{"id":"https://openalex.org/W4412888065","doi":"https://doi.org/10.18653/v1/2025.findings-acl.921","title":"Generative Frame Sampler for Long Video Understanding","display_name":"Generative Frame Sampler for Long Video Understanding","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888065","doi":"https://doi.org/10.18653/v1/2025.findings-acl.921"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.921","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.921","pdf_url":"https://aclanthology.org/2025.findings-acl.921.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.921.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035307582","display_name":"Linli Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linli Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039135087","display_name":"Haoning Wu","orcid":"https://orcid.org/0009-0001-8717-338X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoning Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041046639","display_name":"Kun Ouyang","orcid":"https://orcid.org/0000-0001-7833-3700"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Ouyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020022791","display_name":"Yuanxing Zhang","orcid":"https://orcid.org/0000-0003-1460-8124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanxing Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032046813","display_name":"Caiming Xiong","orcid":"https://orcid.org/0000-0003-0349-8628"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caiming Xiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760111","display_name":"Bei Chen","orcid":"https://orcid.org/0000-0001-9087-012X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bei Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006497264","display_name":"Xu Sun","orcid":"https://orcid.org/0000-0001-9155-0427"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5013528128","display_name":"Junnan Li","orcid":"https://orcid.org/0000-0002-9320-1965"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junnan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17900","last_page":"17917"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9020000100135803,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9020000100135803,"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/computer-science","display_name":"Computer science","score":0.7381393909454346},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6559997797012329},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6286563277244568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5180292725563049},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44570717215538025},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09349533915519714}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7381393909454346},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6559997797012329},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6286563277244568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5180292725563049},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44570717215538025},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09349533915519714}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.921","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.921","pdf_url":"https://aclanthology.org/2025.findings-acl.921.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.921","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.921","pdf_url":"https://aclanthology.org/2025.findings-acl.921.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4370721888","display_name":null,"funder_award_id":"62176002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888065.pdf","grobid_xml":"https://content.openalex.org/works/W4412888065.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Despite":[0],"recent":[1],"advances":[2],"in":[3],"Video":[4],"Large":[5],"Language":[6],"Models":[7],"(VideoLLMs),":[8],"effectively":[9],"understanding":[10],"long-form":[11,112],"videos":[12,18],"remains":[13],"a":[14,37,50,69],"significant":[15],"challenge.Perceiving":[16],"lengthy":[17,46],"containing":[19],"thousands":[20],"of":[21,87],"frames":[22],"poses":[23],"substantial":[24],"computational":[25],"burden.To":[26],"mitigate":[27],"this":[28,30],"issue,":[29],"paper":[31],"introduces":[32],"Generative":[33],"Frame":[34],"Sampler":[35],"(GenS),":[36],"plug-and-play":[38],"module":[39],"integrated":[40],"with":[41,74,103],"VideoLLMs":[42,106],"to":[43,59],"facilitate":[44,63],"efficient":[45],"video":[47,71,113],"perception.Built":[48],"upon":[49],"lightweight":[51],"VideoLLM,":[52],"GenS":[53,82],"leverages":[54],"its":[55],"inherent":[56],"vision-language":[57],"capabilities":[58],"identify":[60],"question-relevant":[61],"frames.To":[62],"effective":[64],"retrieval,":[65],"we":[66],"construct":[67],"GenS-Video-150K,":[68],"large-scale":[70],"instruction":[72],"dataset":[73,140],"dense":[75],"frame":[76],"relevance":[77],"annotations.Extensive":[78],"experiments":[79],"demonstrate":[80],"that":[81],"consistently":[83],"boosts":[84],"the":[85,133,138],"performance":[86],"various":[88],"Vide-oLLMs,":[89],"including":[90],"open-source":[91],"models":[92,142],"(Qwen2-VL-7B,":[93],"Aria-25B,":[94],"VILA-40B,":[95],"LLaVA-Video-7B/72B)":[96],"and":[97,121,141],"proprietary":[98],"assistants":[99],"(GPT-4o,":[100],"Gemini).When":[101],"equipped":[102],"GenS,":[104],"opensource":[105],"achieve":[107],"impressive":[108],"stateof-the-art":[109],"results":[110],"on":[111,119,124,130],"benchmarks:":[114],"LLaVA-Video-72B":[115],"reaches":[116],"66.8":[117],"(+4.3)":[118],"LongVideoBench":[120],"77.0":[122],"(+2.7)":[123],"MLVU,":[125],"while":[126],"Aria":[127],"obtains":[128],"39.2":[129],"HourVideo":[131],"surpassing":[132],"Gemini-1.5-proby":[134],"1.9":[135],"points.We":[136],"release":[137],"code,":[139],"at":[143],"https:":[144],"//generative-sampler.github.io.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}