273","doi":"https://doi.org/10.1109/tpami.2026.3669976","pmid":"https://pubmed.ncbi.nlm.nih.gov/41774585"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3669976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3669976","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086263174","display_name":"Rongkun Zheng","orcid":"https://orcid.org/0000-0002-7860-2023"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Rongkun Zheng","raw_affiliation_strings":["School of Computing and Data Science, The University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0000-8508-7325","affiliations":[{"raw_affiliation_string":"School of Computing and Data Science, The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126539281","display_name":"Lu Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Qi","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127982779","display_name":"Xi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":["School of Computing and Data Science, The University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0008-5008-4720","affiliations":[{"raw_affiliation_string":"School of Computing and Data Science, The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102730412","display_name":"Yuyi Wang","orcid":"https://orcid.org/0000-0001-7273-9873"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Wang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9134-1203","affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128028521","display_name":"Kun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Wang","raw_affiliation_strings":["SenseTime Research, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Shanghai, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127977062","display_name":"Yu Qiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Qiao","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1889-2567","affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128016392","display_name":"Hengshuang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hengshuang Zhao","raw_affiliation_strings":["School of Computing and Data Science, The University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-8277-2706","affiliations":[{"raw_affiliation_string":"School of Computing and Data Science, The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26977291,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"7","first_page":"8429","last_page":"8443"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5914999842643738,"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":0.5914999842643738,"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/T11439","display_name":"Video Analysis and Summarization","score":0.11509999632835388,"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":0.04270000010728836,"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":0.6593999862670898},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.539900004863739},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.42239999771118164},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3952000141143799},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3700000047683716},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.3668000102043152},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3488999903202057},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.34880000352859497},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.3474999964237213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8032000064849854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7317000031471252},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6593999862670898},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.539900004863739},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43070000410079956},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.42239999771118164},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.358599990606308},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3488999903202057},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3474999964237213},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.337799996137619},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3287000060081482},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31619998812675476},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.26100000739097595},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3669976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3669976","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41774585","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41774585","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5776740908622742}],"awards":[{"id":"https://openalex.org/G1018712551","display_name":null,"funder_award_id":"62422606","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5621902803","display_name":null,"funder_award_id":"624B2124","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"Video":[1],"Instance":[2],"Segmentation":[3],"addresses":[4],"the":[5,140,180],"challenging":[6,160],"task":[7],"of":[8,183],"detecting,":[9],"segmenting,":[10],"and":[11,60,69,109,138,149,162],"tracking":[12,150],"objects":[13],"in":[14,152,187,191],"videos,":[15],"including":[16],"categories":[17],"not":[18],"encountered":[19],"during":[20],"training.":[21],"However,":[22],"existing":[23,172],"approaches":[24],"often":[25],"overlook":[26],"rich":[27],"temporal":[28,67],"cues":[29],"from":[30,63],"preceding":[31],"frames,":[32],"limiting":[33],"their":[34],"ability":[35],"to":[36,105,120,132,145],"leverage":[37],"causal":[38,56,184],"context":[39],"for":[40],"robust":[41],"open-world":[42,192],"generalization.":[43],"To":[44],"bridge":[45],"this":[46],"gap,":[47],"we":[48,126],"propose":[49],"CPOVIS,":[50],"a":[51,74,78,97,111,128],"novel":[52],"framework":[53],"that":[54,101,115],"introduces":[55],"prompts-dynamically":[57],"propagated":[58],"visual":[59],"taxonomy":[61],"prompts":[62],"historical":[64],"frames-to":[65],"enhance":[66],"reasoning":[68],"semantic":[70,118],"consistency.":[71],"Built":[72],"upon":[73],"Mask2Former":[75],"architecture":[76],"with":[77],"CLIP":[79],"backbone,":[80],"CPOVIS":[81],"integrates":[82],"three":[83],"core":[84],"innovations:":[85],"1)":[86],"PromptCLIP,":[87],"which":[88],"aligns":[89],"cross-modal":[90],"embeddings":[91],"while":[92],"preserving":[93],"open-vocabulary":[94,147,153],"capabilities;":[95],"2)":[96],"Visual":[98],"Prompt":[99,113],"Injector":[100],"propagates":[102],"object-level":[103],"features":[104],"maintain":[106],"spatial-temporal":[107],"coherence;":[108],"3)":[110],"Taxonomy":[112],"Infuser":[114],"leverages":[116],"hierarchical":[117],"relationships":[119],"stabilize":[121],"unseen":[122],"category":[123],"recognition.":[124],"Furthermore,":[125],"introduce":[127],"contrastive":[129],"learning":[130],"strategy":[131],"disentangle":[133],"object":[134],"representations":[135],"across":[136],"frames":[137],"adapt":[139],"Segment":[141],"Anything":[142],"Model":[143],"(SAM2)":[144],"boost":[146],"segmentation":[148,165],"capacity":[151],"video":[154,164,189],"scenarios.":[155,193],"Extensive":[156],"experiments":[157],"on":[158],"seven":[159],"open-":[161],"closed-vocabulary":[163],"benchmarks":[166],"demonstrate":[167],"CPOVIS's":[168],"state-of-the-art":[169],"performance,":[170],"outperforming":[171],"methods":[173],"by":[174],"significant":[175],"margins.":[176],"Our":[177],"findings":[178],"highlight":[179],"critical":[181],"role":[182],"prompt":[185],"propagation":[186],"advancing":[188],"understanding":[190]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-04T00:00:00"}