{"id":"https://openalex.org/W4414359276","doi":"https://doi.org/10.24963/ijcai.2025/1137","title":"Weakly-Supervised Movie Trailer Generation Driven by Multi-Modal Semantic Consistency","display_name":"Weakly-Supervised Movie Trailer Generation Driven by Multi-Modal Semantic Consistency","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359276","doi":"https://doi.org/10.24963/ijcai.2025/1137"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/1137","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5113315317","display_name":"Sidan Zhu","orcid":"https://orcid.org/0009-0007-1564-5126"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sidan Zhu","raw_affiliation_strings":["Beijing Institute of Technology, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100631524","display_name":"Yutong Wang","orcid":"https://orcid.org/0000-0001-8943-1832"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Wang","raw_affiliation_strings":["Beijing Institute of Technology, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035141289","display_name":"Hongteng Xu","orcid":"https://orcid.org/0000-0003-4192-5360"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongteng Xu","raw_affiliation_strings":["Renmin University of China, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101426324","display_name":"Dixin Luo","orcid":"https://orcid.org/0000-0003-1136-8903"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dixin Luo","raw_affiliation_strings":["Beijing Institute of Technology, Beijing","Key Laboratory of Artificial Intelligence, Ministry of Education, Shanghai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Key Laboratory of Artificial Intelligence, Ministry of Education, Shanghai","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113315317"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21889734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10234","last_page":"10242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9983999729156494,"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":0.9983999729156494,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9703999757766724,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9598000049591064,"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/trailer","display_name":"Trailer","score":0.8691999912261963},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6682999730110168},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6446999907493591},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6406999826431274},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5149999856948853},{"id":"https://openalex.org/keywords/plot","display_name":"Plot (graphics)","score":0.3901999890804291}],"concepts":[{"id":"https://openalex.org/C2779101595","wikidata":"https://www.wikidata.org/wiki/Q7832787","display_name":"Trailer","level":2,"score":0.8691999912261963},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7621999979019165},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6682999730110168},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6446999907493591},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6406999826431274},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5149999856948853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4300000071525574},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39590001106262207},{"id":"https://openalex.org/C167651023","wikidata":"https://www.wikidata.org/wiki/Q1474611","display_name":"Plot (graphics)","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30889999866485596},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.2825999855995178},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27129998803138733},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.262800008058548}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/1137","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0,149],"an":[1],"essential":[2],"movie":[3,20,87,94,111],"promotional":[4],"tool,":[5],"trailers":[6],"are":[7],"designed":[8],"to":[9,45,105],"capture":[10],"the":[11,15,48,106,119,127,155,176],"audience's":[12],"interest":[13],"through":[14],"skillful":[16],"editing":[17],"of":[18,51,179],"key":[19,86,138,145],"shots.":[21],"Although":[22],"some":[23],"attempts":[24],"have":[25],"been":[26],"made":[27],"for":[28,137,144],"automatic":[29],"trailer":[30,56,66,79,108],"generation,":[31],"existing":[32],"methods":[33],"often":[34],"rely":[35],"on":[36,90,110,160],"predefined":[37],"rules":[38],"or":[39],"manual":[40],"fine-grained":[41,165],"annotations":[42],"and":[43,84,93,99,102,124,141,171],"fail":[44],"fully":[46],"leverage":[47],"multi-modal":[49,71,78],"information":[50],"movies,":[52],"resulting":[53],"in":[54],"unsatisfactory":[55],"generation":[57,67,80],"results.":[58],"In":[59],"this":[60],"study,":[61],"we":[62,75,152],"introduce":[63],"a":[64,77,130,150],"weakly-supervised":[65,131],"method":[68,181],"driven":[69],"by":[70],"semantic":[72],"consistency.":[73],"Specifically,":[74],"design":[76],"framework":[81,121],"that":[82],"selects":[83],"sorts":[85],"shots":[88],"based":[89,109,159],"input":[91],"music":[92],"metadata":[95],"(e.g.,":[96],"category":[97],"tags":[98],"plot":[100],"keywords)":[101],"adds":[103],"narration":[104],"generated":[107],"subtitles.":[112],"We":[113],"utilize":[114],"two":[115],"pseudo-scores":[116],"derived":[117],"from":[118],"proposed":[120,156],"as":[122],"labels":[123],"thus":[125],"train":[126],"model":[128,157],"under":[129],"learning":[132],"paradigm,":[133],"ensuring":[134],"trailerness":[135],"consistency":[136,143],"shot":[139,146],"selection":[140],"emotion":[142],"sorting,":[147],"respectively.":[148],"result,":[151],"can":[153],"learn":[154],"solely":[158],"movie-trailer":[161],"pairs":[162],"without":[163],"any":[164],"annotations.":[166],"Both":[167],"objective":[168],"experimental":[169],"results":[170],"subjective":[172],"user":[173],"studies":[174],"demonstrate":[175],"superior":[177],"performance":[178],"our":[180],"over":[182],"previous":[183],"works.":[184],"The":[185],"code":[186],"is":[187],"available":[188],"at":[189],"https://github.com/Dixin-Lab/MMSC.":[190]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}