{"id":"https://openalex.org/W7140201756","doi":"https://doi.org/10.48550/arxiv.2603.20422","title":"PEARL: Personalized Streaming Video Understanding Model","display_name":"PEARL: Personalized Streaming Video Understanding Model","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W7140201756","doi":"https://doi.org/10.48550/arxiv.2603.20422"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.20422","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20422","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.20422","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zheng, Yuanhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zheng, Yuanhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"An, Ruichuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"An, Ruichuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lin, Xiaopeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Xiaopeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Yuxing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yuxing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yang, Sihan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Sihan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Huanyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Huanyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Haodong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Haodong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Qintong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Qintong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Renrui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Renrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Guopeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Guopeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Yifan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Yuheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yuheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Zhang, Wentao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wentao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":13,"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":0.8859000205993652,"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":0.8859000205993652,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0210999995470047,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.010300000198185444,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.6895999908447266},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.46299999952316284},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4562000036239624},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4269999861717224},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.37380000948905945},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3677000105381012},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.36230000853538513},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.33959999680519104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8389000296592712},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.6895999908447266},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4562000036239624},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4269999861717224},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42089998722076416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39259999990463257},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.20422","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20422","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.20422","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20422","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"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":{"Human":[0],"cognition":[1],"of":[2,74,166],"new":[3,13,85,176],"concepts":[4,110],"is":[5,246],"inherently":[6],"a":[7,103,121,131,163,182,189,221],"streaming":[8,241],"process:":[9],"we":[10,65,87,178],"continuously":[11],"recognize":[12],"objects":[14],"or":[15,34,124],"identities":[16],"and":[17,68,129,147,156,169,197,224,236],"update":[18],"our":[19],"memories":[20],"over":[21],"time.":[22],"However,":[23],"current":[24],"multimodal":[25],"personalization":[26,235],"methods":[27],"are":[28,159],"largely":[29],"limited":[30],"to":[31,49,96,106,108,214,219],"static":[32],"images":[33],"offline":[35,196],"videos.":[36],"This":[37],"disconnects":[38],"continuous":[39,140],"visual":[40],"input":[41],"from":[42],"instant":[43],"real-world":[44],"feedback,":[45],"limiting":[46],"their":[47],"ability":[48,105],"provide":[50],"the":[51,71,90],"real-time,":[52],"interactive":[53],"personalized":[54,109,136,242],"responses":[55],"essential":[56],"for":[57],"future":[58],"AI":[59,243],"assistants.":[60,244],"To":[61,80,172],"bridge":[62],"this":[63,84,98,174,229],"gap,":[64],"first":[66,91],"propose":[67,180],"formally":[69],"define":[70],"novel":[72,132],"task":[73],"Personalized":[75],"Streaming":[76],"Video":[77],"Understanding":[78],"(PSVU).":[79],"facilitate":[81],"research":[82,239],"in":[83,126],"direction,":[86],"introduce":[88],"PEARL-Bench,":[89],"comprehensive":[92],"benchmark":[93],"designed":[94],"specifically":[95],"evaluate":[97],"challenging":[99,175],"setting.":[100],"It":[101],"evaluates":[102],"model's":[104],"respond":[107],"at":[111,248],"exact":[112],"timestamps":[113],"under":[114],"two":[115],"modes:":[116],"(1)":[117],"Frame-level,":[118],"focusing":[119,134],"on":[120,135],"specific":[122],"person":[123],"object":[125],"discrete":[127],"frames,":[128],"(2)":[130],"Video-level,":[133],"actions":[137],"unfolding":[138],"across":[139,194],"frames.":[141],"PEARL-Bench":[142],"comprises":[143],"132":[144],"unique":[145],"videos":[146],"2,173":[148],"fine-grained":[149],"annotations":[150],"with":[151],"precise":[152],"timestamps.":[153],"Concept":[154],"diversity":[155],"annotation":[157],"quality":[158],"strictly":[160],"ensured":[161],"through":[162],"combined":[164],"pipeline":[165],"automated":[167],"generation":[168],"human":[170],"verification.":[171],"tackle":[173],"setting,":[177],"further":[179,238],"PEARL,":[181],"plug-and-play,":[183],"training-free":[184],"strategy":[185],"that":[186,201],"serves":[187],"as":[188],"strong":[190],"baseline.":[191],"Extensive":[192],"evaluations":[193],"8":[195],"online":[198],"models":[199],"demonstrate":[200],"PEARL":[202],"achieves":[203],"state-of-the-art":[204],"performance.":[205],"Notably,":[206],"it":[207],"brings":[208],"consistent":[209],"PSVU":[210],"improvements":[211],"when":[212],"applied":[213],"3":[215],"distinct":[216],"architectures,":[217],"proving":[218],"be":[220],"highly":[222],"effective":[223],"robust":[225],"strategy.":[226],"We":[227],"hope":[228],"work":[230],"advances":[231],"vision-language":[232],"model":[233],"(VLM)":[234],"inspires":[237],"into":[240],"Code":[245],"available":[247],"https://github.com/Yuanhong-Zheng/PEARL.":[249]},"counts_by_year":[],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2026-03-25T00:00:00"}
