{"id":"https://openalex.org/W1573393281","doi":"https://doi.org/10.1109/mmsp.2004.1436396","title":"Multimedia/multimodal signal processing, analysis, and understanding","display_name":"Multimedia/multimodal signal processing, analysis, and understanding","publication_year":2005,"publication_date":"2005-06-07","ids":{"openalex":"https://openalex.org/W1573393281","doi":"https://doi.org/10.1109/mmsp.2004.1436396","mag":"1573393281"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2004.1436396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2004.1436396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE 6th Workshop on Multimedia Signal Processing, 2004.","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/A5101457342","display_name":"Thomas S. Huang","orcid":"https://orcid.org/0000-0001-8474-5859"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"T.S. Huang","raw_affiliation_strings":["Beckman Institute for Advanced Science and Technology, University of Illinois, Urbana-Champaign, USA","Beckman Inst. for Adv. Sci. & Technol., Illinois Univ., Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"Beckman Institute for Advanced Science and Technology, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Beckman Inst. for Adv. Sci. & Technol., Illinois Univ., Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101457342"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05073199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.31859999895095825,"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"}},"topics":[{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.31859999895095825,"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":0.8080978393554688},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6265437602996826},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5834205150604248},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5180568695068359},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5135962963104248},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4942503273487091},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47254204750061035},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4615056812763214},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4515026807785034},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4246165454387665},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.4105437099933624},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.41008085012435913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34213095903396606},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.31563299894332886},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.24027442932128906},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.1803669035434723},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.14479216933250427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080978393554688},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6265437602996826},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5834205150604248},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5180568695068359},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5135962963104248},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4942503273487091},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47254204750061035},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4615056812763214},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4515026807785034},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4246165454387665},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.4105437099933624},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.41008085012435913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34213095903396606},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.31563299894332886},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.24027442932128906},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.1803669035434723},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.14479216933250427},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp.2004.1436396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2004.1436396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE 6th Workshop on Multimedia Signal Processing, 2004.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2494533082","https://openalex.org/W1975359510","https://openalex.org/W4214771044","https://openalex.org/W4387698063","https://openalex.org/W4382560817","https://openalex.org/W3110605476","https://openalex.org/W2766269877","https://openalex.org/W2363106653","https://openalex.org/W2020952589"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2],"given.":[3],"\"Multimodal\"":[4],"refers":[5,19],"to":[6,20],"the":[7,21],"different":[8,22],"senses":[9],"(visual,":[10],"audio,":[11,29],"tactile,":[12],"etc.)":[13],"used":[14,90],"in":[15,53,91],"human-computer":[16],"interface.":[17],"\"Multimedia\"":[18],"ways":[23],"of":[24,61,63],"representing":[25],"information":[26],"(text,":[27],"graphics,":[28],"images,":[30],"video,":[31],"etc.).":[32],"A":[33,78],"signal":[34,65],"processing,":[35,66],"analysis,":[36,67],"or":[37,47,50],"understanding":[38],"task":[39],"is":[40,86,89],"called":[41],"multimedia/multimodal":[42,64],"if":[43],"it":[44],"involves":[45],"two":[46],"more":[48],"modalities":[49],"media":[51],"interacting":[52],"nontrivial":[54],"ways.":[55],"We":[56],"shall":[57],"give":[58],"an":[59],"array":[60],"examples":[62],"and":[68,74,80],"understanding,":[69],"including":[70],"audio/visual":[71,75],"speech":[72],"recognition":[73],"emotion":[76],"recognition.":[77],"stable":[79],"robust":[81],"facial":[82],"movement":[83],"tracking":[84],"algorithm":[85],"presented":[87],"which":[88],"both":[92],"tasks.":[93]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}