{"id":"https://openalex.org/W4414384364","doi":"https://doi.org/10.1109/iccv51701.2025.02048","title":"Q-Frame: Query-Aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs","display_name":"Q-Frame: Query-Aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414384364","doi":"https://doi.org/10.1109/iccv51701.2025.02048"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02048","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02048","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/2506.22139","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087582234","display_name":"Shaojie Zhang","orcid":"https://orcid.org/0000-0002-7487-6238"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shaojie Zhang","raw_affiliation_strings":["Xiaomi Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111226079","display_name":"Jiahui Yang","orcid":"https://orcid.org/0009-0000-2262-3012"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahui Yang","raw_affiliation_strings":["Xiaomi Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100606496","display_name":"Jianqin Yin","orcid":"https://orcid.org/0000-0002-1595-2499"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianqin Yin","raw_affiliation_strings":["Xiaomi Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102328739","display_name":"Zhenbo Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenbo Luo","raw_affiliation_strings":["Xiaomi Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054843960","display_name":"Jian Luan","orcid":"https://orcid.org/0000-0002-2383-226X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Luan","raw_affiliation_strings":["Xiaomi Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"MiLM Plus","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"MiLM Plus","raw_affiliation_strings":["Xiaomi Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5087582234"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22732606,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22056","last_page":"22065"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9962000250816345,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9962000250816345,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9735000133514404,"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/frame","display_name":"Frame (networking)","score":0.6243000030517578},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5860999822616577},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5669999718666077},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5540000200271606},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5041000247001648},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4616999924182892},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.40299999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8116000294685364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6322000026702881},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6243000030517578},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5860999822616577},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5669999718666077},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5540000200271606},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5041000247001648},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4706999957561493},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4616999924182892},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.40299999713897705},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34439998865127563},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2646999955177307},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02048","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02048","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:2506.22139","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.22139","pdf_url":"https://arxiv.org/pdf/2506.22139","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.2506.22139","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.22139","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":"pmh:oai:arXiv.org:2506.22139","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.22139","pdf_url":"https://arxiv.org/pdf/2506.22139","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"have":[5],"demonstrated":[6],"significant":[7],"success":[8],"in":[9,16],"visual":[10],"understanding":[11,143],"tasks.":[12,144],"However,":[13],"challenges":[14],"persist":[15],"adapting":[17],"these":[18],"models":[19],"for":[20,60,94],"video":[21,142],"comprehension":[22],"due":[23],"to":[24,41,68,101],"the":[25,43,69,73,91],"large":[26],"volume":[27],"of":[28,48],"data":[29],"and":[30,64,72,113,129,137],"temporal":[31,112],"complexity.":[32],"Existing":[33],"Video-LLMs":[34,100],"using":[35],"uniform":[36],"frame":[37,62,96],"sampling":[38],"often":[39],"struggle":[40],"capture":[42],"query-related":[44],"crucial":[45],"spatiotemporal":[46],"clues":[47],"videos":[49],"effectively.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"introduce":[55],"Q-Frame,":[56],"a":[57,78,84],"novel":[58],"approach":[59],"adaptive":[61],"selection":[63],"multi-resolution":[65],"scaling":[66],"tailored":[67],"video's":[70],"content":[71],"specific":[74],"query.":[75],"Q-Frame":[76,98],"employs":[77],"training-free,":[79],"plug-and-play":[80],"strategy":[81],"generated":[82],"by":[83],"text-image":[85],"matching":[86],"network":[87],"like":[88],"CLIP,":[89],"utilizing":[90],"Gumbel-Max":[92],"trick":[93],"efficient":[95],"selection.":[97],"allows":[99],"process":[102],"more":[103],"frames":[104],"without":[105],"exceeding":[106],"computational":[107],"limits,":[108],"thereby":[109],"preserving":[110],"critical":[111],"spatial":[114],"information.":[115],"We":[116],"demonstrate":[117],"Q-Frame's":[118],"effectiveness":[119],"through":[120],"extensive":[121],"experiments":[122],"on":[123],"benchmark":[124],"datasets,":[125],"including":[126],"MLVU,":[127],"LongVideoBench,":[128],"Video-MME,":[130],"illustrating":[131],"its":[132,138],"superiority":[133],"over":[134],"existing":[135],"methods":[136],"applicability":[139],"across":[140],"various":[141]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}