{"id":"https://openalex.org/W7204893835","doi":"https://doi.org/10.48550/arxiv.2608.29287","title":"PERSIST: Persistent-State Discrimination for Shot Boundary Detection","display_name":"PERSIST: Persistent-State Discrimination for Shot Boundary Detection","publication_year":2026,"publication_date":"2026-08-29","ids":{"openalex":"https://openalex.org/W7204893835","doi":"https://doi.org/10.48550/arxiv.2608.29287"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.29287","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.29287","pdf_url":"https://arxiv.org/pdf/2608.29287","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.29287","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148919260","display_name":"Tingyu Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Lin, Tingyu","raw_affiliation_strings":["Computer Vision Lab TU Wien Vienna , Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Lab TU Wien Vienna , Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034063271","display_name":"Christian Stippel","orcid":"https://orcid.org/0000-0003-0482-902X","observed_orcids":["https://orcid.org/0000-0003-0482-902X"]},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Stippel, Christian","raw_affiliation_strings":["Computer Vision Lab TU Wien Vienna , Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Lab TU Wien Vienna , Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134176583","display_name":"Armin Dadras","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]},{"id":"https://openalex.org/I25485817","display_name":"University of Applied Sciences St P\u00f6lten","ror":"https://ror.org/039a2re55","country_code":"AT","type":"education","lineage":["https://openalex.org/I25485817"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Dadras, Armin","raw_affiliation_strings":["Computer Vision Lab TU Wien Vienna , Austria","Institute of Creative\\Media/Technologies St . P\u00f6lten University of Applied Sciences St. P\u00f6lten , Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Lab TU Wien Vienna , Austria","institution_ids":["https://openalex.org/I145847075"]},{"raw_affiliation_string":"Institute of Creative\\Media/Technologies St . P\u00f6lten University of Applied Sciences St. P\u00f6lten , Austria","institution_ids":["https://openalex.org/I25485817"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148932672","display_name":"Jakob Zenzmaier","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2799334681","display_name":"Ludwig Boltzmann Gesellschaft","ror":"https://ror.org/01v1jam04","country_code":"AT","type":"facility","lineage":["https://openalex.org/I2799334681"]},{"id":"https://openalex.org/I4405258342","display_name":"Ludwig Boltzmann Institute for Digital History","ror":"https://ror.org/00gg0jt32","country_code":"AT","type":"facility","lineage":["https://openalex.org/I2799334681","https://openalex.org/I4405258342"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Zenzmaier, Jakob","raw_affiliation_strings":["Ludwig Boltzmann Institute for Digital History Ludwig Boltzmann Gesellschaft Vienna , Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwig Boltzmann Institute for Digital History Ludwig Boltzmann Gesellschaft Vienna , Austria","institution_ids":["https://openalex.org/I2799334681","https://openalex.org/I4405258342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083550889","display_name":"Florian Kleber","orcid":"https://orcid.org/0000-0001-8351-5066","observed_orcids":["https://orcid.org/0000-0001-8351-5066"]},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Kleber, Florian","raw_affiliation_strings":["Computer Vision Lab TU Wien Vienna , Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Lab TU Wien Vienna , Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005355207","display_name":"Wolfgang Aigner","orcid":"https://orcid.org/0000-0001-5762-1869","observed_orcids":["https://orcid.org/0000-0001-5762-1869"]},"institutions":[{"id":"https://openalex.org/I25485817","display_name":"University of Applied Sciences St P\u00f6lten","ror":"https://ror.org/039a2re55","country_code":"AT","type":"education","lineage":["https://openalex.org/I25485817"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Aigner, Wolfgang","raw_affiliation_strings":["Institute of Creative\\Media/Technologies St . P\u00f6lten University of Applied Sciences St. P\u00f6lten , Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Creative\\Media/Technologies St . P\u00f6lten University of Applied Sciences St. P\u00f6lten , Austria","institution_ids":["https://openalex.org/I25485817"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019162549","display_name":"Robert Sablatnig","orcid":"https://orcid.org/0000-0003-4195-1593","observed_orcids":["https://orcid.org/0000-0003-4195-1593"]},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Sablatnig, Robert","raw_affiliation_strings":["Computer Vision Lab TU Wien Vienna , Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Lab TU Wien Vienna , Austria","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.9994999766349792,"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":0.9994999766349792,"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/T13579","display_name":"Image and Video Stabilization","score":9.999999747378752e-05,"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":0.0,"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/shot-boundary-detection","display_name":"shot boundary detection","score":1.0},{"id":"https://openalex.org/keywords/video-segmentation","display_name":"video segmentation","score":0.460999995470047},{"id":"https://openalex.org/keywords/false-positive-reduction","display_name":"false positive reduction","score":0.6700000166893005},{"id":"https://openalex.org/keywords/archival-footage","display_name":"archival footage","score":0.4690000116825104},{"id":"https://openalex.org/keywords/motion-blur","display_name":"motion blur","score":0.7889999747276306},{"id":"https://openalex.org/keywords/occlusion","display_name":"occlusion","score":0.7519999742507935},{"id":"https://openalex.org/keywords/explainable-decision-making","display_name":"explainable