{"id":"https://openalex.org/W4416417319","doi":"https://doi.org/10.1109/iccv51701.2025.01942","title":"Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?","display_name":"Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416417319","doi":"https://doi.org/10.1109/iccv51701.2025.01942"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01942","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.12496","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113084792","display_name":"Tianyuan Qu","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":"Tianyuan Qu","raw_affiliation_strings":["CUHK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010564305","display_name":"Longxiang Tang","orcid":"https://orcid.org/0009-0005-2704-3718"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Longxiang Tang","raw_affiliation_strings":["HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025923008","display_name":"Bohao Peng","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":"Bohao Peng","raw_affiliation_strings":["CUHK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066489766","display_name":"Senqiao Yang","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":"Senqiao Yang","raw_affiliation_strings":["CUHK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051340429","display_name":"Bei Yu","orcid":"https://orcid.org/0000-0001-6406-4810"},"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":"Bei Yu","raw_affiliation_strings":["CUHK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052856441","display_name":"Jiaya Jia","orcid":"https://orcid.org/0000-0002-1246-553X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiaya Jia","raw_affiliation_strings":["HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"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":"20889","last_page":"20899"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9546999931335449,"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":0.9546999931335449,"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":0.021299999207258224,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.004600000102072954,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8396000266075134},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.774399995803833},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6251999735832214},{"id":"https://openalex.org/keywords/sampling-frame","display_name":"Sampling frame","score":0.47510001063346863},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.4025999903678894},{"id":"https://openalex.org/keywords/poisson-sampling","display_name":"Poisson sampling","score":0.2824999988079071}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8396000266075134},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.774399995803833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7157999873161316},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6251999735832214},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5216000080108643},{"id":"https://openalex.org/C198327121","wikidata":"https://www.wikidata.org/wiki/Q7410163","display_name":"Sampling frame","level":3,"score":0.47510001063346863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4586000144481659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41990000009536743},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.4025999903678894},{"id":"https://openalex.org/C82152865","wikidata":"https://www.wikidata.org/wiki/Q7208505","display_name":"Poisson sampling","level":5,"score":0.2824999988079071},{"id":"https://openalex.org/C195454712","wikidata":"https://www.wikidata.org/wiki/Q17133861","display_name":"Lot quality assurance sampling","level":4,"score":0.2793999910354614},{"id":"https://openalex.org/C192489979","wikidata":"https://www.wikidata.org/wiki/Q1502997","display_name":"Systematic sampling","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2621000111103058},{"id":"https://openalex.org/C75373757","wikidata":"https://www.wikidata.org/wiki/Q7410160","display_name":"Sampling design","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01942","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:2503.12496","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.12496","pdf_url":"https://arxiv.org/pdf/2503.12496","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.12496","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.12496","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.12496","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.12496","pdf_url":"https://arxiv.org/pdf/2503.12496","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"The":[0],"rise":[1],"of":[2,111,156],"Large":[3],"Vision-Language":[4],"Models":[5],"(LVLMs)":[6],"has":[7,177],"significantly":[8,142],"advanced":[9],"video":[10],"understanding.":[11],"However,":[12],"efficiently":[13],"processing":[14],"long":[15],"videos":[16],"remains":[17],"a":[18,72,100,124,161],"challenge":[19],"due":[20],"to":[21,47,69,81,129,135],"the":[22,43,64,84,92,153],"``Sampling":[23],"Dilemma'':":[24],"low-density":[25],"sampling":[26,33,66,85,117],"risks":[27],"missing":[28],"critical":[29],"information,":[30],"while":[31],"high-density":[32],"introduces":[34],"redundancy.":[35],"To":[36,90],"address":[37,152],"this":[38,170],"issue,":[39],"we":[40,98,122],"introduce":[41],"LSDBench,":[42],"first":[44],"benchmark":[45,173],"designed":[46],"evaluate":[48],"LVLMs":[49,168],"on":[50,77],"long-video":[51,158],"tasks":[52],"by":[53,88,95],"constructing":[54],"high":[55],"Necessary":[56],"Sampling":[57,104],"Density":[58],"(NSD)":[59],"questions,":[60,97],"where":[61],"NSD":[62],"represents":[63],"minimum":[65],"density":[67],"required":[68],"accurately":[70],"answer":[71],"given":[73],"question.":[74],"LSDBench":[75,148],"focuses":[76],"dense,":[78],"short-duration":[79],"actions":[80],"rigorously":[82],"assess":[83],"strategies":[86],"employed":[87],"LVLMs.":[89],"tackle":[91],"challenges":[93,155],"posed":[94],"high-NSD":[96,157],"propose":[99],"novel":[101],"Reasoning-Driven":[102],"Hierarchical":[103],"(RHS)":[105],"framework,":[106],"which":[107],"combines":[108],"global":[109],"localization":[110],"question-relevant":[112],"cues":[113],"with":[114,141],"local":[115],"dense":[116],"for":[118,164],"precise":[119],"inference.":[120],"Additionally,":[121],"develop":[123],"lightweight":[125],"Semantic-Guided":[126],"Frame":[127],"Selector":[128],"prioritize":[130],"informative":[131],"frames,":[132],"enabling":[133],"RHS":[134,150],"achieve":[136],"comparable":[137],"or":[138],"superior":[139],"performance":[140],"fewer":[143],"sampled":[144],"frames.":[145],"Together,":[146],"our":[147],"and":[149,166,174],"framework":[151],"unique":[154],"tasks,":[159],"setting":[160],"new":[162],"standard":[163],"evaluating":[165],"improving":[167],"in":[169],"domain.":[171],"Our":[172],"evaluation":[175],"codes":[176],"been":[178],"released":[179],"at:":[180],"https://github.com/dvlab-research/LSDBench":[181]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}