{"id":"https://openalex.org/W7133362550","doi":"https://doi.org/10.48550/arxiv.2603.00512","title":"Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understanding","display_name":"Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understanding","publication_year":2026,"publication_date":"2026-02-28","ids":{"openalex":"https://openalex.org/W7133362550","doi":"https://doi.org/10.48550/arxiv.2603.00512"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.00512","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00512","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.00512","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128023124","display_name":"Wang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chen, Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127883592","display_name":"Yuhui Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Yuhui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112987153","display_name":"Yongdong Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Yongdong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127948713","display_name":"Tianyu Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Tianyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010577514","display_name":"Luojun Lin","orcid":"https://orcid.org/0000-0002-1141-2487"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Luojun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127932770","display_name":"Jiayi Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Jiayi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127903788","display_name":"Yan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Zheng, Xiawu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Xiawu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5128023124"],"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":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":0.26969999074935913,"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":0.26969999074935913,"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":0.11180000007152557,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.10300000011920929,"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/leverage","display_name":"Leverage (statistics)","score":0.5066999793052673},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4652000069618225},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4526999890804291},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4456000030040741},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4124999940395355},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3991999924182892},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3873000144958496},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3840000033378601},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.3783999979496002},{"id":"https://openalex.org/keywords/residual-frame","display_name":"Residual frame","score":0.37790000438690186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.70660001039505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5853999853134155},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5066999793052673},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4526999890804291},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4374000132083893},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41119998693466187},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C204641915","wikidata":"https://www.wikidata.org/wiki/Q7315509","display_name":"Residual frame","level":4,"score":0.37790000438690186},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3334999978542328},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.31310001015663147},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29789999127388},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.2874000072479248},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2791000008583069},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.27379998564720154},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.26010000705718994},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25679999589920044},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25360000133514404},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.00512","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00512","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.00512","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00512","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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Frame":[0,54],"selection":[1],"is":[2,112,263],"crucial":[3],"due":[4,115],"to":[5,19,30,94,116,205,225],"high":[6,28,76],"frame":[7,203],"redundancy":[8],"and":[9,123,147,162,214,253],"limited":[10],"context":[11],"windows":[12],"when":[13],"applying":[14,151],"Large":[15],"Vision-Language":[16],"Models":[17],"(LVLMs)":[18],"long":[20],"videos.":[21],"Current":[22],"methods":[23],"typically":[24],"select":[25,226],"frames":[26,40],"with":[27],"relevance":[29,77],"a":[31,36,61,66,164,196,202,210,227],"given":[32],"query,":[33],"resulting":[34],"in":[35,107,144],"disjointed":[37],"set":[38,231],"of":[39,46,88,99,104,178,232],"that":[41,64,91,237],"disregard":[42],"the":[43,96,108,132,156,170,175,186,220],"narrative":[44,89],"structure":[45],"video.":[47,100],"In":[48],"this":[49,152,179],"paper,":[50],"we":[51,130,154],"introduce":[52],"Wavelet-based":[53],"Selection":[55],"by":[56,246],"Detecting":[57],"Semantic":[58],"Boundary":[59],"(WFS-SB),":[60],"training-free":[62],"framework":[63],"presents":[65],"new":[67],"perspective:":[68],"effective":[69],"video":[70,187],"understanding":[71],"hinges":[72],"not":[73],"only":[74],"on":[75,81,192,209,248,251,255],"but,":[78],"more":[79],"importantly,":[80],"capturing":[82],"semantic":[83,166,182],"shifts":[84],"-":[85],"pivotal":[86],"moments":[87],"change":[90,167],"are":[92],"essential":[93],"comprehending":[95],"holistic":[97],"storyline":[98],"However,":[101],"direct":[102],"detection":[103],"abrupt":[105],"changes":[106],"query-frame":[109],"similarity":[110],"signal":[111,158,168,180],"often":[113],"unreliable":[114],"high-frequency":[117],"noise":[118],"arising":[119],"from":[120,169],"model":[121],"uncertainty":[122],"transient":[124],"visual":[125],"variations.":[126],"To":[127],"address":[128],"this,":[129,193],"leverage":[131],"wavelet":[133],"transform,":[134,153],"which":[135,184],"provides":[136],"an":[137],"ideal":[138],"solution":[139],"through":[140],"its":[141],"multi-resolution":[142],"analysis":[143],"both":[145],"time":[146],"frequency":[148],"domains.":[149],"By":[150],"decompose":[155],"noisy":[157],"into":[159,188],"multiple":[160],"scales":[161],"extract":[163],"clean":[165],"coarsest":[171],"scale.":[172],"We":[173],"identify":[174],"local":[176],"extrema":[177],"as":[181],"boundaries,":[183],"segment":[185],"coherent":[189],"clips.":[190],"Building":[191],"WFS-SB":[194,238],"comprises":[195],"two-stage":[197],"strategy:":[198],"first,":[199],"adaptively":[200],"allocating":[201],"budget":[204],"each":[206,217],"clip":[207],"based":[208],"composite":[211],"importance":[212],"score;":[213],"second,":[215],"within":[216],"clip,":[218],"employing":[219],"Maximal":[221],"Marginal":[222],"Relevance":[223],"approach":[224],"diverse":[228],"yet":[229],"relevant":[230],"frames.":[233],"Extensive":[234],"experiments":[235],"show":[236],"significantly":[239],"boosts":[240],"LVLM":[241],"performance,":[242],"e.g.,":[243],"improving":[244],"accuracy":[245],"5.5%":[247],"VideoMME,":[249],"9.5%":[250],"MLVU,":[252],"6.2%":[254],"LongVideoBench,":[256],"consistently":[257],"outperforming":[258],"state-of-the-art":[259],"methods.":[260],"Our":[261],"code":[262],"available":[264],"at":[265],"https://github.com/MAC-AutoML/WFS-SB.":[266]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2026-03-04T00:00:00"}