{"id":"https://openalex.org/W3033715838","doi":"https://doi.org/10.1145/3372278.3390740","title":"One Perceptron to Rule Them All: Language, Vision, Audio and Speech","display_name":"One Perceptron to Rule Them All: Language, Vision, Audio and Speech","publication_year":2020,"publication_date":"2020-06-02","ids":{"openalex":"https://openalex.org/W3033715838","doi":"https://doi.org/10.1145/3372278.3390740","mag":"3033715838"},"language":"en","primary_location":{"id":"doi:10.1145/3372278.3390740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2117/192196","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051863471","display_name":"Xavier Gir\u00f3-i-Nieto","orcid":"https://orcid.org/0000-0002-9935-5332"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Xavier Giro-i-Nieto","raw_affiliation_strings":["Universitat Politecnica de Catalunya, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Politecnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051863471"],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05081486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996399998664856,"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":0.992900013923645,"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/closed-captioning","display_name":"Closed captioning","score":0.8826483488082886},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.850197970867157},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6581066250801086},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5306835174560547},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5283190608024597},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.49897217750549316},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.48401638865470886},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4437513053417206},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4321352243423462},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.42963501811027527},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4279303550720215},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1863863468170166}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8826483488082886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.850197970867157},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6581066250801086},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5306835174560547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5283190608024597},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.49897217750549316},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.48401638865470886},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4437513053417206},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4321352243423462},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.42963501811027527},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4279303550720215},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1863863468170166},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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":2,"locations":[{"id":"doi:10.1145/3372278.3390740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/192196","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/192196","pdf_url":null,"source":{"id":"https://openalex.org/S4210207057","display_name":"QRU Quaderns de Recerca en Urbanisme","issn_l":"2014-9689","issn":["2014-9689","2385-6777"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310322448","host_organization_name":"Q71272178","host_organization_lineage":["https://openalex.org/P4310322448"],"host_organization_lineage_names":["Q71272178"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference lecture"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/192196","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/192196","pdf_url":null,"source":{"id":"https://openalex.org/S4210207057","display_name":"QRU Quaderns de Recerca en Urbanisme","issn_l":"2014-9689","issn":["2014-9689","2385-6777"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310322448","host_organization_name":"Q71272178","host_organization_lineage":["https://openalex.org/P4310322448"],"host_organization_lineage_names":["Q71272178"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference lecture"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8700000047683716}],"awards":[{"id":"https://openalex.org/G2709078255","display_name":null,"funder_award_id":"TEC2016-75976-R","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G480096916","display_name":null,"funder_award_id":"TEC2016-75976-R","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"}],"funders":[{"id":"https://openalex.org/F4320321505","display_name":"Generalitat de Catalunya","ror":"https://ror.org/01bg62x04"},{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1895577753","https://openalex.org/W1923211482","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2112796928","https://openalex.org/W2123024445","https://openalex.org/W2163605009","https://openalex.org/W2504108613","https://openalex.org/W2546190447","https://openalex.org/W2551572271","https://openalex.org/W2584032004","https://openalex.org/W2737041163","https://openalex.org/W2783457476","https://openalex.org/W2795151422","https://openalex.org/W2922538097","https://openalex.org/W2949382160","https://openalex.org/W2949888546","https://openalex.org/W2949999304","https://openalex.org/W2950276680","https://openalex.org/W2952746495","https://openalex.org/W2962866381","https://openalex.org/W2963019222","https://openalex.org/W2963115079","https://openalex.org/W2963403868","https://openalex.org/W2963902314","https://openalex.org/W2964171275","https://openalex.org/W3034765865","https://openalex.org/W3099884890"],"related_works":["https://openalex.org/W2783312365","https://openalex.org/W1872130062","https://openalex.org/W1806995473","https://openalex.org/W2293457016","https://openalex.org/W159132833","https://openalex.org/W2977842567","https://openalex.org/W3185852197","https://openalex.org/W38394648","https://openalex.org/W180507639","https://openalex.org/W3033715838"],"abstract_inverted_index":{"Deep":[0],"neural":[1,51,60],"networks":[2],"have":[3,77],"boosted":[4],"the":[5,34,46,58,73],"convergence":[6],"of":[7,33,37,43,49],"multimedia":[8],"data":[9],"analytics":[10],"in":[11,18],"a":[12,38],"unified":[13],"framework":[14],"shared":[15],"by":[16],"practitioners":[17],"natural":[19],"language,":[20],"vision":[21],"and":[22,40,64,68],"speech.":[23],"Image":[24],"captioning,":[25],"lip":[26],"reading":[27],"or":[28],"video":[29],"sonorization":[30],"are":[31],"some":[32],"first":[35],"applications":[36],"new":[39],"exciting":[41],"field":[42],"research":[44],"exploiting":[45],"generalization":[47],"properties":[48],"deep":[50],"representation.":[52],"This":[53],"tutorial":[54],"will":[55],"firstly":[56],"review":[57,72],"basic":[59],"architectures":[61],"to":[62,70],"encode":[63],"decode":[65],"vision,":[66],"text":[67],"audio,":[69],"later":[71],"those":[74],"models":[75],"that":[76],"successfully":[78],"translated":[79],"information":[80],"across":[81],"modalities.":[82]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2020-06-12T00:00:00"}
