{"id":"https://openalex.org/W2999201579","doi":"https://doi.org/10.1109/ism46123.2019.00025","title":"Sensory Media Association through Reciprocating Training","display_name":"Sensory Media Association through Reciprocating Training","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2999201579","doi":"https://doi.org/10.1109/ism46123.2019.00025","mag":"2999201579"},"language":"en","primary_location":{"id":"doi:10.1109/ism46123.2019.00025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ism46123.2019.00025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Multimedia (ISM)","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/A5100336322","display_name":"Qiong Liu","orcid":"https://orcid.org/0000-0003-1856-6160"},"institutions":[{"id":"https://openalex.org/I26274970","display_name":"FX Palo Alto Laboratory","ror":"https://ror.org/05ef4zt88","country_code":"US","type":"facility","lineage":["https://openalex.org/I26274970"]},{"id":"https://openalex.org/I4210132870","display_name":"Xerox (United States)","ror":"https://ror.org/03jwzwq24","country_code":"US","type":"company","lineage":["https://openalex.org/I4210132870"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qiong Liu","raw_affiliation_strings":["Fuji-Xerox Palo Lab (FXPAL) 3174 Porter Drive, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Fuji-Xerox Palo Lab (FXPAL) 3174 Porter Drive, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I26274970","https://openalex.org/I4210132870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101861282","display_name":"Hao Hu","orcid":"https://orcid.org/0000-0002-9422-750X"},"institutions":[{"id":"https://openalex.org/I26274970","display_name":"FX Palo Alto Laboratory","ror":"https://ror.org/05ef4zt88","country_code":"US","type":"facility","lineage":["https://openalex.org/I26274970"]},{"id":"https://openalex.org/I4210132870","display_name":"Xerox (United States)","ror":"https://ror.org/03jwzwq24","country_code":"US","type":"company","lineage":["https://openalex.org/I4210132870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Hu","raw_affiliation_strings":["Fuji-Xerox Palo Lab (FXPAL) 3174 Porter Drive, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Fuji-Xerox Palo Lab (FXPAL) 3174 Porter Drive, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I26274970","https://openalex.org/I4210132870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067897434","display_name":"Ray Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ray Yuan","raw_affiliation_strings":["EECS Department, University of California Berkeley 387 Soda Hall, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"EECS Department, University of California Berkeley 387 Soda Hall, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100712432","display_name":"Yanxia Zhang","orcid":"https://orcid.org/0000-0002-6610-5265"},"institutions":[{"id":"https://openalex.org/I4210132870","display_name":"Xerox (United States)","ror":"https://ror.org/03jwzwq24","country_code":"US","type":"company","lineage":["https://openalex.org/I4210132870"]},{"id":"https://openalex.org/I26274970","display_name":"FX Palo Alto Laboratory","ror":"https://ror.org/05ef4zt88","country_code":"US","type":"facility","lineage":["https://openalex.org/I26274970"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanxia Zhang","raw_affiliation_strings":["Fuji-Xerox Palo Lab (FXPAL) 3174 Porter Drive, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Fuji-Xerox Palo Lab (FXPAL) 3174 Porter Drive, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I26274970","https://openalex.org/I4210132870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102965312","display_name":"Yanying Chen","orcid":"https://orcid.org/0000-0001-7996-0677"},"institutions":[{"id":"https://openalex.org/I26274970","display_name":"FX Palo Alto Laboratory","ror":"https://ror.org/05ef4zt88","country_code":"US","type":"facility","lineage":["https://openalex.org/I26274970"]},{"id":"https://openalex.org/I4210132870","display_name":"Xerox (United States)","ror":"https://ror.org/03jwzwq24","country_code":"US","type":"company","lineage":["https://openalex.org/I4210132870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan-Ying Chen","raw_affiliation_strings":["Fuji-Xerox Palo Lab (FXPAL) 3174 Porter Drive, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Fuji-Xerox Palo Lab (FXPAL) 3174 Porter Drive, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I26274970","https://openalex.org/I4210132870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100336322"],"corresponding_institution_ids":["https://openalex.org/I26274970","https://openalex.org/I4210132870"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16472321,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"108","last_page":"1083"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9926999807357788,"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":0.9926999807357788,"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/T10860","display_name":"Speech and Audio Processing","score":0.9854999780654907,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.761482834815979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7021934986114502},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6517159938812256},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.6125059127807617},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5652795433998108},{"id":"https://openalex.org/keywords/stimulus-modality","display_name":"Stimulus