{"id":"https://openalex.org/W2051721233","doi":"https://doi.org/10.1145/2647868.2654969","title":"Multimodal Dynamic Networks for Gesture Recognition","display_name":"Multimodal Dynamic Networks for Gesture Recognition","publication_year":2014,"publication_date":"2014-11-03","ids":{"openalex":"https://openalex.org/W2051721233","doi":"https://doi.org/10.1145/2647868.2654969","mag":"2051721233"},"language":"en","primary_location":{"id":"doi:10.1145/2647868.2654969","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2647868.2654969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Multimedia","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/A5100599890","display_name":"Di Wu","orcid":"https://orcid.org/0000-0002-4753-8161"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Di Wu","raw_affiliation_strings":["The University of Sheffield, Sheffield, United Kingdom"],"affiliations":[{"raw_affiliation_string":"The University of Sheffield, Sheffield, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082634513","display_name":"Ling Shao","orcid":"https://orcid.org/0000-0002-8264-6117"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ling Shao","raw_affiliation_strings":["The University of Sheffield, Sheffield, United Kingdom"],"affiliations":[{"raw_affiliation_string":"The University of Sheffield, Sheffield, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100599890"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":2.9182,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.90642044,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"945","last_page":"948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9951000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.8381319046020508},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8163376450538635},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.6516594886779785},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6076547503471375},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5811960697174072},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5807704925537109},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.579862117767334},{"id":"https://openalex.org/keywords/sign-language","display_name":"Sign language","score":0.5541175007820129},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5443493723869324},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4983179569244385},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4925718903541565},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4817364513874054},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4634513556957245},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.45064622163772583},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4496866762638092},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4191342890262604},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.39244621992111206}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8381319046020508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8163376450538635},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.6516594886779785},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6076547503471375},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5811960697174072},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5807704925537109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.579862117767334},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.5541175007820129},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5443493723869324},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4983179569244385},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4925718903541565},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4817364513874054},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4634513556957245},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.45064622163772583},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4496866762638092},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4191342890262604},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39244621992111206},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2647868.2654969","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2647868.2654969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.671.4993","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.671.4993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://lshao.staff.shef.ac.uk/pub/Multimodal_ACMMM2014.pdf","raw_type":"text"},{"id":"pmh:oai:nrl.northumbria.ac.uk:22928","is_oa":false,"landing_page_url":"http://nrl.northumbria.ac.uk/id/eprint/22928/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401884","display_name":"Northumbria Research Link (Northumbria University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32394136","host_organization_name":"Northumbria University","host_organization_lineage":["https://openalex.org/I32394136"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Book Section"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:62410","is_oa":false,"landing_page_url":"https://ueaeprints.uea.ac.uk/id/eprint/62410/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Book Section"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W146900863","https://openalex.org/W154472438","https://openalex.org/W1904365287","https://openalex.org/W1979378996","https://openalex.org/W1985469025","https://openalex.org/W1993882792","https://openalex.org/W1995113806","https://openalex.org/W2030061193","https://openalex.org/W2031342017","https://openalex.org/W2073139398","https://openalex.org/W2108036388","https://openalex.org/W2150111138","https://openalex.org/W2164587673","https://openalex.org/W2168570452","https://openalex.org/W2184188583","https://openalex.org/W2973289689","https://openalex.org/W4254181784","https://openalex.org/W6686207219"],"related_works":["https://openalex.org/W3040456104","https://openalex.org/W3177712091","https://openalex.org/W4390482156","https://openalex.org/W4384518601","https://openalex.org/W2046356236","https://openalex.org/W4378804484","https://openalex.org/W2616157432","https://openalex.org/W2541705465","https://openalex.org/W2185431043","https://openalex.org/W2921243003"],"abstract_inverted_index":{"Multimodal":[0],"input":[1,67],"is":[2],"a":[3,20],"real-world":[4],"situation":[5],"in":[6],"gesture":[7,30],"recognition":[8],"applications":[9],"such":[10],"as":[11],"sign":[12],"language":[13],"recognition.":[14,31],"In":[15,95],"this":[16],"paper,":[17],"we":[18,55,97],"propose":[19],"novel":[21],"bi-modal":[22],"(audio":[23],"and":[24,45,112],"skeleton":[25],"joints)":[26],"dynamic":[27,34],"network":[28],"for":[29,61,77,86],"First,":[32],"state-of-the-art":[33],"Deep":[35],"Belief":[36],"Networks":[37],"are":[38,84],"deployed":[39],"to":[40,75,91],"extract":[41,104],"high":[42],"level":[43],"audio":[44],"skeletal":[46],"joints":[47],"representations.":[48],"Then,":[49],"instead":[50],"of":[51,59,122],"traditional":[52,120],"late":[53,123],"fusion,":[54],"adopt":[56],"another":[57],"layer":[58],"perceptron":[60],"cross":[62],"modality":[63],"learning":[64,102],"taking":[65],"the":[66,80,88,113,119],"from":[68],"each":[69],"individual":[70,110],"net's":[71],"penultimate":[72],"layer.":[73],"Finally,":[74],"account":[76],"temporal":[78],"dynamics,":[79],"learned":[81],"shared":[82,107],"representations":[83],"used":[85],"estimating":[87],"emission":[89],"probability":[90],"infer":[92],"action":[93],"sequences.":[94],"particular,":[96],"demonstrate":[98],"that":[99],"multimodal":[100],"feature":[101],"will":[103],"semantically":[105],"meaningful":[106],"representations,":[108],"outperforming":[109],"modalities,":[111],"early":[114],"fusion":[115],"scheme's":[116],"efficacy":[117],"against":[118],"method":[121],"fusion.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}