{"id":"https://openalex.org/W4413145364","doi":"https://doi.org/10.1109/cvpr52734.2025.00360","title":"VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by VIdeo SpatioTemporal Augmentation","display_name":"VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by VIdeo SpatioTemporal Augmentation","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145364","doi":"https://doi.org/10.1109/cvpr52734.2025.00360"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5115003662","display_name":"Weiming Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Weiming Ren","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115597396","display_name":"Huan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I2799847335","display_name":"Art Institute of Portland","ror":"https://ror.org/01cb0jg64","country_code":"US","type":"education","lineage":["https://openalex.org/I2799847335","https://openalex.org/I2799969541"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huan Yang","raw_affiliation_strings":["01.AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"01.AI","institution_ids":["https://openalex.org/I2799847335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023748712","display_name":"Jie Min","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jie Min","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118092803","display_name":"Cong Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Cong Wei","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wenhu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Wenhu Chen","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"3804","last_page":"3814"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9944999814033508,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9944999814033508,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9927999973297119,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9887999892234802,"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/duration","display_name":"Duration (music)","score":0.8166887760162354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7257190942764282}],"concepts":[{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.8166887760162354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7257190942764282},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2348837382","https://openalex.org/W746329893","https://openalex.org/W4205872570","https://openalex.org/W4245971243","https://openalex.org/W1922805944","https://openalex.org/W4253588120","https://openalex.org/W2383732295"],"abstract_inverted_index":{"Current":[0],"large":[1],"multimodal":[2],"models":[3,148],"(LMMs)":[4],"face":[5],"significant":[6],"challenges":[7],"in":[8,120],"processing":[9],"and":[10,50,61,73,76,97,108],"comprehending":[11],"long-duration":[12,49,107],"or":[13],"high-resolution":[14,51,109,139],"videos,":[15],"which":[16,145],"is":[17],"mainly":[18],"due":[19],"to":[20,65,82],"the":[21,136,157],"lack":[22],"of":[23,124,159],"high-quality":[24],"datasets.":[25,58],"To":[26],"address":[27],"this":[28,89],"issue":[29],"from":[30,55],"a":[31,39,100,150],"Average":[32],"Accuracy":[33],"data-centric":[34],"perspective,":[35],"we":[36,91,134],"propose":[37],"VISTA,":[38],"simple":[40],"yet":[41],"effective":[42],"VIdeo":[43],"SpatioTemporal":[44],"Augmentation":[45],"framework":[46],"that":[47],"synthesizes":[48],"video":[52,94,101,110,114,140],"instruction-following":[53,102],"pairs":[54,80],"existing":[56],"video-caption":[57],"VISTA":[59],"spatially":[60],"temporally":[62],"combines":[63],"videos":[64,69],"create":[66],"new":[67],"synthetic":[68],"with":[70],"extended":[71],"durations":[72],"enhanced":[74],"resolutions,":[75],"subsequently":[77],"produces":[78],"question-answer":[79],"pertaining":[81],"these":[83],"newly":[84],"synthesized":[85],"videos.":[86],"Based":[87],"on":[88,116,144],"paradigm,":[90],"develop":[92],"seven":[93],"augmentation":[95],"methods":[96],"curate":[98],"VISTA-400K,":[99],"dataset":[103],"aimed":[104],"at":[105],"enhancing":[106],"understanding.":[111,132],"Finetuning":[112],"various":[113],"LMMs":[115],"our":[117,146,160],"data":[118],"resulted":[119],"an":[121],"average":[122],"improvement":[123],"3.3%":[125],"across":[126],"four":[127],"challenging":[128],"benchmarks":[129],"for":[130],"long-video":[131],"Furthermore,":[133],"introduce":[135],"first":[137],"comprehensive":[138],"understanding":[141],"benchmark":[142],"HRVideoBench,":[143],"finetuned":[147],"achieve":[149],"6.5%":[151],"performance":[152],"gain.":[153],"These":[154],"results":[155],"highlight":[156],"effectiveness":[158],"framework.":[161]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}