{"id":"https://openalex.org/W2058549804","doi":"https://doi.org/10.1109/icassp.2013.6638341","title":"Benchmarking methods for audio-visual recognition using tiny training sets","display_name":"Benchmarking methods for audio-visual recognition using tiny training sets","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2058549804","doi":"https://doi.org/10.1109/icassp.2013.6638341","mag":"2058549804"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-00861645","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066621495","display_name":"Xavier Alameda-Pineda","orcid":"https://orcid.org/0000-0002-5354-1084"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xavier Alameda-Pineda","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, Universit\u00e9 de Grenoble, France","INRIA Grenoble Rho\u0301ne-Alpes, Grenoble, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, Universit\u00e9 de Grenoble, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I899635006"]},{"raw_affiliation_string":"INRIA Grenoble Rho\u0301ne-Alpes, Grenoble, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063541182","display_name":"Jordi S\u00e0nchez-Riera","orcid":"https://orcid.org/0000-0002-4803-5742"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jordi Sanchez-Riera","raw_affiliation_strings":["INRIA Grenoble-Rh\u00f4ne-Alpes, France","INRIA Grenoble Rho\u0301ne-Alpes, Grenoble, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble-Rh\u00f4ne-Alpes, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"INRIA Grenoble Rho\u0301ne-Alpes, Grenoble, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078307335","display_name":"Radu Horaud","orcid":"https://orcid.org/0000-0001-5232-024X"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Radu Horaud","raw_affiliation_strings":["INRIA Grenoble-Rh\u00f4ne-Alpes, France","INRIA Grenoble Rho\u0301ne-Alpes, Grenoble, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble-Rh\u00f4ne-Alpes, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"INRIA Grenoble Rho\u0301ne-Alpes, Grenoble, France","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"99","issue":null,"first_page":"3662","last_page":"3666"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.995199978351593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8126790523529053},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8081302046775818},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7788650393486023},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6627278327941895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6010775566101074},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5662682056427002},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.526482105255127},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5203737616539001},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5052860379219055},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4991469383239746},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47519195079803467},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.46841850876808167},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4670020341873169},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4466698467731476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8126790523529053},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8081302046775818},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7788650393486023},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6627278327941895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6010775566101074},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5662682056427002},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.526482105255127},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5203737616539001},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5052860379219055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4991469383239746},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47519195079803467},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.46841850876808167},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4670020341873169},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4466698467731476},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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":3,"locations":[{"id":"doi:10.1109/icassp.2013.6638341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.300.4676","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.300.4676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://perception.inrialpes.fr/Publications/2013/ASH13/AlamedaSanchezHoraudICASSP13.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00861645v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00861645","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2013 - IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE Signal Processing Society, May 2013, Vancouver, Canada. pp.3662-3666, ⟨10.1109/ICASSP.2013.6638341⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00861645v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00861645","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2013 - IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE Signal Processing Society, May 2013, Vancouver, Canada. pp.3662-3666, ⟨10.1109/ICASSP.2013.6638341⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W77254694","https://openalex.org/W1571024744","https://openalex.org/W1604034532","https://openalex.org/W1998891211","https://openalex.org/W2020163092","https://openalex.org/W2025954386","https://openalex.org/W2056197638","https://openalex.org/W2083270451","https://openalex.org/W2130239535","https://openalex.org/W2131486730","https://openalex.org/W2141939040","https://openalex.org/W6633893416"],"related_works":["https://openalex.org/W1487808658","https://openalex.org/W3172695526","https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W2169074127","https://openalex.org/W2163707935","https://openalex.org/W83146503","https://openalex.org/W202723009","https://openalex.org/W2188612292","https://openalex.org/W4206462905"],"abstract_inverted_index":{"The":[0,42],"problem":[1],"of":[2,38,51,68,75,87,102],"choosing":[3],"a":[4,26,52,84,90,99],"classifier":[5],"for":[6,58],"audio-visual":[7],"command":[8],"recognition":[9],"is":[10,44,83],"addressed.":[11],"Because":[12],"such":[13],"commands":[14,24],"are":[15],"culture-":[16],"and":[17,40,48,66],"user-dependant,":[18],"methods":[19],"need":[20],"to":[21,98],"learn":[22],"new":[23],"from":[25],"few":[27],"examples.":[28],"We":[29,56],"benchmark":[30],"three":[31],"state-of-the-art":[32],"discriminative":[33],"classifiers":[34],"based":[35],"on":[36,46],"bag":[37],"words":[39],"SVM.":[41],"comparison":[43],"made":[45],"monocular":[47],"monaural":[49],"recordings":[50],"publicly":[53],"available":[54],"dataset.":[55],"seek":[57],"the":[59,69,73],"best":[60],"trade":[61],"off":[62],"between":[63],"speed,":[64],"robustness":[65],"size":[67],"training":[70],"set.":[71],"In":[72],"light":[74],"over":[76],"150,000":[77],"experiments,":[78],"we":[79],"conclude":[80],"that":[81,93],"this":[82],"promising":[85],"direction":[86],"work":[88],"towards":[89],"flexible":[91],"methodology":[92],"must":[94],"be":[95],"easily":[96],"adaptable":[97],"large":[100],"variety":[101],"users.":[103]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}