{"id":"https://openalex.org/W2895905649","doi":"https://doi.org/10.1145/3264869.3264870","title":"Multimodal Fusion Strategies","display_name":"Multimodal Fusion Strategies","publication_year":2018,"publication_date":"2018-10-17","ids":{"openalex":"https://openalex.org/W2895905649","doi":"https://doi.org/10.1145/3264869.3264870","mag":"2895905649"},"language":"en","primary_location":{"id":"doi:10.1145/3264869.3264870","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3264869.3264870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Workshop on Audio-Visual Scene Understanding for Immersive 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/A5026204977","display_name":"Hanseok Ko","orcid":"https://orcid.org/0000-0002-8744-4514"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hanseok Ko","raw_affiliation_strings":["Korea University, Seoul, Rebublic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University, Seoul, Rebublic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5026204977"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11085948,"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":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9934999942779541,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9934999942779541,"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":0.9904000163078308,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9865000247955322,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8203998804092407},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6224559545516968},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.4778439700603485},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4731265902519226},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4642093777656555},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45249199867248535},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4489235579967499},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.44485586881637573},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4123302698135376},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4007111191749573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8203998804092407},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6224559545516968},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.4778439700603485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4731265902519226},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4642093777656555},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45249199867248535},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4489235579967499},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.44485586881637573},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4123302698135376},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4007111191749573},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3264869.3264870","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3264869.3264870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Workshop on Audio-Visual Scene Understanding for Immersive Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2582644041","https://openalex.org/W2613134859","https://openalex.org/W2772728560","https://openalex.org/W2802893970"],"related_works":["https://openalex.org/W2185469136","https://openalex.org/W2011264131","https://openalex.org/W4306353150","https://openalex.org/W2026860389","https://openalex.org/W8219677","https://openalex.org/W3216879894","https://openalex.org/W2890132085","https://openalex.org/W2168054807","https://openalex.org/W2058990474","https://openalex.org/W2365286546"],"abstract_inverted_index":{"Two-hour":[0],"movie":[1,5],"or":[2,46],"a":[3,16,139],"short":[4],"clip":[6],"as":[7],"its":[8],"subset":[9],"is":[10],"intended":[11],"to":[12,23,92,170],"capture":[13],"and":[14,26,51,60,71,81,96,104,117,134,160],"present":[15],"meaningful":[17],"(or":[18],"significant)":[19],"story":[20],"in":[21,56,64,142],"video":[22,61,82,87,157,177],"be":[24,120,138],"recognized":[25],"understood":[27],"by":[28],"human":[29,38,74],"audience.":[30],"What":[31],"if":[32],"we":[33],"substitute":[34],"the":[35,53,65,77,94,124,132,153,172],"task":[36],"of":[37,42,49,58,122,155],"audience":[39],"with":[40,109,115],"that":[41,100],"an":[43],"intelligent":[44,147],"machine":[45],"robot":[47],"capable":[48,121],"capturing":[50],"processing":[52],"semantic":[54,98],"information":[55,136,174],"terms":[57],"audio":[59,78,133],"cues":[62,175],"contained":[63],"video?":[66],"By":[67],"using":[68],"both":[69],"auditory":[70],"visual":[72,135],"means,":[73],"brain":[75],"processes":[76],"(sound,":[79],"speech)":[80],"(background":[83],"image":[84],"scene,":[85],"moving":[86],"objects,":[88],"written":[89],"characters)":[90],"modalities":[91],"extract":[93],"spatial":[95],"temporal":[97],"information,":[99],"are":[101],"contextually":[102],"complementary":[103],"robust.":[105],"Smart":[106],"machines":[107],"equipped":[108,114],"audiovisual":[110],"multisensors":[111],"(e.g.":[112],"CCTV":[113],"cameras":[116],"microphones)":[118],"should":[119],"achieving":[123],"same":[125],"task.":[126,180],"An":[127],"appropriate":[128],"fusion":[129,164],"strategy":[130],"combining":[131],"would":[137],"key":[140],"component":[141],"developing":[143],"such":[144],"artificial":[145],"general":[146],"(AGI)":[148],"systems.":[149],"This":[150],"talk":[151],"reviews":[152],"challenges":[154],"current":[156],"analytics":[158,179],"schemes":[159],"explores":[161],"various":[162],"sensor":[163],"techniques":[165],"[1,":[166],"2,":[167],"3,":[168],"4]":[169],"combine":[171],"audio-visual":[173],"for":[176],"content":[178]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}