{"id":"https://openalex.org/W4291700316","doi":"https://doi.org/10.1109/icccs55155.2022.9846612","title":"CM-CIF: Cross-Modal for Unaligned Modality Fusion with Continuous Integrate-and-Fire","display_name":"CM-CIF: Cross-Modal for Unaligned Modality Fusion with Continuous Integrate-and-Fire","publication_year":2022,"publication_date":"2022-04-22","ids":{"openalex":"https://openalex.org/W4291700316","doi":"https://doi.org/10.1109/icccs55155.2022.9846612"},"language":"en","primary_location":{"id":"doi:10.1109/icccs55155.2022.9846612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccs55155.2022.9846612","pdf_url":null,"source":{"id":"https://openalex.org/S4363608130","display_name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10072/418510","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100783067","display_name":"Zheng Jiang","orcid":"https://orcid.org/0000-0003-0862-2720"},"institutions":[{"id":"https://openalex.org/I31683504","display_name":"Beijing Forestry University","ror":"https://ror.org/04xv2pc41","country_code":"CN","type":"education","lineage":["https://openalex.org/I1327237609","https://openalex.org/I31683504","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zheng Jiang","raw_affiliation_strings":["Beijing Forestry University,School of Information Science &amp; Technology,Beijing,China","School of Information Science &amp"],"affiliations":[{"raw_affiliation_string":"Beijing Forestry University,School of Information Science &amp; Technology,Beijing,China","institution_ids":["https://openalex.org/I31683504"]},{"raw_affiliation_string":"School of Information Science &amp","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462079","display_name":"Yang Xu","orcid":"https://orcid.org/0000-0002-0932-8112"},"institutions":[{"id":"https://openalex.org/I31683504","display_name":"Beijing Forestry University","ror":"https://ror.org/04xv2pc41","country_code":"CN","type":"education","lineage":["https://openalex.org/I1327237609","https://openalex.org/I31683504","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Xu","raw_affiliation_strings":["Beijing Forestry University,School of Information Science &amp; Technology,Beijing,China","School of Information Science &amp"],"affiliations":[{"raw_affiliation_string":"Beijing Forestry University,School of Information Science &amp; Technology,Beijing,China","institution_ids":["https://openalex.org/I31683504"]},{"raw_affiliation_string":"School of Information Science &amp","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100704964","display_name":"Yanyan Xu","orcid":"https://orcid.org/0000-0001-7174-6588"},"institutions":[{"id":"https://openalex.org/I31683504","display_name":"Beijing Forestry University","ror":"https://ror.org/04xv2pc41","country_code":"CN","type":"education","lineage":["https://openalex.org/I1327237609","https://openalex.org/I31683504","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyan Xu","raw_affiliation_strings":["Beijing Forestry University,School of Information Science &amp; Technology,Beijing,China","School of Information Science &amp"],"affiliations":[{"raw_affiliation_string":"Beijing Forestry University,School of Information Science &amp; Technology,Beijing,China","institution_ids":["https://openalex.org/I31683504"]},{"raw_affiliation_string":"School of Information Science &amp","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102845007","display_name":"Dengfeng Ke","orcid":"https://orcid.org/0000-0001-8459-0412"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dengfeng Ke","raw_affiliation_strings":["Beijing Language and Culture University,School of Information Science,Beijing,China","School of Information Science, Beijing Language and Culture University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University,School of Information Science,Beijing,China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"School of Information Science, Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037325282","display_name":"Kaile Su","orcid":"https://orcid.org/0000-0001-6741-9699"},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kaile Su","raw_affiliation_strings":["Griffith University,Institute for Integrated and Intelligent Systems,Nathan,Australia","Institute for Integrated and Intelligent Systems, Griffith University, Nathan, Australia"],"affiliations":[{"raw_affiliation_string":"Griffith University,Institute for Integrated and Intelligent Systems,Nathan,Australia","institution_ids":["https://openalex.org/I11701301"]},{"raw_affiliation_string":"Institute for Integrated and Intelligent Systems, Griffith University, Nathan, Australia","institution_ids":["https://openalex.org/I11701301"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100783067"],"corresponding_institution_ids":["https://openalex.org/I31683504"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05529226,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"358","last_page":"361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.998199999332428,"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":0.9947999715805054,"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":0.80843186378479},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6846129298210144},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6061519980430603},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.5551849007606506},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5464218854904175},