{"id":"https://openalex.org/W4379932012","doi":"https://doi.org/10.1145/3591106.3592247","title":"Shot Retrieval and Assembly with Text Script for Video Montage Generation","display_name":"Shot Retrieval and Assembly with Text Script for Video Montage Generation","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4379932012","doi":"https://doi.org/10.1145/3591106.3592247"},"language":"en","primary_location":{"id":"doi:10.1145/3591106.3592247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM 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/A5007163320","display_name":"G. Yang","orcid":"https://orcid.org/0000-0001-8163-6569"},"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":true,"raw_author_name":"Guoxing Yang","raw_affiliation_strings":["Renmin University of China, China"],"raw_orcid":"https://orcid.org/0000-0001-8163-6569","affiliations":[{"raw_affiliation_string":"Renmin University of China, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030033393","display_name":"Haoyu Lu","orcid":"https://orcid.org/0000-0003-2620-6296"},"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":"Haoyu Lu","raw_affiliation_strings":["Renmin University of China, China"],"raw_orcid":"https://orcid.org/0000-0003-2620-6296","affiliations":[{"raw_affiliation_string":"Renmin University of China, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038217154","display_name":"Zelong Sun","orcid":"https://orcid.org/0000-0002-2614-8121"},"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":"Zelong Sun","raw_affiliation_strings":["Renmin University of China, China"],"raw_orcid":"https://orcid.org/0000-0002-2614-8121","affiliations":[{"raw_affiliation_string":"Renmin University of China, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085349794","display_name":"Zhiwu Lu","orcid":"https://orcid.org/0000-0003-0280-7724"},"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":"Zhiwu Lu","raw_affiliation_strings":["Renmin University of China, China"],"raw_orcid":"https://orcid.org/0000-0003-0280-7724","affiliations":[{"raw_affiliation_string":"Renmin University of China, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007163320"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.2355,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49907337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"298","last_page":"306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9990000128746033,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9984999895095825,"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":0.7211492657661438},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5149201154708862},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5089981555938721},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3943619728088379},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35825419425964355},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3535177707672119}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7211492657661438},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5149201154708862},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5089981555938721},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3943619728088379},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35825419425964355},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3535177707672119},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3591106.3592247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1996204097","https://openalex.org/W2019660985","https://openalex.org/W2114859792","https://openalex.org/W2117178839","https://openalex.org/W2425121537","https://openalex.org/W2532670842","https://openalex.org/W2738077708","https://openalex.org/W2798708692","https://openalex.org/W2885775891","https://openalex.org/W2963223499","https://openalex.org/W2963541336","https://openalex.org/W2963890755","https://openalex.org/W2963916161","https://openalex.org/W2970231061","https://openalex.org/W2984008963","https://openalex.org/W2988785632","https://openalex.org/W2998356391","https://openalex.org/W3035265375","https://openalex.org/W3035635319","https://openalex.org/W3105232955","https://openalex.org/W3117484799","https://openalex.org/W3174873881","https://openalex.org/W3204588463","https://openalex.org/W6604529294","https://openalex.org/W6608190711"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"With":[0],"the":[1,31,37,91,166,189,193,197],"development":[2],"of":[3,33,49,65,99,181,196],"video":[4,15,27,47,75,112,169,204],"sharing":[5],"websites,":[6],"numerous":[7],"users":[8,23],"desire":[9],"to":[10,24,30,45],"create":[11,25,46],"their":[12],"own":[13],"attractive":[14],"montages.":[16],"However,":[17],"it":[18,39],"is":[19,40,131],"difficult":[20],"for":[21,43,74,86,111,133,148],"inexperienced":[22],"well-edited":[26],"montages":[28,48],"due":[29],"lack":[32],"professional":[34],"expertise.":[35],"In":[36],"meantime,":[38],"time-consuming":[41],"even":[42],"experts":[44],"high":[50],"quality,":[51],"which":[52,78,178],"requires":[53],"effectively":[54],"selecting":[55],"shots":[56,119],"from":[57],"abundant":[58],"candidates":[59],"and":[60,89,117,158,202],"assembling":[61,118],"them":[62],"together.":[63],"Instead":[64],"manual":[66],"creation,":[67],"various":[68],"automatic":[69],"methods":[70],"have":[71],"been":[72],"proposed":[73,198],"montage":[76,113,170],"generation,":[77,171],"typically":[79],"take":[80],"a":[81,108,127,174],"single":[82],"sentence":[83],"as":[84],"input":[85],"text-to-shot":[87],"retrieval,":[88],"ignore":[90],"semantic":[92],"cross-sentence":[93,134],"coherence":[94,135],"given":[95],"complicated":[96],"text":[97,122],"script":[98],"multiple":[100],"sentences.":[101],"To":[102,124,164],"overcome":[103],"this":[104,125,140],"drawback,":[105],"we":[106,172],"propose":[107],"novel":[109,143],"model":[110],"generation":[114],"by":[115],"retrieving":[116],"with":[120,139],"arbitrary":[121],"scripts.":[123],"end,":[126],"sequence":[128],"consistency":[129],"transformer":[130],"devised":[132],"modeling.":[136],"More":[137],"importantly,":[138],"transformer,":[141],"two":[142],"sequence-level":[144],"tasks":[145],"are":[146,206],"defined":[147],"sentence-shot":[149],"alignment":[150],"in":[151,184],"sequence-level:":[152],"Cross-Modal":[153],"Sequence":[154,160],"Matching":[155],"(CMSM)":[156],"task,":[157],"Chaotic":[159],"Recovering":[161],"(CSR)":[162],"task.":[163],"facilitate":[165],"research":[167],"on":[168,188],"construct":[173],"new,":[175],"highly-varied":[176],"dataset":[177,191,201],"collects":[179],"thousands":[180],"video-script":[182],"pairs":[183],"documentary.":[185],"Extensive":[186],"experiments":[187],"constructed":[190],"demonstrate":[192],"superior":[194],"performance":[195],"model.":[199],"The":[200],"generated":[203],"demos":[205],"available":[207],"at":[208],"https://github.com/RATVDemo/RATV.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}