{"id":"https://openalex.org/W7204959860","doi":"https://doi.org/10.48550/arxiv.2608.28699","title":"Beyond Visual Boundaries: Rethinking Scene Segmentation for Movie RAG","display_name":"Beyond Visual Boundaries: Rethinking Scene Segmentation for Movie RAG","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204959860","doi":"https://doi.org/10.48550/arxiv.2608.28699"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.28699","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28699","pdf_url":"https://arxiv.org/pdf/2608.28699","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.28699","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148927412","display_name":"Dong-Hee Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Dong-Hee","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148894867","display_name":"Seonwoo Choi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Choi, Seonwoo","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148939864","display_name":"Changbeen Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Changbeen","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120025820","display_name":"Jungmyung Wi","orcid":"https://orcid.org/0009-0005-0913-6566","observed_orcids":["https://orcid.org/0009-0005-0913-6566"]},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wi, Jungmyung","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153424362","display_name":"Juyeon Ko","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ko, Juyeon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148850929","display_name":"Youngju Choi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Choi, Youngju","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148939335","display_name":"Il Hyeon Mun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mun, Il Hyeon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125390144","display_name":"Hyunwoo J. Kim","orcid":"https://orcid.org/0000-0002-2181-9264","observed_orcids":["https://orcid.org/0000-0002-2181-9264"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Hyunwoo J.","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100454683","display_name":"Donghyun Kim","orcid":"https://orcid.org/0000-0002-7132-4454","observed_orcids":["https://orcid.org/0000-0002-7132-4454"]},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Donghyun","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":["https://openalex.org/I197347611"]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.7407000064849854,"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/T11439","display_name":"Video Analysis and Summarization","score":0.7407000064849854,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2551000118255615,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.0006000000284984708,"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/scene-segmentation","display_name":"scene segmentation","score":0.9789999723434448},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9929999709129333},{"id":"https://openalex.org/keywords/long-form-video","display_name":"long-form video","score":0.6990000009536743},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.7910000085830688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7807999849319458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6503999829292297},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6463000178337097},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.5698000192642212},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4535999894142151},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43849998712539673},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3824000060558319},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3138999938964844},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3046000003814697},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.28699","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28699","pdf_url":"https://arxiv.org/pdf/2608.28699","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.28699","doi":"https://doi.org/10.48550/arxiv.2608.28699","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.28699","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.28699","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28699","pdf_url":"https://arxiv.org/pdf/2608.28699","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204959860.pdf","grobid_xml":"https://content.openalex.org/works/W7204959860.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417097907","https://openalex.org/W7117538205","https://openalex.org/W3034364644","https://openalex.org/W4416255922","https://openalex.org/W7138469371","https://openalex.org/W7147367612","https://openalex.org/W4417097840","https://openalex.org/W190821737","https://openalex.org/W7164821104","https://openalex.org/W4415332863"],"abstract_inverted_index":{"Understanding":[0],"long-form":[1],"video":[2,42,57],"remains":[3],"a":[4,34,88,99,164,171,186],"fundamental":[5],"challenge":[6,209],"for":[7,44,69,102,210,228],"multimodal":[8],"large":[9],"language":[10],"models":[11],"(MLLMs).":[12],"Sparse":[13],"frame":[14],"sampling":[15,24],"fails":[16],"to":[17,130],"capture":[18],"fine-grained":[19],"visual":[20],"details,":[21],"while":[22],"dense":[23],"quickly":[25],"exceeds":[26],"context":[27],"length":[28],"limits.":[29],"Retrieval-augmented":[30],"generation":[31],"(RAG)":[32],"offers":[33],"promising":[35],"middle":[36],"ground":[37],"by":[38,158],"selectively":[39],"retrieving":[40],"relevant":[41],"segments":[43,58,196],"grounded":[45],"generation,":[46],"yet":[47],"its":[48],"effectiveness":[49],"critically":[50],"depends":[51],"on":[52,119,200],"the":[53,56,139,207,222],"quality":[54],"of":[55,84,138],"used":[59,190],"as":[60,191],"retrieval":[61,105,192],"units.":[62,106],"In":[63],"this":[64,114,159],"paper,":[65],"we":[66,161],"investigate":[67],"RAG":[68,215],"movie":[70,121,202,214,229],"understanding,":[71],"which":[72],"demands":[73],"story-level":[74],"reasoning":[75],"over":[76,153],"characters,":[77],"events,":[78],"and":[79,124,178],"narrative":[80,154,179,223],"arcs":[81],"spanning":[82,175],"hours":[83],"content.":[85],"Scene":[86],"segmentation,":[87],"long-studied":[89],"problem":[90],"that":[91,126,206,226],"partitions":[92],"movies":[93],"into":[94],"semantically":[95],"coherent":[96],"units,":[97,193],"is":[98,216],"natural":[100],"candidate":[101],"defining":[103],"such":[104],"We":[107],"reexamine":[108],"whether":[109],"existing":[110],"methods":[111],"actually":[112],"serve":[113],"role":[115],"through":[116],"comprehensive":[117],"evaluation":[118],"downstream":[120,201],"understanding":[122,203],"tasks,":[123,204],"find":[125],"they":[127],"consistently":[128],"fail":[129],"outperform":[131,197],"naive":[132],"uniform":[133,198],"temporal":[134],"chunking.":[135],"Our":[136],"audit":[137],"most":[140],"standard":[141],"scene":[142,166,211],"segmentation":[143,167,212],"benchmarks":[144],"reveals":[145],"why:":[146],"current":[147],"annotations":[148],"prioritize":[149],"visually":[150],"salient":[151],"transitions":[152],"event":[155,224],"structure.":[156],"Motivated":[157],"mismatch,":[160],"introduce":[162],"NarraScene,":[163],"narrative-centric":[165],"dataset":[168],"annotated":[169],"with":[170],"three-level":[172],"cognitive":[173],"taxonomy":[174],"physical,":[176],"character,":[177],"change,":[180],"where":[181],"every":[182],"valid":[183],"boundary":[184],"requires":[185],"narrative-level":[187],"shift.":[188],"When":[189],"these":[194],"narrative-grounded":[195],"chunking":[199],"suggesting":[205],"central":[208],"in":[213],"not":[217],"detecting":[218],"boundaries,":[219],"but":[220],"identifying":[221],"units":[225],"matter":[227],"understanding.":[230]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-02T00:00:00"}