{"id":"https://openalex.org/W3173161217","doi":"https://doi.org/10.5220/0010832700003124","title":"Hear Me out: Fusional Approaches for Audio Augmented Temporal Action Localization","display_name":"Hear Me out: Fusional Approaches for Audio Augmented Temporal Action Localization","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3173161217","doi":"https://doi.org/10.5220/0010832700003124","mag":"3173161217"},"language":"en","primary_location":{"id":"doi:10.5220/0010832700003124","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010832700003124","pdf_url":null,"source":{"id":"https://openalex.org/S4363608825","display_name":"Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 17th 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":"hybrid","oa_url":"https://doi.org/10.5220/0010832700003124","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055256202","display_name":"Anurag Bagchi","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anurag Bagchi","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad, India, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, India, --- Select a Country ---","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057581764","display_name":"Jazib Mahmood","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jazib Mahmood","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad, India, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, India, --- Select a Country ---","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088785237","display_name":"Dolton Fernandes","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dolton Fernandes","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad, India, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, India, --- Select a Country ---","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038936106","display_name":"Ravi Kiran Sarvadevabhatla","orcid":"https://orcid.org/0000-0003-4134-1154"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ravi Sarvadevabhatla","raw_affiliation_strings":["Center for Visual Information Technology (CVIT), IIIT Hyderabad, India, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Visual Information Technology (CVIT), IIIT Hyderabad, India, --- Select a Country ---","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4157,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.87484915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"144","last_page":"154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9945999979972839,"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/T12290","display_name":"Human Motion and Animation","score":0.9861000180244446,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7916325330734253},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6735965013504028},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6530929803848267},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6367841958999634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5463434457778931},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5270816683769226},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5075196027755737},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4827572703361511},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.412636935710907},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39702141284942627},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33269140124320984},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.22601711750030518},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07779327034950256}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7916325330734253},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6735965013504028},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6530929803848267},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6367841958999634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5463434457778931},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5270816683769226},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5075196027755737},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4827572703361511},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.412636935710907},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39702141284942627},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33269140124320984},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.22601711750030518},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07779327034950256},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0010832700003124","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010832700003124","pdf_url":null,"source":{"id":"https://openalex.org/S4363608825","display_name":"Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0010832700003124","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010832700003124","pdf_url":null,"source":{"id":"https://openalex.org/S4363608825","display_name":"Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W84281818","https://openalex.org/W1536680647","https://openalex.org/W1927052826","https://openalex.org/W2179401333","https://openalex.org/W2238265856","https://openalex.org/W2342662179","https://openalex.org/W2486996822","https://openalex.org/W2507009361","https://openalex.org/W2508191294","https://openalex.org/W2511428026","https://openalex.org/W2526050071","https://openalex.org/W2526479943","https://openalex.org/W2593722617","https://openalex.org/W2597958930","https://openalex.org/W2604730366","https://openalex.org/W2619697695","https://openalex.org/W2789221157","https://openalex.org/W2883915488","https://openalex.org/W2889682419","https://openalex.org/W2893390896","https://openalex.org/W2896538040","https://openalex.org/W2902139928","https://openalex.org/W2949436914","https://openalex.org/W2950534130","https://openalex.org/W2962677524","https://openalex.org/W2962899219","https://openalex.org/W2962960500","https://openalex.org/W2963315828","https://openalex.org/W2963448607","https://openalex.org/W2963470929","https://openalex.org/W2963524571","https://openalex.org/W2964109005","https://openalex.org/W2971680695","https://openalex.org/W2972389745","https://openalex.org/W2982623348","https://openalex.org/W2984507287","https://openalex.org/W2986407524","https://openalex.org/W2997706915","https://openalex.org/W3016452762","https://openalex.org/W3034623254","https://openalex.org/W3085617392","https://openalex.org/W3093287838","https://openalex.org/W3100481960","https://openalex.org/W3107327400","https://openalex.org/W3130662682","https://openalex.org/W3170936177","https://openalex.org/W3172347581","https://openalex.org/W3175514052","https://openalex.org/W3176444885"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"State":[0],"of":[1,38,49,66,95,107],"the":[2,20,32,64,72,96,108],"art":[3,97,109],"architectures":[4],"for":[5,31,61,81,93],"untrimmed":[6],"video":[7,79],"Temporal":[8],"Action":[9],"Localization":[10],"(TAL)":[11],"have":[12],"only":[13],"considered":[14],"RGB":[15],"and":[16,78,119,133,139],"Flow":[17],"modalities,":[18],"leaving":[19],"information-rich":[21],"audio":[22,77],"modality":[23,131],"totally":[24],"unexploited.":[25],"Audio":[26],"fusion":[27,129],"has":[28],"been":[29],"explored":[30],"related":[33],"but":[34,57],"arguably":[35],"easier":[36],"problem":[37],"trimmed":[39],"(clip-level)":[40],"action":[41],"recognition.":[42],"However,":[43],"TAL":[44,99,134],"poses":[45],"a":[46],"unique":[47],"set":[48],"challenges.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"propose":[55],"simple":[56],"effective":[58],"fusion-based":[59],"approaches":[60],"TAL.":[62,83],"To":[63],"best":[65],"our":[67,69,88],"knowledge,":[68],"work":[70],"is":[71],"first":[73],"to":[74],"jointly":[75],"consider":[76],"modalities":[80],"supervised":[82],"We":[84],"experimentally":[85],"show":[86],"that":[87],"schemes":[89],"consistently":[90],"improve":[91],"performance":[92,110],"state":[94,106],"video-only":[98],"approaches.":[100],"Specifically,":[101],"they":[102],"help":[103],"achieve":[104],"new":[105],"on":[111],"large-scale":[112],"benchmark":[113],"datasets":[114],"-":[115],"ActivityNet-1.3":[116],"(54.34":[117],"mAP@0.5)":[118],"THUMOS14":[120],"(57.18":[121],"mAP@0.5).":[122],"Our":[123,136],"experiments":[124],"include":[125],"ablations":[126],"involving":[127],"multiple":[128],"schemes,":[130],"combinations":[132],"architectures.":[135],"code,":[137],"models":[138],"associated":[140],"data":[141],"will":[142],"be":[143],"made":[144],"available.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}