{"id":"https://openalex.org/W2962970472","doi":"https://doi.org/10.1145/3206025.3206046","title":"CBVMR","display_name":"CBVMR","publication_year":2018,"publication_date":"2018-06-05","ids":{"openalex":"https://openalex.org/W2962970472","doi":"https://doi.org/10.1145/3206025.3206046","mag":"2962970472"},"language":"en","primary_location":{"id":"doi:10.1145/3206025.3206046","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3206025.3206046","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 ACM on International Conference on Multimedia Retrieval","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/A5044809763","display_name":"Sungeun Hong","orcid":"https://orcid.org/0000-0003-1774-9168"},"institutions":[{"id":"https://openalex.org/I4210101891","display_name":"Korea Institute of Brain Science","ror":"https://ror.org/017stnw60","country_code":"KR","type":"facility","lineage":["https://openalex.org/I4210101891"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungeun Hong","raw_affiliation_strings":["SK T-Brain, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SK T-Brain, Seoul, South Korea","institution_ids":["https://openalex.org/I4210101891"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043449123","display_name":"Woobin Im","orcid":"https://orcid.org/0000-0002-9269-4833"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woobin Im","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019223153","display_name":"Hyun Suk Yang","orcid":"https://orcid.org/0000-0002-7056-3648"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyun S. Yang","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6627,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.85817637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"353","last_page":"361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T11439","display_name":"Video Analysis and Summarization","score":0.9983000159263611,"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":0.9922000169754028,"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":0.8586688041687012},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7324004173278809},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7101974487304688},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6782657504081726},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6073691248893738},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5418693423271179},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5368301272392273},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.506986141204834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38968557119369507},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19233497977256775},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11033552885055542}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8586688041687012},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7324004173278809},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7101974487304688},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6782657504081726},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6073691248893738},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5418693423271179},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5368301272392273},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.506986141204834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38968557119369507},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19233497977256775},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11033552885055542},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3206025.3206046","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3206025.3206046","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 ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W21006490","https://openalex.org/W152593412","https://openalex.org/W272962585","https://openalex.org/W306648316","https://openalex.org/W1527575280","https://openalex.org/W1540613698","https://openalex.org/W1731081199","https://openalex.org/W1813265826","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2017064407","https://openalex.org/W2041797434","https://openalex.org/W2080391922","https://openalex.org/W2092127997","https://openalex.org/W2097117768","https://openalex.org/W2100235303","https://openalex.org/W2106053110","https://openalex.org/W2107430826","https://openalex.org/W2108598243","https://openalex.org/W2112912048","https://openalex.org/W2116777898","https://openalex.org/W2123841332","https://openalex.org/W2132980123","https://openalex.org/W2137028279","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2340600463","https://openalex.org/W2404335437","https://openalex.org/W2551439276","https://openalex.org/W2562630055","https://openalex.org/W2571951934","https://openalex.org/W2592658867","https://openalex.org/W2593172378","https://openalex.org/W2952656102","https://openalex.org/W2963389687","https://openalex.org/W3099514962","https://openalex.org/W4297969478","https://openalex.org/W4299439299","https://openalex.org/W6637618735"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2010935248","https://openalex.org/W627697492"],"abstract_inverted_index":{"Up":[0],"to":[1,137],"now,":[2],"only":[3,91],"limited":[4],"research":[5,27],"has":[6],"been":[7],"conducted":[8],"on":[9,29],"crossmodal":[10],"retrieval":[11,52],"of":[12,24,141],"suitable":[13],"music":[14,57,77],"for":[15,54,98,144],"a":[16,48,111],"specified":[17],"video":[18,55],"or":[19,35],"vice":[20],"versa.":[21],"Moreover,":[22],"much":[23],"the":[25,67,86,92,119,139,150],"existing":[26],"relies":[28],"metadata":[30],"such":[31,73],"as":[32],"keywords,":[33],"tags,":[34],"description":[36],"that":[37,58,74,117],"must":[38],"be":[39,103,156],"individually":[40],"produced":[41],"and":[42,56,76,133,152],"attached":[43],"posterior.":[44],"This":[45],"paper":[46],"introduces":[47],"new":[49],"content-based,":[50],"cross-modal":[51],"method":[53],"is":[59,96],"implemented":[60],"through":[61],"deep":[62],"neural":[63],"networks.":[64],"We":[65,128],"train":[66],"network":[68],"via":[69],"inter-modal":[70,93],"ranking":[71,94],"loss":[72,116],"videos":[75],"with":[78],"similar":[79],"semantics":[80],"end":[81],"up":[82],"close":[83],"together":[84],"in":[85,158],"embedding":[87],"space.":[88],"However,":[89],"if":[90],"constraint":[95],"used":[97],"embedding,":[99],"modality-specific":[100],"characteristics":[101],"can":[102,155],"lost.":[104],"To":[105],"address":[106],"this":[107],"problem,":[108],"we":[109],"propose":[110],"novel":[112],"soft":[113],"intra-modal":[114,124],"structure":[115],"leverages":[118],"relative":[120],"distance":[121],"relationship":[122],"between":[123],"samples":[125],"before":[126],"embedding.":[127],"also":[129],"introduce":[130],"reasonable":[131],"quantitative":[132],"qualitative":[134],"experimental":[135],"protocols":[136,143],"solve":[138],"lack":[140],"standard":[142],"less-mature":[145],"video-music":[146],"related":[147],"tasks.":[148],"All":[149],"datasets":[151],"source":[153],"code":[154],"found":[157],"our":[159],"online":[160],"repository":[161],"(https://github.com/csehong/VM-NET).":[162]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2019-07-30T00:00:00"}
