{"id":"https://openalex.org/W7204167328","doi":"https://doi.org/10.48550/arxiv.2608.22359","title":"Pre-Decoding Acoustic Triage for Budgeted Vision-Language Captioning of Untrimmed Egocentric Video","display_name":"Pre-Decoding Acoustic Triage for Budgeted Vision-Language Captioning of Untrimmed Egocentric Video","publication_year":2026,"publication_date":"2026-08-23","ids":{"openalex":"https://openalex.org/W7204167328","doi":"https://doi.org/10.48550/arxiv.2608.22359"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.22359","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22359","pdf_url":"https://arxiv.org/pdf/2608.22359","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":"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/2608.22359","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010044195","display_name":"Masoud Jalayer","orcid":"https://orcid.org/0000-0001-8013-8613","observed_orcids":["https://orcid.org/0000-0001-8013-8613"]},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jalayer, Masoud","raw_affiliation_strings":["Dept. of Electrical Engineering and Automation Aalto University , 02150 Espoo , Finland","Dept. of Information and Communications Engineering ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering and Automation Aalto University , 02150 Espoo , Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Dept. of Information and Communications Engineering ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139158257","display_name":"Changyi Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Changyi","raw_affiliation_strings":["Dept. of Information and Communications Engineering ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Information and Communications Engineering ,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148051251","display_name":"Yu Xiao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Yu","raw_affiliation_strings":["Dept. of Information and Communications Engineering ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Information and Communications Engineering ,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9829000234603882,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9829000234603882,"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":0.007799999788403511,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.0015999999595806003,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/egocentric-video","display_name":"egocentric video","score":0.8399999737739563},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8190000057220459},{"id":"https://openalex.org/keywords/captioning","display_name":"captioning","score":0.5849999785423279},{"id":"https://openalex.org/keywords/token-compression","display_name":"token compression","score":0.6029999852180481},{"id":"https://openalex.org/keywords/quantization","display_name":"quantization","score":0.734000027179718},{"id":"https://openalex.org/keywords/sound-event-detection","display_name":"sound event detection","score":0.5590000152587891},{"id":"https://openalex.org/keywords/ego4d","display_name":"Ego4D","score":0.6949999928474426},{"id":"https://openalex.org/keywords/epic-kitchens-100","display_name":"EPIC-KITCHENS-100","score":0.968999981880188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7386999726295471},{"id":"https://openalex.org/C2777120189","wikidata":"https://www.wikidata.org/wiki/Q780067","display_name":"Triage","level":2,"score":0.6010000109672546},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4632999897003174},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4620000123977661},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3831999897956848},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.33329999446868896},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.31869998574256897},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30410000681877136},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.30070000886917114},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C2777548347","wikidata":"https://www.wikidata.org/wiki/Q5456937","display_name":"Flagging","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22359","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22359","pdf_url":"https://arxiv.org/pdf/2608.22359","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.22359","doi":"https://doi.org/10.48550/arxiv.2608.22359","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22359","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:2608.22359","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22359","pdf_url":"https://arxiv.org/pdf/2608.22359","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204167328.pdf","grobid_xml":"https://content.openalex.org/works/W7204167328.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7215046111","https://openalex.org/W4415255544","https://openalex.org/W7155100494","https://openalex.org/W7139936341","https://openalex.org/W3034658206","https://openalex.org/W7161826536","https://openalex.org/W2395155446","https://openalex.org/W4416037015","https://openalex.org/W3147809258","https://openalex.org/W3013460114"],"abstract_inverted_index":{"Automatically":[0],"analyzing":[1],"hours-long":[2],"egocentric":[3],"video":[4,78,101],"is":[5,103],"increasingly":[6],"essential":[7],"for":[8],"progress":[9],"monitoring,":[10],"quality":[11],"control,":[12],"and":[13,18,194,205],"safety":[14],"in":[15,118],"logistics,":[16],"construction,":[17],"manufacturing.":[19],"Yet":[20],"current":[21],"pipelines":[22],"that":[23,80],"process":[24],"short,":[25],"fixed-size":[26],"windows":[27,57,70,93],"with":[28,39,110],"a":[29,59,126],"vision-language":[30],"model":[31,43],"(VLM)":[32],"are":[33,84,212],"prohibitively":[34],"expensive":[35],"because":[36],"cost":[37],"scales":[38],"the":[40,77,81,95,106,119,122,132,167,170,187,202],"number":[41],"of":[42,166,174],"calls.":[44],"To":[45],"reduce":[46],"this":[47,209],"cost,":[48],"prior":[49],"work":[50],"proposes":[51],"triage":[52,171],"policies":[53,64],"to":[54,86,134],"select":[55,92],"which":[56,74],"merit":[58],"VLM":[60,175],"invocation.":[61],"However,":[62],"these":[63],"either":[65],"sample":[66],"uniformly":[67],"or":[68,113],"rank":[69],"using":[71,94,154],"visual":[72,198],"features,":[73],"ironically":[75],"requires":[76],"decoding":[79],"budget":[82],"constraints":[83],"meant":[85],"avoid.":[87],"We":[88],"propose":[89],"audio-first":[90],"triage:":[91],"lightest":[96],"modality,":[97],"scored":[98],"before":[99],"any":[100],"frame":[102],"decoded,":[104],"so":[105],"approach":[107],"composes":[108],"naturally":[109],"token":[111],"compression":[112],"quantization.":[114],"The":[115],"novelty":[116],"lies":[117],"objective,":[120],"not":[121],"representation:":[123],"rather":[124],"than":[125,164],"per-frame":[127],"sound-event":[128,160],"detector,":[129],"we":[130],"train":[131],"selector":[133],"trigger":[135],"once":[136],"per":[137],"action.":[138],"This":[139],"objective":[140],"shift":[141],"improves":[142],"action":[143],"coverage":[144,179],"by":[145],"4.0-10.8":[146],"percentage":[147],"points":[148],"across":[149],"all":[150],"evaluated":[151],"call":[152],"rates,":[153],"frozen":[155],"AudioSet-pretrained":[156],"features":[157],"without":[158],"domain-specific":[159],"labels.":[161],"Using":[162],"fewer":[163],"half":[165],"available":[168],"calls,":[169],"cuts":[172],"9-20%":[173],"calls":[176],"at":[177,213],"matched":[178],"on":[180,189],"EPIC-KITCHENS-100":[181],"(EK-100),":[182],"surpasses":[183],"uniform":[184],"sampling":[185],"through":[186],"mid-range":[188],"Ego4D":[190],"over":[191],"247":[192],"clips,":[193],"outperforms":[195],"two":[196],"recent":[197],"keyframe":[199],"selectors.":[200],"Code,":[201],"reference":[203],"implementation":[204],"every":[206],"results":[207],"file":[208],"manuscript":[210],"reads":[211],"https://github.com/masjalayer/PreDecoding-AcousticTriage.":[214]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}