decision-making","score":0.3610000014305115}],"concepts":[{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.7544000148773193},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6870999932289124},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.5996000170707703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5630000233650208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45649999380111694},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.44179999828338623},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.41609999537467957},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3880999982357025},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.37869998812675476},{"id":"https://openalex.org/C2780624872","wikidata":"https://www.wikidata.org/wiki/Q852453","display_name":"Motion detection","level":3,"score":0.357699990272522},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.34299999475479126},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C2779086471","wikidata":"https://www.wikidata.org/wiki/Q2051704","display_name":"False memory","level":3,"score":0.32499998807907104},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27869999408721924},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.29287","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.29287","pdf_url":"https://arxiv.org/pdf/2608.29287","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.29287","doi":"https://doi.org/10.48550/arxiv.2608.29287","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.29287","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.29287","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.29287","pdf_url":"https://arxiv.org/pdf/2608.29287","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2079560105","display_name":"Visual Analytics and Computer Vision Meet Cultural Heritage","funder_award_id":"DFH 37","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"}],"funders":[{"id":"https://openalex.org/F4320321181","display_name":"Austrian Science Fund","ror":"https://ror.org/013tf3c58"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204893835.pdf","grobid_xml":"https://content.openalex.org/works/W7204893835.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2022582203","https://openalex.org/W2033431158","https://openalex.org/W2133649345","https://openalex.org/W2613762307","https://openalex.org/W2618658145","https://openalex.org/W2760103357","https://openalex.org/W2886229039","https://openalex.org/W2948138094","https://openalex.org/W2962677524","https://openalex.org/W2970068368","https://openalex.org/W3095481265","https://openalex.org/W4322741600","https://openalex.org/W4393343355","https://openalex.org/W4403791714","https://openalex.org/W7157253705","https://openalex.org/W7159625921"],"related_works":["https://openalex.org/W7044031166","https://openalex.org/W1971641581","https://openalex.org/W2010114018","https://openalex.org/W4414212531","https://openalex.org/W1966959462","https://openalex.org/W1965434768","https://openalex.org/W2527999122","https://openalex.org/W4304113924","https://openalex.org/W2078810715","https://openalex.org/W2165384368"],"abstract_inverted_index":{"Shot":[0],"boundary":[1,45,54],"detection":[2],"(SBD)":[3],"is":[4,50,61,87,140,159,257],"widely":[5],"treated":[6],"as":[7,19,44,52],"the":[8,68,81,137,143,151,221,245],"localisation":[9],"of":[10,67,170],"local":[11,34,58,109],"visual":[12],"discontinuities,":[13],"yet":[14],"many":[15],"false":[16,175,194,202],"positives":[17,176,195,203],"such":[18],"hand-held":[20],"shake,":[21],"illumination":[22],"flicker,":[23],"motion":[24],"blur,":[25],"occlusion,":[26],"and":[27,100,113,154,173,184,199,229],"damaged":[28],"archival":[29,174],"material":[30],"produce":[31],"equally":[32],"sharp":[33],"change":[35,59],"without":[36],"introducing":[37],"a":[38,48,53,64,75,90,95,101,116,122,163,209],"new":[39],"shot.":[40],"We":[41],"reformulate":[42],"SBD":[43],"semantic":[46,107],"discrimination:":[47],"frame":[49],"favoured":[51],"only":[55],"when":[56],"its":[57,145,155,201],"evidence":[60],"accompanied":[62],"by":[63,207],"persistent":[65],"update":[66],"video's":[69],"latent":[70,92,157],"temporal":[71,124],"state,":[72],"rather":[73],"than":[74],"transient":[76,111],"excursion":[77],"that":[78,104,197],"returns":[79],"to":[80,178],"surrounding":[82],"trend.":[83],"This":[84],"persistence":[85,138],"test":[86],"operationalised":[88],"with":[89,220],"continuous":[91],"state":[93,158],"from":[94,150,239],"FiLM-conditioned":[96],"sinusoidal":[97],"representation":[98],"network":[99],"structured":[102],"discriminator":[103],"combines":[105],"three":[106],"cues,":[108],"change,":[110],"impulse,":[112],"return-to-trend,":[114],"into":[115,133,142],"single":[117],"interpretable":[118],"per-frame":[119,146],"signal":[120],"over":[121],"dual-rate":[123],"backbone.":[125],"The":[126],"resulting":[127],"framework,":[128],"PERSIST,":[129],"turns":[130],"every":[131],"decision":[132],"an":[134,179],"inspectable":[135],"one:":[136],"criterion":[139],"trained":[141,181],"classifier,":[144],"effect":[147],"stays":[148],"readable":[149],"gate":[152],"triple,":[153],"learned":[156],"measurably":[160],"boundary-discriminative.":[161],"On":[162],"2,727-video":[164],"per-subtype":[165],"diagnostic":[166,198],"it":[167,189,237],"removes":[168],"33-80%":[169],"flash,":[171],"text-overlay,":[172],"relative":[177],"identically":[180],"cue":[182],"detector,":[183],"at":[185,259],"matched":[186],"true-transition":[187],"recall":[188],"roughly":[190],"halves":[191],"TransNetV2's":[192],"pseudo-event":[193],"on":[196,204,248],"cuts":[200],"ClipShots":[205,240],"footage":[206],"about":[208],"quarter,":[210],"while":[211,217],"preserving":[212],"recall.":[213],"It":[214],"does":[215],"so":[216],"reaching":[218],"parity":[219],"strongest":[222],"public":[223],"detector":[224],"across":[225],"online,":[226],"broadcast,":[227],"short-form,":[228],"historical-archive":[230],"transfer":[231],"evaluations,":[232],"under":[233],"markedly":[234],"stricter":[235],"training:":[236],"learns":[238],"real":[241],"transitions":[242,252],"only,":[243],"whereas":[244],"anchor":[246],"draws":[247],"additional":[249],"corpora":[250],"whose":[251],"are":[253],"85%":[254],"synthetic.":[255],"Code":[256],"available":[258],"https://github.com/linty5/PERSIST.":[260]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-02T00:00:00"}