{"id":"https://openalex.org/W3107408554","doi":"https://doi.org/10.1145/3400286.3418216","title":"Learning Multi-modal Representations of Narrative Multimedia","display_name":"Learning Multi-modal Representations of Narrative Multimedia","publication_year":2020,"publication_date":"2020-10-13","ids":{"openalex":"https://openalex.org/W3107408554","doi":"https://doi.org/10.1145/3400286.3418216","mag":"3107408554"},"language":"en","primary_location":{"id":"doi:10.1145/3400286.3418216","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3400286.3418216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","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/A5069645890","display_name":"O\u2010Joun Lee","orcid":"https://orcid.org/0000-0001-8921-5443"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"O-Joun Lee","raw_affiliation_strings":["Pohang University of Science and Technology, Pohang-si, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pohang University of Science and Technology, Pohang-si, Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064901030","display_name":"Jin Taek Kim","orcid":"https://orcid.org/0000-0001-7389-4867"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jin-Taek Kim","raw_affiliation_strings":["Pohang University of Science and Technology, Pohang-si, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pohang University of Science and Technology, Pohang-si, Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I123900574"],"apc_list":null,"apc_paid":null,"fwci":0.1709,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49306827,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9991999864578247,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9991999864578247,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.965499997138977,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9417999982833862,"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/autoencoder","display_name":"Autoencoder","score":0.8251066207885742},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8096245527267456},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.7562237977981567},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5927577614784241},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5669333338737488},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5267654657363892},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5139762759208679},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.48410189151763916},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4693772792816162},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.44123539328575134},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4068716764450073},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3631114661693573},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33931005001068115},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13049820065498352}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8251066207885742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8096245527267456},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.7562237977981567},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5927577614784241},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5669333338737488},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5267654657363892},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5139762759208679},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.48410189151763916},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4693772792816162},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.44123539328575134},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4068716764450073},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3631114661693573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33931005001068115},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13049820065498352},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3400286.3418216","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3400286.3418216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2136655611","https://openalex.org/W2142498761","https://openalex.org/W2395716099","https://openalex.org/W2416624481","https://openalex.org/W2468480579","https://openalex.org/W2737925311","https://openalex.org/W2792961392","https://openalex.org/W2802895140","https://openalex.org/W2885641986","https://openalex.org/W2917506927","https://openalex.org/W2945065865","https://openalex.org/W2946165673","https://openalex.org/W2995974568","https://openalex.org/W2999672052","https://openalex.org/W3015061410","https://openalex.org/W3040754998","https://openalex.org/W3121351448","https://openalex.org/W3121652883","https://openalex.org/W4251470661","https://openalex.org/W4394477982","https://openalex.org/W6681029592"],"related_works":["https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4389832810","https://openalex.org/W4220682630","https://openalex.org/W3181622257","https://openalex.org/W3163146846"],"abstract_inverted_index":{"This":[0],"study":[1],"aims":[2],"to":[3,72,170],"learn":[4,114],"task-agnostic":[5],"representations":[6,106,115,169],"of":[7,34,85,107,116,174],"narrative":[8,19,36,44,118,140],"multimedia.":[9],"The":[10,75,101,127,159],"existing":[11,53],"studies":[12],"focused":[13],"on":[14,109,148],"only":[15],"stories":[16],"in":[17,124],"the":[18,35,52,61,69,83,125,139,145,157,167,172,177],"multimedia":[20,37],"without":[21],"considering":[22],"their":[23],"physical":[24],"features.":[25,74,87,126],"We":[26,67],"propose":[27,93],"a":[28,39,117],"method":[29,104,130],"for":[30,82,137,176],"incorporating":[31],"multi-modal":[32],"features":[33,56,108],"into":[38],"unified":[40],"vector":[41,168],"representation.":[42],"For":[43],"features,":[45,91],"we":[46,92,113,143],"embed":[47],"character":[48],"networks":[49],"as":[50],"with":[51],"studies.":[54],"Textual":[55],"can":[57,79],"be":[58,80],"represented":[59],"using":[60],"LSTM":[62],"(Long-Short":[63],"Term":[64],"Memory)":[65],"autoencoder.":[66],"apply":[68,144],"convolutional":[70,76],"autoencoder":[71,77],"visual":[73],"also":[78],"used":[81],"spectrograms":[84],"audible":[86],"To":[88],"combine":[89],"these":[90],"two":[94],"methods:":[95],"early":[96,102],"fusion":[97,103,129],"and":[98],"late":[99,128],"fusion.":[100],"composes":[105],"each":[110],"scene.":[111],"Then,":[112],"work":[119],"by":[120,165],"predicting":[121,171],"time-sequential":[122],"changes":[123],"concatenates":[131],"feature":[132],"vectors":[133],"that":[134,152],"are":[135,153],"trained":[136],"allover":[138],"work.":[141],"Finally,":[142],"proposed":[146,160],"methods":[147,161],"webtoons":[149],"(i.e.,":[150],"comics":[151],"serially":[154],"published":[155],"through":[156],"web).":[158],"have":[162],"been":[163],"evaluated":[164],"applying":[166],"preferences":[173],"users":[175],"webtoons.":[178]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}