{"id":"https://openalex.org/W4416249994","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227376","title":"DMIMHD: Dynamic Modality Interaction for Multi-Modal Human Desire Understanding","display_name":"DMIMHD: Dynamic Modality Interaction for Multi-Modal Human Desire Understanding","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416249994","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227376"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227376","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227376","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5100381541","display_name":"Xinyi Zhang","orcid":"https://orcid.org/0000-0002-0581-9707"},"institutions":[{"id":"https://openalex.org/I4210150146","display_name":"Moscow State University","ror":"https://ror.org/050a13t43","country_code":"TJ","type":"education","lineage":["https://openalex.org/I4210150146"]},{"id":"https://openalex.org/I19880235","display_name":"Lomonosov Moscow State University","ror":"https://ror.org/010pmpe69","country_code":"RU","type":"education","lineage":["https://openalex.org/I19880235"]}],"countries":["RU","TJ"],"is_corresponding":true,"raw_author_name":"Xiangrui Zhang","raw_affiliation_strings":["Lomonosov Moscow State University"],"affiliations":[{"raw_affiliation_string":"Lomonosov Moscow State University","institution_ids":["https://openalex.org/I4210150146","https://openalex.org/I19880235"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100381541"],"corresponding_institution_ids":["https://openalex.org/I19880235","https://openalex.org/I4210150146"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37250944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6449000239372253,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6449000239372253,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.21619999408721924,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.020500000566244125,"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":0.6988000273704529},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4657000005245209},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.41100001335144043},{"id":"https://openalex.org/keywords/human-interaction","display_name":"Human interaction","score":0.4065999984741211},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.34049999713897705},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.3091999888420105}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6988000273704529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6819999814033508},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.49619999527931213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49459999799728394},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4657000005245209},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.41100001335144043},{"id":"https://openalex.org/C2987082051","wikidata":"https://www.wikidata.org/wiki/Q223642","display_name":"Human interaction","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.29899999499320984},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2854999899864197},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C2780806968","wikidata":"https://www.wikidata.org/wiki/Q6045196","display_name":"Interaction model","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227376","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227376","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2026899404","https://openalex.org/W2096970808","https://openalex.org/W2194775991","https://openalex.org/W2251394420","https://openalex.org/W2593043963","https://openalex.org/W2928165649","https://openalex.org/W3019577029","https://openalex.org/W3043840704","https://openalex.org/W3154902219","https://openalex.org/W3155230099","https://openalex.org/W4287891157","https://openalex.org/W4385245566","https://openalex.org/W4388900169","https://openalex.org/W4390414889","https://openalex.org/W4391020222","https://openalex.org/W4400228936","https://openalex.org/W4401035295","https://openalex.org/W4409366412","https://openalex.org/W4409367143","https://openalex.org/W4415798884"],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"human":[1,10,23,95],"desires":[2,41],"is":[3,17],"crucial":[4],"for":[5,94,142],"deepening":[6],"our":[7,150],"knowledge":[8],"of":[9,19,28,65,108],"behavior,":[11],"sentiment,":[12],"and":[13,45,59,111],"emotion,":[14],"as":[15],"desire":[16,96],"one":[18],"the":[20,26,54,62,82,87,124,128,133],"most":[21],"fundamental":[22],"instincts.":[24],"With":[25],"rise":[27],"multimedia,":[29],"significant":[30],"progress":[31],"has":[32],"been":[33],"made":[34],"in":[35,51,118],"multi-modal":[36],"computational":[37],"methods":[38],"that":[39,149],"analyze":[40],"by":[42],"combining":[43],"textual":[44],"visual":[46],"data.":[47,130],"However,":[48],"challenges":[49],"persist":[50],"effectively":[52],"capturing":[53],"interactions":[55],"between":[56],"these":[57,71],"modalities,":[58],"thereby":[60],"limiting":[61],"full":[63],"exploitation":[64],"their":[66],"complementary":[67],"information.":[68],"To":[69],"address":[70],"challenges,":[72],"we":[73,99,113],"introduce":[74],"novel":[75],"modality":[76,109,139],"interaction":[77,92,102,125,140],"modeling":[78],"network":[79],"based":[80,126],"on":[81,127],"dynamic":[83,90],"selection":[84],"mechanism,":[85],"marking":[86],"first":[88],"unified":[89],"multimodal":[91],"approach":[93],"understanding.":[97],"Specifically,":[98],"design":[100],"four":[101],"units":[103],"to":[104,121,135],"capture":[105],"different":[106,143],"levels":[107],"interactions,":[110],"meanwhile":[112],"employ":[114],"a":[115],"soft":[116],"selector":[117],"each":[119],"unit":[120],"dynamically":[122],"adjust":[123],"input":[129],"This":[131],"allows":[132],"model":[134,151],"adaptively":[136],"learn":[137],"diverse":[138],"patterns":[141],"samples.":[144],"Extensive":[145],"experimental":[146],"results":[147],"demonstrate":[148],"outperforms":[152],"several":[153],"state-of-the-art":[154],"methods.":[155],"<sup":[156],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[157],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[158]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}