{"id":"https://openalex.org/W4403791051","doi":"https://doi.org/10.1145/3664647.3680751","title":"An Inverse Partial Optimal Transport Framework for Music-guided Trailer Generation","display_name":"An Inverse Partial Optimal Transport Framework for Music-guided Trailer Generation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791051","doi":"https://doi.org/10.1145/3664647.3680751"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680751","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on 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/A5035931170","display_name":"Yutong Wang","orcid":"https://orcid.org/0009-0000-2225-5037"},"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":"Yutong Wang","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-2225-5037","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","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":false,"raw_author_name":"Sidan Zhu","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-1564-5126","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","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, China"],"raw_orcid":"https://orcid.org/0000-0003-4192-5360","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","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 & Key Laboratory of Artificial Intelligence, Ministry of Education, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1136-8903","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology & Key Laboratory of Artificial Intelligence, Ministry of Education, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035931170"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.2381,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53582764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"9739","last_page":"9748"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9987999796867371,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9912999868392944,"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":0.8053222894668579},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5482394099235535},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.42855358123779297},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15866056084632874},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1111626923084259}],"concepts":[{"id":"https://openalex.org/C2779101595","wikidata":"https://www.wikidata.org/wiki/Q7832787","display_name":"Trailer","level":2,"score":0.8053222894668579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5482394099235535},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.42855358123779297},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15866056084632874},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1111626923084259},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680751","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1999075139","https://openalex.org/W2006180404","https://openalex.org/W2064469569","https://openalex.org/W2087625213","https://openalex.org/W2559655401","https://openalex.org/W2735159761","https://openalex.org/W2739107216","https://openalex.org/W2766348671","https://openalex.org/W2909693411","https://openalex.org/W2953014951","https://openalex.org/W2962681491","https://openalex.org/W2996858319","https://openalex.org/W2998702515","https://openalex.org/W2999905431","https://openalex.org/W3007724151","https://openalex.org/W3034337242","https://openalex.org/W3034730770","https://openalex.org/W3090449556","https://openalex.org/W3106932526","https://openalex.org/W3131747507","https://openalex.org/W3174928076","https://openalex.org/W3214180234","https://openalex.org/W4230270698","https://openalex.org/W4233762729","https://openalex.org/W4284674178","https://openalex.org/W4304080347","https://openalex.org/W4304084190","https://openalex.org/W4306317292","https://openalex.org/W4309167169","https://openalex.org/W4385668779","https://openalex.org/W4386071707","https://openalex.org/W4386076646","https://openalex.org/W4386634627","https://openalex.org/W4387968041","https://openalex.org/W4390872358","https://openalex.org/W6752398176","https://openalex.org/W6790775169"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2911148753","https://openalex.org/W2101882832","https://openalex.org/W4327694446","https://openalex.org/W819012784","https://openalex.org/W1494281395","https://openalex.org/W2754401799","https://openalex.org/W2602800186"],"abstract_inverted_index":{"Trailer":[0],"generation":[1,50],"is":[2,215],"a":[3,76,93,165,178],"challenging":[4],"video":[5],"clipping":[6],"task":[7,51],"that":[8],"aims":[9],"to":[10,38,86,164,176],"select":[11],"highlighting":[12],"shots":[13,58,134,139],"from":[14],"long":[15],"videos":[16],"like":[17],"movies":[18,172],"and":[19,54,71,102,106,121,135,173,189,209],"re-organize":[20],"them":[21],"in":[22,81,205],"an":[23,31,107,157],"attractive":[24],"way.":[25],"In":[26,44,90],"this":[27,88,91],"study,":[28],"we":[29,46,151],"propose":[30],"inverse":[32,158],"partial":[33,159],"optimal":[34,143,160],"transport":[35,144,161],"(IPOT)":[36],"framework":[37,85],"achieve":[39,87],"music-guided":[40],"movie":[41,57,101,126,133],"trailer":[42,49,137,193],"generation.":[43],"particular,":[45],"formulate":[47],"the":[48,66,82,97,113,117,122,125,129,132,141,148,153],"as":[52,140],"selecting":[53],"sorting":[55],"key":[56],"based":[59],"on":[60,147],"audio":[61],"shots,":[62,104],"which":[63],"involves":[64],"matching":[65,110],"latent":[67,78,98,119],"representations":[68,99,120],"across":[69],"visual":[70,207],"acoustic":[72],"modalities.":[73],"We":[74,169],"learn":[75,152],"multi-modal":[77],"representation":[79],"model":[80,154],"proposed":[83],"IPOT":[84,200],"aim.":[89],"framework,":[92],"two-tower":[94],"encoder":[95],"derives":[96],"of":[100,124],"music":[103,138],"respectively,":[105],"attention-assisted":[108],"Sinkhorn":[109],"network":[111],"parameterizes":[112],"grounding":[114,149],"distance":[115],"between":[116,131],"shots'":[118],"distribution":[123],"shots.":[127],"Taking":[128],"correspondence":[130],"its":[136],"observed":[142],"plan":[145],"defined":[146],"distances,":[150],"by":[155],"solving":[156],"problem,":[162],"leading":[163],"bi-level":[166],"optimization":[167],"strategy.":[168],"collect":[170],"real-world":[171],"their":[174],"trailers":[175],"construct":[177],"dataset":[179],"with":[180,196],"abundant":[181],"label":[182],"information":[183],"called":[184],"CMTD":[185],"and,":[186],"accordingly,":[187],"train":[188],"evaluate":[190],"various":[191],"automatic":[192],"generators.":[194],"Compared":[195],"state-of-the-art":[197],"methods,":[198],"our":[199],"method":[201],"consistently":[202],"shows":[203],"superiority":[204],"subjective":[206],"effects":[208],"objective":[210],"quantitative":[211],"measurements.":[212],"The":[213],"code":[214],"available":[216],"at":[217],"https://github.com/Dixin-Lab/Automatic-Movie-Trailer-Generator.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}