{"id":"https://openalex.org/W7160334100","doi":"https://doi.org/10.1109/wacv61042.2026.00783","title":"Scalable Video Action Anticipation with Cross Linear Attentive Memory","display_name":"Scalable Video Action Anticipation with Cross Linear Attentive Memory","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160334100","doi":"https://doi.org/10.1109/wacv61042.2026.00783"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00783","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":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025665858","display_name":"Zeyun Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zeyun Zhong","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059089901","display_name":"Manuel Mart\u00edn","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111500","display_name":"Fraunhofer Institute of Optronics, System Technologies and Image Exploitation","ror":"https://ror.org/01zx97922","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210111500","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Manuel Martin","raw_affiliation_strings":["Fraunhofer IOSB"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IOSB","institution_ids":["https://openalex.org/I4210111500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124943388","display_name":"David Schneider","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"David Schneider","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102858494","display_name":"David Lerch","orcid":"https://orcid.org/0009-0008-6707-3059"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"David J. Lerch","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135313604","display_name":"Chengzhi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chengzhi Wu","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065967898","display_name":"Frederik Diederichs","orcid":"https://orcid.org/0000-0002-8600-6176"},"institutions":[{"id":"https://openalex.org/I4210111500","display_name":"Fraunhofer Institute of Optronics, System Technologies and Image Exploitation","ror":"https://ror.org/01zx97922","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210111500","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frederik Diederichs","raw_affiliation_strings":["Fraunhofer IOSB"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IOSB","institution_ids":["https://openalex.org/I4210111500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012240246","display_name":"J\u00fcergen Gall","orcid":"https://orcid.org/0000-0002-9447-3399"},"institutions":[{"id":"https://openalex.org/I4387154616","display_name":"Lamarr Institute for Machine Learning and Artificial Intelligence","ror":"https://ror.org/04s11ea33","country_code":null,"type":"facility","lineage":["https://openalex.org/I135140700","https://openalex.org/I200332995","https://openalex.org/I4210098062","https://openalex.org/I4210144576","https://openalex.org/I4387154616","https://openalex.org/I4923324","https://openalex.org/I4923324"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Juergen Gall","raw_affiliation_strings":["Lamarr Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lamarr Institute","institution_ids":["https://openalex.org/I4387154616"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073930300","display_name":"J\u00fcrgen Beyerer","orcid":"https://orcid.org/0000-0003-3556-7181"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00fcrgen Beyerer","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6944594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8113","last_page":"8123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.8848999738693237,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.8848999738693237,"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/T12290","display_name":"Human Motion and Animation","score":0.029100000858306885,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.009600000455975533,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/action","display_name":"Action (physics)","score":0.5644000172615051},{"id":"https://openalex.org/keywords/anticipation","display_name":"Anticipation (artificial intelligence)","score":0.5516999959945679},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.3659000098705292},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3546000123023987},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.29330000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6904000043869019},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.5516999959945679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5202999711036682},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3449000120162964},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2565000057220459},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25380000472068787},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wacv61042.2026.00783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00783","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:publica.fraunhofer.de:publica/515969","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/515969","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2222512263","https://openalex.org/W2342437993","https://openalex.org/W2422305492","https://openalex.org/W2507009361","https://openalex.org/W2766736793","https://openalex.org/W2945792291","https://openalex.org/W2963524571","https://openalex.org/W2963570630","https://openalex.org/W2963720581","https://openalex.org/W2963737762","https://openalex.org/W2989506443","https://openalex.org/W2993447238","https://openalex.org/W3021013305","https://openalex.org/W3089810082","https://openalex.org/W3096383329","https://openalex.org/W3096609285","https://openalex.org/W3106884574","https://openalex.org/W3124982122","https://openalex.org/W3205786327","https://openalex.org/W3207758636","https://openalex.org/W4214555767","https://openalex.org/W4214589115","https://openalex.org/W4312355936","https://openalex.org/W4312372834","https://openalex.org/W4312660844","https://openalex.org/W4312690503","https://openalex.org/W4312772544","https://openalex.org/W4312873759","https://openalex.org/W4313023218","https://openalex.org/W4319299948","https://openalex.org/W4319300049","https://openalex.org/W4385573415","https://openalex.org/W4386076008","https://openalex.org/W4386076167","https://openalex.org/W4386083063","https://openalex.org/W4386113260","https://openalex.org/W4390190626","https://openalex.org/W4390873483","https://openalex.org/W4390874667","https://openalex.org/W4394596846","https://openalex.org/W4402702917","https://openalex.org/W4402726946","https://openalex.org/W4402727280","https://openalex.org/W4402727512","https://openalex.org/W4402959357","https://openalex.org/W4403922262","https://openalex.org/W4404719524","https://openalex.org/W7133239857"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,52,121,161],"action":[3,163],"anticipation":[4,141],"rely":[5],"heavily":[6],"on":[7,128],"Transformer":[8,116],"architectures":[9],"to":[10,28,86,100],"learn":[11],"discriminative":[12],"representations":[13],"of":[14,108],"the":[15,106,109],"past":[16],"observation,":[17],"incurring":[18],"high":[19,125],"computational":[20],"and":[21,39,95,112,131,133,143],"memory":[22,71,97],"overhead":[23],"that":[24,55,73],"limits":[25],"their":[26,45],"applicability":[27],"long":[29],"videos.":[30],"While":[31],"temporal":[32,110],"processors":[33],"with":[34,64,124,148],"linear":[35,84,92],"complexity":[36,94],"like":[37],"RNNs":[38],"state-space":[40],"models":[41],"offer":[42],"efficient":[43],"alternatives,":[44],"sequential":[46],"nature":[47],"risks":[48],"overlooking":[49],"subtle":[50],"cues":[51,78],"observed":[53],"frames":[54],"could":[56],"enhance":[57],"future":[58,119],"anticipation.":[59],"We":[60],"address":[61],"this":[62],"limitation":[63],"Cross":[65],"Linear":[66],"Attentive":[67],"Memory":[68],"(CLAM),":[69],"a":[70,114],"module":[72],"selectively":[74],"retrieves":[75],"complementary":[76],"context":[77],"from":[79],"frame":[80],"features.":[81],"By":[82],"reformulating":[83],"attention":[85],"replace":[87],"traditional":[88],"cross-attention,":[89],"CLAM":[90],"achieves":[91,158],"computation":[93],"constant":[96],"usage":[98],"relative":[99],"input":[101],"length.":[102],"Finally,":[103],"by":[104],"fusing":[105],"outputs":[107],"processor":[111],"CLAM,":[113],"non-autoregressive":[115],"decoder":[117],"generates":[118],"actions":[120],"one":[122],"shot":[123],"accuracy.":[126],"Experiments":[127],"egocentric":[129],"(EpicKitchens100":[130],"Ego4D)":[132],"third-person":[134],"(Thumos14)":[135],"benchmarks":[136],"demonstrate":[137],"our":[138],"model\u2019s":[139],"superior":[140],"accuracy":[142],"scalability,":[144],"processing":[145],"longer":[146],"sequences":[147],"significantly":[149],"less":[150],"latency":[151],"growth":[152],"than":[153],"alternatives.":[154],"Our":[155],"approach":[156],"also":[157],"promising":[159],"results":[160],"online":[162],"detection.":[164]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-06T00:00:00"}