{"id":"https://openalex.org/W4417010012","doi":"https://doi.org/10.1109/wacv61042.2026.00035","title":"Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video?","display_name":"Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video?","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417010012","doi":"https://doi.org/10.1109/wacv61042.2026.00035"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.02846","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069445569","display_name":"Manuel Benavent-Lled\u00f3","orcid":"https://orcid.org/0000-0001-8809-8476"},"institutions":[{"id":"https://openalex.org/I130194489","display_name":"University of Alicante","ror":"https://ror.org/05t8bcz72","country_code":"ES","type":"education","lineage":["https://openalex.org/I130194489"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Manuel Benavent-Lledo","raw_affiliation_strings":["Universidad de Alicante,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad de Alicante,Spain","institution_ids":["https://openalex.org/I130194489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018734389","display_name":"Konstantinos Bacharidis","orcid":"https://orcid.org/0000-0002-3867-7119"},"institutions":[{"id":"https://openalex.org/I8901234","display_name":"Foundation for Research and Technology Hellas","ror":"https://ror.org/052rphn09","country_code":"GR","type":"facility","lineage":["https://openalex.org/I8901234"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Konstantinos Bacharidis","raw_affiliation_strings":["Foundation for Research and Technology-Hellas,Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Foundation for Research and Technology-Hellas,Greece","institution_ids":["https://openalex.org/I8901234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062755841","display_name":"Victoria Manousaki","orcid":"https://orcid.org/0000-0003-2181-791X"},"institutions":[{"id":"https://openalex.org/I8901234","display_name":"Foundation for Research and Technology Hellas","ror":"https://ror.org/052rphn09","country_code":"GR","type":"facility","lineage":["https://openalex.org/I8901234"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Victoria Manousaki","raw_affiliation_strings":["Foundation for Research and Technology-Hellas,Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Foundation for Research and Technology-Hellas,Greece","institution_ids":["https://openalex.org/I8901234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023684097","display_name":"Konstantinos Papoutsakis","orcid":"https://orcid.org/0000-0002-2467-8727"},"institutions":[{"id":"https://openalex.org/I8901234","display_name":"Foundation for Research and Technology Hellas","ror":"https://ror.org/052rphn09","country_code":"GR","type":"facility","lineage":["https://openalex.org/I8901234"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Konstantinos Papoutsakis","raw_affiliation_strings":["Foundation for Research and Technology-Hellas,Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Foundation for Research and Technology-Hellas,Greece","institution_ids":["https://openalex.org/I8901234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023467254","display_name":"Antonis Argyros","orcid":"https://orcid.org/0000-0001-8230-3192"},"institutions":[{"id":"https://openalex.org/I8901234","display_name":"Foundation for Research and Technology Hellas","ror":"https://ror.org/052rphn09","country_code":"GR","type":"facility","lineage":["https://openalex.org/I8901234"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Antonis Argyros","raw_affiliation_strings":["Foundation for Research and Technology-Hellas,Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Foundation for Research and Technology-Hellas,Greece","institution_ids":["https://openalex.org/I8901234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019125954","display_name":"Jose Garcia-Rodriguez","orcid":"https://orcid.org/0000-0002-8057-5706"},"institutions":[{"id":"https://openalex.org/I130194489","display_name":"University of Alicante","ror":"https://ror.org/05t8bcz72","country_code":"ES","type":"education","lineage":["https://openalex.org/I130194489"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jose Garcia-Rodriguez","raw_affiliation_strings":["Universidad de Alicante,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad de Alicante,Spain","institution_ids":["https://openalex.org/I130194489"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5069445569"],"corresponding_institution_ids":["https://openalex.org/I130194489"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01109199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6952999830245972,"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":0.6952999830245972,"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":0.23770000040531158,"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/T11431","display_name":"Action Observation and Synchronization","score":0.017799999564886093,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/anticipation","display_name":"Anticipation (artificial intelligence)","score":0.8442999720573425},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.7494000196456909},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6445000171661377},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5206000208854675},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4830000102519989},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.38100001215934753},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.3224000036716461}],"concepts":[{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.8442999720573425},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7494000196456909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6830999851226807},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6445000171661377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5375000238418579},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5206000208854675},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4830000102519989},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25920000672340393},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2515999972820282},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.02846","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.02846","pdf_url":"https://arxiv.org/pdf/2512.02846","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2512.02846","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.02846","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":"pmh:oai:arXiv.org:2512.02846","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.02846","pdf_url":"https://arxiv.org/pdf/2512.02846","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Anticipating":[0],"actions":[1,32],"before":[2],"they":[3],"occur":[4],"is":[5,54,133],"a":[6,35,39,46,99,105,115,147],"core":[7],"challenge":[8],"in":[9,89],"action":[10,125,149,157],"understanding":[11],"research.":[12],"While":[13],"conventional":[14],"methods":[15,173],"rely":[16],"on":[17,60,86],"extracting":[18],"and":[19,93,122,171,181],"aggregating":[20],"temporal":[21],"information":[22,126],"from":[23,38,114,139,143],"videos,":[24],"as":[25],"humans":[26],"we":[27,69,96],"can":[28,76,161],"often":[29],"predict":[30],"upcoming":[31],"by":[33,146],"observing":[34],"single":[36,116],"moment":[37],"scene,":[40],"when":[41],"given":[42],"sufficient":[43],"context.":[44,130],"Can":[45],"model":[47],"achieve":[48],"this":[49,67,83],"competence?":[50],"The":[51],"short":[52],"answer":[53],"yes,":[55],"although":[56],"its":[57],"effectiveness":[58],"depends":[59],"the":[61,64],"complexity":[62],"of":[63],"task.":[65],"In":[66],"work,":[68],"investigate":[70],"to":[71,127,165],"what":[72],"extent":[73],"video":[74,169],"aggregation":[75],"be":[77],"replaced":[78],"with":[79,111],"alternative":[80],"modalities.":[81],"To":[82],"end,":[84],"based":[85],"recent":[87],"advances":[88],"visual":[90],"feature":[91],"extraction":[92],"language-based":[94],"reasoning,":[95,121],"introduce":[97],"AAG,":[98],"method":[100],"for":[101,118],"Action":[102],"Anticipation":[103],"at":[104],"Glimpse.":[106],"AAG":[107,160],"combines":[108],"RGB":[109],"features":[110],"depth":[112],"cues":[113],"frame":[117],"enhanced":[119],"spatial":[120],"incorporates":[123],"prior":[124],"provide":[128],"long-term":[129],"This":[131],"context":[132],"obtained":[134],"either":[135],"through":[136],"textual":[137],"summaries":[138],"Vision-Language":[140],"Models,":[141],"or":[142],"predictions":[144],"generated":[145],"single-frame":[148,156],"recognizer.":[150],"Our":[151],"results":[152],"demonstrate":[153],"that":[154],"multimodal":[155],"anticipation":[158],"using":[159],"perform":[162],"competitively":[163],"compared":[164],"both":[166],"temporally":[167],"aggregated":[168],"baselines":[170],"state-of-the-art":[172],"across":[174],"three":[175],"instructional":[176],"activity":[177],"datasets:":[178],"IKEA-ASM,":[179],"Meccano,":[180],"Assembly101.":[182]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2025-12-04T00:00:00"}