{"id":"https://openalex.org/W2112166433","doi":"https://doi.org/10.1109/icme.2000.869668","title":"Learning from multimodal observations","display_name":"Learning from multimodal observations","publication_year":2002,"publication_date":"2002-11-07","ids":{"openalex":"https://openalex.org/W2112166433","doi":"https://doi.org/10.1109/icme.2000.869668","mag":"2112166433"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2000.869668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2000.869668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532)","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/A5004281470","display_name":"Deb Roy","orcid":"https://orcid.org/0000-0002-2780-4768"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"D. Roy","raw_affiliation_strings":["Media Laboratory, MIT, Cambridge, MA, USA","Media Lab., MIT, Cambridge, MA, , USA"],"affiliations":[{"raw_affiliation_string":"Media Laboratory, MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210122954"]},{"raw_affiliation_string":"Media Lab., MIT, Cambridge, MA, , USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5004281470"],"corresponding_institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":2.5569,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.90512279,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"579","last_page":"582"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9914000034332275,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.982200026512146,"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":0.6337667107582092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3866926431655884},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37922707200050354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6337667107582092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3866926431655884},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37922707200050354}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2000.869668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2000.869668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.42.7992","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.42.7992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vismod.www.media.mit.edu/people/dkroy/papers/pdf/ieee_multimedia2000.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W110802701","https://openalex.org/W1519957219","https://openalex.org/W1540596022","https://openalex.org/W1942647574","https://openalex.org/W2033010331","https://openalex.org/W2048679005","https://openalex.org/W2062526508","https://openalex.org/W2099111195","https://openalex.org/W2107917162","https://openalex.org/W2110871230","https://openalex.org/W2126493631","https://openalex.org/W2130607791","https://openalex.org/W2131030609","https://openalex.org/W2131709365","https://openalex.org/W2135884851","https://openalex.org/W2140661818","https://openalex.org/W2140830074","https://openalex.org/W2151856467","https://openalex.org/W2158069733","https://openalex.org/W2161176841","https://openalex.org/W2171144711","https://openalex.org/W4237938692","https://openalex.org/W6683630705"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2045456578","https://openalex.org/W2918883224","https://openalex.org/W3106945349","https://openalex.org/W3204394973","https://openalex.org/W2278205256","https://openalex.org/W2883555950","https://openalex.org/W4246426965","https://openalex.org/W2051154247","https://openalex.org/W3005892291"],"abstract_inverted_index":{"Human-computer":[0],"interaction":[1],"based":[2],"on":[3,13],"recognition":[4],"of":[5,29,34,51,62],"speech,":[6],"gestures,":[7],"and":[8,25,77],"other":[9],"natural":[10],"modalities":[11],"is":[12,39,79],"the":[14,41,49],"rise.":[15],"Recognition":[16],"technologies":[17],"are":[18],"typically":[19],"developed":[20],"in":[21,43],"a":[22],"statistical":[23],"framework":[24],"require":[26],"large":[27],"amounts":[28],"training":[30],"data.":[31],"The":[32],"cost":[33],"collecting":[35],"manually":[36],"annotated":[37],"data":[38,55],"usually":[40],"bottleneck":[42],"developing":[44],"such":[45],"systems.":[46],"We":[47],"explore":[48],"idea":[50],"learning":[52,71],"from":[53,74],"unannotated":[54],"by":[56,68],"leveraging":[57],"information":[58],"across":[59],"multiple":[60],"modes":[61],"input.":[63],"A":[64],"working":[65],"system":[66],"inspired":[67],"infant":[69],"language":[70],"which":[72],"learns":[73],"untranscribed":[75],"speech":[76],"images":[78],"presented.":[80]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}