{"id":"https://openalex.org/W4417155826","doi":"https://doi.org/10.1109/iccv51701.2025.02165","title":"PVChat: Personalized Video Chat with One-Shot Learning","display_name":"PVChat: Personalized Video Chat with One-Shot Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417155826","doi":"https://doi.org/10.1109/iccv51701.2025.02165"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02165","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.17069","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089019283","display_name":"Yufei Shi","orcid":"https://orcid.org/0000-0002-6999-0191"},"institutions":[{"id":"https://openalex.org/I4210133058","display_name":"Medvis (United States)","ror":"https://ror.org/03hhmg705","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133058"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yufei Shi","raw_affiliation_strings":["MedVisAI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MedVisAI Lab","institution_ids":["https://openalex.org/I4210133058"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111316052","display_name":"Weilong Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weilong Yan","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100946299","display_name":"Gang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gang Xu","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100775183","display_name":"Yumeng Li","orcid":"https://orcid.org/0000-0002-5562-1707"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yumeng Li","raw_affiliation_strings":["Nankai University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100773473","display_name":"Yu\u2010Cheng Chen","orcid":"https://orcid.org/0000-0003-1696-4667"},"institutions":[{"id":"https://openalex.org/I4210133058","display_name":"Medvis (United States)","ror":"https://ror.org/03hhmg705","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133058"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yucheng Chen","raw_affiliation_strings":["MedVisAI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MedVisAI Lab","institution_ids":["https://openalex.org/I4210133058"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064468010","display_name":"Z. Y. Li","orcid":"https://orcid.org/0000-0002-4652-9845"},"institutions":[{"id":"https://openalex.org/I4210133058","display_name":"Medvis (United States)","ror":"https://ror.org/03hhmg705","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133058"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenxi Li","raw_affiliation_strings":["MedVisAI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MedVisAI Lab","institution_ids":["https://openalex.org/I4210133058"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420016","display_name":"F. Richard Yu","orcid":"https://orcid.org/0000-0003-1006-7594"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Yu","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351330","display_name":"Ming Li","orcid":"https://orcid.org/0000-0001-7430-4961"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108170273","display_name":"Si Yong Yeo","orcid":"https://orcid.org/0000-0001-6403-6019"},"institutions":[{"id":"https://openalex.org/I4210133058","display_name":"Medvis (United States)","ror":"https://ror.org/03hhmg705","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133058"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Si Yong Yeo","raw_affiliation_strings":["MedVisAI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MedVisAI Lab","institution_ids":["https://openalex.org/I4210133058"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5089019283"],"corresponding_institution_ids":["https://openalex.org/I4210133058"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3727853,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23321","last_page":"23331"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9824000000953674,"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":0.9824000000953674,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0024999999441206455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10028","display_name":"Topic Modeling","score":0.002300000051036477,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/pipeline","display_name":"Pipeline (software)","score":0.5990999937057495},{"id":"https://openalex.org/keywords/personalized-learning","display_name":"Personalized learning","score":0.5622000098228455},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5004000067710876},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4993000030517578},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4392000138759613},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.43540000915527344},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.4058000147342682},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.39259999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8413000106811523},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5990999937057495},{"id":"https://openalex.org/C142039133","wikidata":"https://www.wikidata.org/wiki/Q3620943","display_name":"Personalized learning","level":5,"score":0.5622000098228455},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5234000086784363},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5004000067710876},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4993000030517578},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4392000138759613},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42750000953674316},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.39259999990463257},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32850000262260437},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2833999991416931},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2816999852657318},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2597000002861023}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02165","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.17069","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.17069","pdf_url":"https://arxiv.org/pdf/2503.17069","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2503.17069","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.17069","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.17069","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.17069","pdf_url":"https://arxiv.org/pdf/2503.17069","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"large":[1],"language":[2],"models":[3],"(ViLLMs)":[4],"excel":[5],"in":[6,37,206],"general":[7],"video":[8,68,110,175],"understanding,":[9],"e.g.,":[10],"recognizing":[11],"activities":[12],"like":[13],"talking":[14],"and":[15,40,104,124,154,200],"eating,":[16],"but":[17],"struggle":[18],"with":[19,32,117],"identity-aware":[20],"comprehension,":[21],"such":[22],"as":[23],"\"Wilson":[24],"is":[25,30],"receiving":[26],"chemotherapy\"":[27],"or":[28],"\"Tom":[29],"discussing":[31],"Sarah\",":[33],"limiting":[34],"their":[35],"applicability":[36],"smart":[38,41],"healthcare":[39],"home":[42],"environments.":[43],"To":[44,127],"address":[45],"this":[46],"limitation,":[47],"we":[48,93,131,164],"propose":[49,132],"a":[50,66,75,81,87,113,133,166,178,213],"one-shot":[51],"learning":[52,90,149,180,211],"framework":[53],"PVChat,":[54],"the":[55],"first":[56],"personalized":[57,207],"ViLLM":[58,79],"that":[59,99],"enables":[60],"subject-aware":[61],"question":[62],"answering":[63],"(QA)":[64],"from":[65,108,171,182,212],"single":[67,214],"for":[69,147,159],"each":[70],"subject.":[71],"Our":[72],"approach":[73],"optimizes":[74],"Mixture-of-Heads":[76],"(MoH)":[77],"enhanced":[78],"on":[80,191],"synthetically":[82],"augmented":[83],"video-QA":[84],"dataset,":[85],"leveraging":[86],"progressive":[88,148],"image-to-video":[89],"strategy.":[91],"Specifically,":[92],"introduce":[94],"an":[95],"automated":[96],"augmentation":[97],"pipeline":[98],"synthesizes":[100],"identity-preserving":[101],"positive":[102],"samples":[103],"retrieves":[105],"hard":[106],"negatives":[107],"existing":[109],"corpora,":[111],"generating":[112],"diverse":[114,192],"training":[115,168],"dataset":[116],"four":[118],"QA":[119],"types:":[120],"existence,":[121],"appearance,":[122],"action,":[123],"location":[125],"inquiries.":[126],"enhance":[128],"subject-specific":[129],"learning,":[130],"ReLU":[134],"Routing":[135],"MoH":[136],"attention":[137,161],"mechanism,":[138],"alongside":[139],"two":[140],"novel":[141],"objectives:":[142],"(1)":[143],"Smooth":[144],"Proximity":[145],"Regularization":[146],"through":[150],"exponential":[151],"distance":[152],"scaling":[153],"(2)":[155],"Head":[156],"Activation":[157],"Enhancement":[158],"balanced":[160],"routing.":[162],"Finally,":[163],"adopt":[165],"two-stage":[167],"strategy,":[169],"transitioning":[170],"image":[172],"pre-training":[173],"to":[174,185,217],"fine-tuning,":[176],"enabling":[177],"gradual":[179],"process":[181],"static":[183],"attributes":[184],"dynamic":[186],"representations.":[187],"We":[188],"evaluate":[189],"PVChat":[190],"datasets":[193],"covering":[194],"medical":[195],"scenarios,":[196],"TV":[197],"series,":[198],"anime,":[199],"real-world":[201],"footage,":[202],"demonstrating":[203],"its":[204],"superiority":[205],"feature":[208],"understanding":[209],"after":[210],"video,":[215],"compared":[216],"state-of-the-art":[218],"ViLLMs.":[219]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}