{"id":"https://openalex.org/W4408353311","doi":"https://doi.org/10.1109/icassp49660.2025.10890569","title":"Open-Modality Latent Modality Interaction Maximization for Audio-Visual Learning","display_name":"Open-Modality Latent Modality Interaction Maximization for Audio-Visual Learning","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353311","doi":"https://doi.org/10.1109/icassp49660.2025.10890569"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":null,"display_name":"Zhao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Yang","raw_affiliation_strings":["Xi’an Jiaotong University,School of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101966096","display_name":"Rui Jiang","orcid":"https://orcid.org/0000-0001-5007-5746"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Jiang","raw_affiliation_strings":["Xi’an Jiaotong University,School of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103805225","display_name":"Xiao Fu","orcid":"https://orcid.org/0009-0006-6601-5290"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Fu","raw_affiliation_strings":["Xi’an Jiaotong University,School of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050052141","display_name":"Wei Xi","orcid":"https://orcid.org/0000-0001-9348-2982"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xi","raw_affiliation_strings":["Xi’an Jiaotong University,School of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101471775","display_name":"Jizhong Zhao","orcid":"https://orcid.org/0000-0003-1037-9619"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jizhong Zhao","raw_affiliation_strings":["Xi’an Jiaotong University,School of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.993399977684021,"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/T11309","display_name":"Music and Audio Processing","score":0.993399977684021,"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/T10860","display_name":"Speech and Audio Processing","score":0.9735000133514404,"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":0.960099995136261,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.8355051279067993},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7033765912055969},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5076786279678345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.422573059797287},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34348756074905396},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3403901159763336},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32008469104766846},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.17855393886566162}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.8355051279067993},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7033765912055969},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5076786279678345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.422573059797287},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34348756074905396},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3403901159763336},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32008469104766846},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.17855393886566162}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1503933356","https://openalex.org/W2098923380","https://openalex.org/W2194775991","https://openalex.org/W2619697695","https://openalex.org/W2962899219","https://openalex.org/W2962960500","https://openalex.org/W2963155035","https://openalex.org/W2964109005","https://openalex.org/W3016011581","https://openalex.org/W3035321581","https://openalex.org/W3049737225","https://openalex.org/W3137384391","https://openalex.org/W3154807520","https://openalex.org/W3162322471","https://openalex.org/W3175825020","https://openalex.org/W3209983272","https://openalex.org/W4200436929","https://openalex.org/W4372260527","https://openalex.org/W4372267501","https://openalex.org/W4382460739","https://openalex.org/W4385570713","https://openalex.org/W6600983433","https://openalex.org/W6809497388","https://openalex.org/W6839936984","https://openalex.org/W6844194202","https://openalex.org/W6852203651","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W2385859805","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731"],"abstract_inverted_index":{"The":[0],"utilization":[1],"of":[2,8,33,91],"multimodal":[3,25,44,70,75,119],"cues":[4,76],"enhances":[5],"the":[6,17,31,40,50,84],"effectiveness":[7],"specific":[9],"cognitive":[10],"tasks":[11],"in":[12,48],"audio-visual":[13],"learning.":[14],"However,":[15],"on":[16,134,150],"one":[18],"hand,":[19,42],"designing":[20],"a":[21,58,89,122],"unified":[22],"model":[23,67,142],"for":[24,69],"learning":[26,78],"poses":[27],"challenges":[28],"due":[29],"to":[30,96,114,130],"presence":[32],"information":[34,64,81,107,117],"redundancy":[35,101],"and":[36,82,100,109,155],"modality":[37,80,124],"noise.":[38],"On":[39],"other":[41],"existing":[43],"models":[45],"face":[46],"limitations":[47],"handling":[49],"modality-missing":[51],"inference.":[52],"In":[53],"this":[54],"work,":[55],"we":[56],"propose":[57],"Latent":[59],"Modality":[60],"Interaction":[61],"with":[62],"mutual":[63,106],"Maximization":[65],"(LMIM)":[66],"architecture":[68],"learning,":[71],"which":[72],"effectively":[73],"integrates":[74],"by":[77],"essential":[79],"reducing":[83],"redundant":[85],"information.":[86],"We":[87],"employ":[88],"group":[90],"latent":[92],"tokens":[93],"as":[94],"pivots":[95],"filter":[97],"out":[98],"noise":[99],"across":[102],"different":[103],"modalities.":[104],"Simultaneously,":[105],"maximization":[108],"distribution":[110],"alignment":[111],"are":[112],"utilized":[113],"preserve":[115],"task-related":[116],"through":[118],"fusion.":[120],"Furthermore,":[121],"random":[123],"masking":[125],"training":[126],"strategy":[127],"is":[128],"employed":[129],"mitigate":[131],"potential":[132],"over-reliance":[133],"dominant":[135],"modality.":[136],"Extensive":[137],"experiments":[138],"demonstrate":[139],"that":[140],"our":[141],"achieves":[143],"significant":[144],"improvement":[145],"over":[146],"current":[147],"competitive":[148],"baselines":[149],"two":[151],"datasets,":[152],"including":[153],"UCF51":[154],"Kinetics-Sounds":[156],"datasets.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}