modality","score":0.5391491055488586},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5218811631202698},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5076979398727417},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49388939142227173},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4786478281021118},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4389566481113434},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.41164594888687134},{"id":"https://openalex.org/keywords/sensory-system","display_name":"Sensory system","score":0.3540722727775574},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35149824619293213},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34316352009773254},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.16369229555130005},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10092797875404358}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.761482834815979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7021934986114502},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6517159938812256},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.6125059127807617},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5652795433998108},{"id":"https://openalex.org/C26486553","wikidata":"https://www.wikidata.org/wiki/Q371870","display_name":"Stimulus modality","level":3,"score":0.5391491055488586},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5218811631202698},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5076979398727417},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49388939142227173},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4786478281021118},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4389566481113434},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.41164594888687134},{"id":"https://openalex.org/C94487597","wikidata":"https://www.wikidata.org/wiki/Q11101","display_name":"Sensory system","level":2,"score":0.3540722727775574},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35149824619293213},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34316352009773254},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.16369229555130005},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10092797875404358},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ism46123.2019.00025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ism46123.2019.00025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Multimedia (ISM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1527571715","https://openalex.org/W2001771035","https://openalex.org/W2184188583","https://openalex.org/W2414857070","https://openalex.org/W2724105803","https://openalex.org/W2796933306","https://openalex.org/W2963902314","https://openalex.org/W6686207219","https://openalex.org/W6740076004"],"related_works":["https://openalex.org/W1540085252","https://openalex.org/W2006830765","https://openalex.org/W2593242293","https://openalex.org/W2051102306","https://openalex.org/W2237537322","https://openalex.org/W2155838649","https://openalex.org/W2063505906","https://openalex.org/W2950678851","https://openalex.org/W4301248618","https://openalex.org/W2937381246"],"abstract_inverted_index":{"Machine":[0],"learning":[1,11,18,21,36,42,61,74,88,94,135],"achieved":[2],"great":[3],"progress":[4],"in":[5,122,192],"recent":[6],"years.":[7],"However,":[8],"state-of-the-art":[9],"machine":[10,35,162],"systems":[12,19],"are":[13,100],"still":[14],"far":[15],"behind":[16],"biological":[17,60],"on":[20],"directly":[22],"from":[23,37,140,165],"sensors":[24],"without":[25],"offline":[26],"labeling.":[27],"This":[28],"paper":[29],"proposes":[30],"an":[31],"approach":[32,159],"for":[33,87,93,113,148,154],"automating":[34],"multi-modal":[38],"sensors.":[39],"In":[40],"this":[41],"setup,":[43],"the":[44,73,104,126,134,157,181,193],"system":[45,62,81,127],"has":[46],"no":[47],"access":[48],"to":[49,58,102,132,163],"any":[50],"human":[51],"labeling":[52],"tool":[53],"which":[54],"is":[55],"not":[56],"available":[57],"a":[59,65,68,145,161],"such":[63],"as":[64],"dog":[66],"or":[67,170],"newborn":[69],"baby.":[70],"We":[71,179],"tested":[72],"proposal":[75],"with":[76,184],"audiovisual":[77],"data.":[78],"The":[79],"testing":[80],"contains":[82],"two":[83,108,169],"deep":[84,98],"autoencoders,":[85,109],"one":[86,130],"speech":[89],"representations":[90],"and":[91,116,188,199],"another":[92,137],"image":[95,155],"representations.":[96],"Two":[97],"networks":[99],"trained":[101],"bridge":[103],"latent":[105,124],"spaces":[106],"of":[107,136,168],"yielding":[110],"representation":[111],"mappings":[112],"both":[114,123],"speech-to-image":[115],"image-to-speech.":[117],"To":[118],"improve":[119],"feature":[120],"clustering":[121],"spaces,":[125],"alternately":[128],"uses":[129,144],"modality":[131,147],"guide":[133],"modality.":[138],"Different":[139],"traditional":[141],"technology":[142],"that":[143],"fixed":[146],"supervision":[149],"(e.g.":[150],"using":[151],"text":[152],"labels":[153],"classification),":[156],"proposed":[158,182],"facilitates":[160],"learn":[164],"sensory":[166],"inputs":[167],"more":[171],"modalities":[172],"through":[173],"alternating":[174],"guidance":[175],"among":[176],"these":[177],"modalities.":[178],"evaluate":[180],"model":[183],"MNIST":[185],"digit":[186,190],"images":[187],"corresponding":[189],"speeches":[191],"Google":[194],"Command":[195],"Digit":[196],"Dataset":[197],"(GCDD)":[198],"got":[200],"very":[201],"promising":[202],"results.":[203]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}