{"id":"https://openalex.org/W2895368507","doi":"https://doi.org/10.1109/icassp.2019.8683898","title":"Dense Multimodal Fusion for Hierarchically Joint Representation","display_name":"Dense Multimodal Fusion for Hierarchically Joint Representation","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2895368507","doi":"https://doi.org/10.1109/icassp.2019.8683898","mag":"2895368507"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100670614","display_name":"Di Hu","orcid":"https://orcid.org/0000-0002-7118-6733"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Hu","raw_affiliation_strings":["School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an, Shaanxi, 710072, P. R. China","School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi'an, Shaanxi, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an, Shaanxi, 710072, P. R. China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi'an, Shaanxi, P. R. China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086326894","display_name":"Chengze Wang","orcid":"https://orcid.org/0000-0003-2349-6427"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengze Wang","raw_affiliation_strings":["School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an, Shaanxi, 710072, P. R. China","School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi'an, Shaanxi, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an, Shaanxi, 710072, P. R. China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi'an, Shaanxi, P. R. China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003222421","display_name":"Feiping Nie","orcid":"https://orcid.org/0000-0002-0871-6519"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiping Nie","raw_affiliation_strings":["School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an, Shaanxi, 710072, P. R. China","School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi'an, Shaanxi, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an, Shaanxi, 710072, P. R. China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi'an, Shaanxi, P. R. China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100740143","display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0002-0019-4197"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an, Shaanxi, 710072, P. R. China","School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi'an, Shaanxi, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi’an, Shaanxi, 710072, P. R. China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi'an, Shaanxi, P. R. China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":4.7788,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.96152376,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3941","last_page":"3945"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973999857902527,"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":0.7906384468078613},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7118993997573853},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.667992115020752},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6081439256668091},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5774418115615845},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5374247431755066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5344613790512085},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.505151093006134},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.49493879079818726},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.45954933762550354},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4569062292575836},{"id":"https://openalex.org/keywords/stacking","display_name":"Stacking","score":0.4178513288497925},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3758751451969147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7906384468078613},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7118993997573853},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.667992115020752},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6081439256668091},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5774418115615845},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5374247431755066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5344613790512085},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.505151093006134},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.49493879079818726},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.45954933762550354},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4569062292575836},{"id":"https://openalex.org/C33347731","wikidata":"https://www.wikidata.org/wiki/Q285210","display_name":"Stacking","level":2,"score":0.4178513288497925},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3758751451969147},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C46141821","wikidata":"https://www.wikidata.org/wiki/Q209402","display_name":"Nuclear magnetic resonance","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W142803501","https://openalex.org/W1531976713","https://openalex.org/W1964073652","https://openalex.org/W1989085630","https://openalex.org/W2022799064","https://openalex.org/W2055098062","https://openalex.org/W2088998933","https://openalex.org/W2106277773","https://openalex.org/W2112796928","https://openalex.org/W2148463593","https://openalex.org/W2164530430","https://openalex.org/W2164587673","https://openalex.org/W2184188583","https://openalex.org/W2474638510","https://openalex.org/W2476034201","https://openalex.org/W2512032049","https://openalex.org/W2546919788","https://openalex.org/W2613677041","https://openalex.org/W2767290858","https://openalex.org/W2913932916","https://openalex.org/W2962900249","https://openalex.org/W4285719527","https://openalex.org/W6605737493","https://openalex.org/W6606244218","https://openalex.org/W6631751486","https://openalex.org/W6681753794","https://openalex.org/W6686207219","https://openalex.org/W6694692806","https://openalex.org/W6721087566"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Multiple":[0],"modalities":[1],"can":[2,80,146],"provide":[3],"more":[4,148],"valuable":[5],"information":[6],"than":[7],"single":[8],"one":[9],"by":[10,31,55],"describing":[11],"the":[12,24,40,53,82,88,100,111],"same":[13],"contents":[14],"in":[15,76,84,115,119],"various":[16],"ways.":[17],"Previous":[18],"methods":[19],"mainly":[20],"focus":[21],"on":[22,132],"fusing":[23],"shallow":[25],"features":[26],"or":[27],"high-level":[28],"representations":[29,54,75],"generated":[30],"unimodal":[32],"deep":[33],"networks,":[34,64],"which":[35,65,117],"only":[36],"capture":[37,81],"part":[38],"of":[39],"hierarchical":[41,103],"correlations":[42,83],"across":[43],"modalities.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"propose":[49],"to":[50,98,110],"densely":[51],"integrate":[52],"greedily":[56],"stacking":[57],"multiple":[58,112],"shared":[59,78,91],"layers":[60,79,92],"between":[61,90],"different":[62,77,85],"modality-specific":[63],"is":[66],"named":[67],"as":[68],"Dense":[69],"Multimodal":[70],"Fusion":[71],"(DMF).":[72],"The":[73,139],"joint":[74,150],"levels,":[86],"and":[87,125,136],"connection":[89],"also":[93],"provides":[94],"an":[95],"efficient":[96],"way":[97],"learn":[99,147],"dependence":[101],"among":[102],"correlations.":[104],"These":[105],"two":[106],"properties":[107],"jointly":[108],"contribute":[109],"learning":[113],"paths":[114],"DMF,":[116],"results":[118],"faster":[120],"convergence,":[121],"lower":[122],"training":[123],"loss,":[124],"better":[126],"performance.":[127],"We":[128],"evaluate":[129],"our":[130,144],"model":[131,145],"audiovisual":[133],"speech":[134],"recognition":[135],"cross-modal":[137],"retrieval.":[138],"noticeable":[140],"performance":[141],"demonstrates":[142],"that":[143],"effective":[149],"representation.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}