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.540437638759613},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5214118957519531},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.49315589666366577},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.4628424346446991},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4427567422389984},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.42768988013267517},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3591909408569336},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33442217111587524},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.14974966645240784}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.80843186378479},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6846129298210144},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6061519980430603},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5551849007606506},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5464218854904175},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.540437638759613},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5214118957519531},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.49315589666366577},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4628424346446991},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4427567422389984},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.42768988013267517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3591909408569336},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33442217111587524},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.14974966645240784},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icccs55155.2022.9846612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccs55155.2022.9846612","pdf_url":null,"source":{"id":"https://openalex.org/S4363608130","display_name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 7th International Conference on Computer and Communication Systems (ICCCS)","raw_type":"proceedings-article"},{"id":"pmh:oai:research-repository.griffith.edu.au:10072/418510","is_oa":true,"landing_page_url":"http://hdl.handle.net/10072/418510","pdf_url":null,"source":{"id":"https://openalex.org/S4306402548","display_name":"Griffith Research Online (Griffith University, Queensland, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I11701301","host_organization_name":"Griffith University","host_organization_lineage":["https://openalex.org/I11701301"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference output"}],"best_oa_location":{"id":"pmh:oai:research-repository.griffith.edu.au:10072/418510","is_oa":true,"landing_page_url":"http://hdl.handle.net/10072/418510","pdf_url":null,"source":{"id":"https://openalex.org/S4306402548","display_name":"Griffith Research Online (Griffith University, Queensland, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I11701301","host_organization_name":"Griffith University","host_organization_lineage":["https://openalex.org/I11701301"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference output"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2015143272","https://openalex.org/W2127141656","https://openalex.org/W2551572271","https://openalex.org/W2886945201","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2964051877","https://openalex.org/W2964182350","https://openalex.org/W2964266095","https://openalex.org/W3006974783","https://openalex.org/W3015383493","https://openalex.org/W3015830103","https://openalex.org/W3035299099","https://openalex.org/W3093145643","https://openalex.org/W3108792608","https://openalex.org/W3148757058","https://openalex.org/W3155560190","https://openalex.org/W3197976821","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6734491695","https://openalex.org/W6739901393","https://openalex.org/W6754392867","https://openalex.org/W6754420807"],"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/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"The":[0,82],"purpose":[1],"of":[2,11,42,48,57],"Audio-Visual":[3],"Speech":[4],"Recognition":[5],"is":[6],"to":[7,51,87],"identify":[8],"the":[9,12,17,34,40,45,55,58,88,93,103,107,113],"content":[10],"spoken":[13],"sentence":[14],"by":[15],"extracting":[16],"lip":[18],"movement":[19],"features":[20,23],"and":[21,109,117],"acoustic":[22,62,94],"from":[24],"an":[25],"input":[26],"video":[27],"file":[28],"containing":[29],"a":[30,52,75,125],"person's":[31],"conversation.":[32],"Although":[33],"current":[35],"audio-visual":[36],"fusion":[37,56],"models":[38],"solve":[39,67],"problem":[41],"inconsistency":[43],"in":[44,70],"time":[46],"length":[47],"different":[49],"modalities":[50,59],"certain":[53],"extent,":[54],"may":[60],"cause":[61],"boundary":[63,95],"ambiguity.":[64],"To":[65],"better":[66],"this":[68,71],"problem,":[69],"paper,":[72],"we":[73],"propose":[74],"model":[76,83,105],"named":[77],"Cross-Modal":[78],"Continuous":[79],"Integrate-and-Fire":[80],"(CM-CIF).":[81],"integrates":[84],"cross-modal":[85],"information":[86],"accumulated":[89],"weight":[90],"so":[91],"that":[92,122],"can":[96],"be":[97],"located":[98],"more":[99],"accurate.":[100],"We":[101],"use":[102],"Transformer-seq2seq":[104],"as":[106],"baseline":[108],"test":[110],"CM-CIF":[111,123],"on":[112],"public":[114],"datasets":[115],"LRS2":[116],"LRS3.":[118],"Experimental":[119],"results":[120],"show":[121],"achieves":[124],"competitive":[126],"performance.":[127]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
