{"id":"https://openalex.org/W3131175560","doi":"https://doi.org/10.5220/0010337306370644","title":"Temporal Bilinear Encoding Network of Audio-visual Features at Low Sampling Rates","display_name":"Temporal Bilinear Encoding Network of Audio-visual Features at Low Sampling Rates","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3131175560","doi":"https://doi.org/10.5220/0010337306370644","mag":"3131175560"},"language":"en","primary_location":{"id":"doi:10.5220/0010337306370644","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010337306370644","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0010337306370644","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048948657","display_name":"Feiyan Hu","orcid":"https://orcid.org/0000-0001-7451-6438"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Feiyan Hu","raw_affiliation_strings":["Insight Centre for Data Analytics, Dublin City University, Dublin, Ireland, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Insight Centre for Data Analytics, Dublin City University, Dublin, Ireland, --- Select a Country ---","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015509923","display_name":"Eva Mohedano","orcid":null},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Eva Mohedano","raw_affiliation_strings":["Insight Centre for Data Analytics, Dublin City University, Dublin, Ireland, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Insight Centre for Data Analytics, Dublin City University, Dublin, Ireland, --- Select a Country ---","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106498523","display_name":"Noel E. O\u2019Connor","orcid":"https://orcid.org/0000-0002-4033-9135"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Noel O\u2019Connor","raw_affiliation_strings":["Insight Centre for Data Analytics, Dublin City University, Dublin, Ireland, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Insight Centre for Data Analytics, Dublin City University, Dublin, Ireland, --- Select a Country ---","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073924795","display_name":"Kevin McGuinness","orcid":"https://orcid.org/0000-0003-1336-6477"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Kevin Mcguinness","raw_affiliation_strings":["Insight Centre for Data Analytics, Dublin City University, Dublin, Ireland, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Insight Centre for Data Analytics, Dublin City University, Dublin, Ireland, --- Select a Country ---","institution_ids":["https://openalex.org/I42934936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048948657"],"corresponding_institution_ids":["https://openalex.org/I42934936"],"apc_list":null,"apc_paid":null,"fwci":0.4571,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58627451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"637","last_page":"644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9984999895095825,"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/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/pooling","display_name":"Pooling","score":0.826265811920166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8207747936248779},{"id":"https://openalex.org/keywords/bilinear-interpolation","display_name":"Bilinear interpolation","score":0.7333966493606567},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6580517292022705},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.61726975440979},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5257276296615601},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5081799030303955},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4542768597602844},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36072322726249695},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.30318474769592285}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.826265811920166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8207747936248779},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.7333966493606567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6580517292022705},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.61726975440979},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5257276296615601},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5081799030303955},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4542768597602844},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36072322726249695},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30318474769592285},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0010337306370644","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010337306370644","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0010337306370644","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010337306370644","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1522734439","https://openalex.org/W1755205674","https://openalex.org/W1923404803","https://openalex.org/W1966385142","https://openalex.org/W2016053056","https://openalex.org/W2033740597","https://openalex.org/W2104657103","https://openalex.org/W2105527258","https://openalex.org/W2146897752","https://openalex.org/W2156303437","https://openalex.org/W2170653751","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2235034809","https://openalex.org/W2462996230","https://openalex.org/W2507009361","https://openalex.org/W2526050071","https://openalex.org/W2556024076","https://openalex.org/W2570343428","https://openalex.org/W2608988379","https://openalex.org/W2745519816","https://openalex.org/W2752386593","https://openalex.org/W2883502031","https://openalex.org/W2890234836","https://openalex.org/W2894879265","https://openalex.org/W2952363938","https://openalex.org/W2963015194","https://openalex.org/W2963066927","https://openalex.org/W2963216700","https://openalex.org/W2963370182","https://openalex.org/W2963524571","https://openalex.org/W4300614726"],"related_works":["https://openalex.org/W2950524887","https://openalex.org/W2883502031","https://openalex.org/W2261271299","https://openalex.org/W2963066927","https://openalex.org/W4280638452","https://openalex.org/W3111811104","https://openalex.org/W4380083739","https://openalex.org/W2964944724","https://openalex.org/W4285020665","https://openalex.org/W3160506688"],"abstract_inverted_index":{"Current":[0],"deep":[1],"learning":[2],"based":[3],"video":[4,28],"classification":[5,29,95],"architectures":[6],"are":[7],"typically":[8],"trained":[9],"end-to-end":[10],"on":[11,66,91,122],"large":[12],"volumes":[13],"of":[14,88,108],"data":[15],"and":[16,48,57,118,145],"require":[17],"extensive":[18],"computational":[19,137],"resources.This":[20],"paper":[21],"aims":[22],"to":[23,83,130],"exploit":[24,105],"audio-visual":[25],"information":[26,53],"in":[27,81],"with":[30,72,111],"a":[31,100],"1":[32,126],"frame":[33],"per":[34],"second":[35],"sampling":[36,74],"rate.We":[37,75],"propose":[38],"Temporal":[39],"Bilinear":[40],"Encoding":[41],"Networks":[42],"(TBEN)":[43],"for":[44,70,142],"encoding":[45],"both":[46,143],"audio":[47],"visual":[49,116],"long":[50],"range":[51],"temporal":[52,68],"using":[54,97],"bilinear":[55,59],"pooling":[56,60,65],"demonstrate":[58],"is":[61],"better":[62],"than":[63,139],"average":[64],"the":[67,78,86,89,92,106],"dimension":[69],"videos":[71],"low":[73],"also":[76,104],"embed":[77],"label":[79],"hierarchy":[80],"TBEN":[82,98,110],"further":[84],"improve":[85],"robustness":[87],"classifier.Experiments":[90],"FGA240":[93],"fine-grained":[94],"dataset":[96],"achieve":[99,128],"new":[101],"state-of-the-art":[102],"(hit@1=47.95%).We":[103],"possibility":[107],"incorporating":[109],"multiple":[112],"decoupled":[113],"modalities":[114],"like":[115],"semantic":[117],"motion":[119],"features:":[120],"experiments":[121],"UCF101":[123],"sampled":[124],"at":[125],"FPS":[127],"close":[129],"state-ofthe-art":[131],"accuracy":[132],"(hit@1=91.03%)while":[133],"requiring":[134],"significantly":[135],"less":[136],"resources":[138],"competing":[140],"approaches":[141],"training":[144],"prediction.":[146]},"counts_by_year":[{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}