{"id":"https://openalex.org/W3184970013","doi":"https://doi.org/10.1145/3503161.3548268","title":"Transcript to Video: Efficient Clip Sequencing from Texts","display_name":"Transcript to Video: Efficient Clip Sequencing from Texts","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W3184970013","doi":"https://doi.org/10.1145/3503161.3548268","mag":"3184970013"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548268","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548268","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th 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/A5107209536","display_name":"Yu Xiong","orcid":"https://orcid.org/0000-0003-2582-3663"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yu Xiong","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022774523","display_name":"Fabian Caba Heilbron","orcid":"https://orcid.org/0000-0002-3129-1985"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fabian Caba Heilbron","raw_affiliation_strings":["Adobe Research, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research, San Jose, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010087030","display_name":"Dahua Lin","orcid":"https://orcid.org/0000-0002-8865-7896"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dahua Lin","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5107209536"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.5397,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.7396977,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5407","last_page":"5416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","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/T11439","display_name":"Video Analysis and Summarization","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976999759674072,"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":0.9948999881744385,"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":0.8335808515548706},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6250834465026855},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5251926183700562},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4988224506378174},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4242042005062103},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.40222129225730896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3376869261264801}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8335808515548706},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6250834465026855},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5251926183700562},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4988224506378174},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4242042005062103},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.40222129225730896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3376869261264801},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548268","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548268","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.75,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1802459088","https://openalex.org/W1895577753","https://openalex.org/W1924343884","https://openalex.org/W1927052826","https://openalex.org/W1996204097","https://openalex.org/W2078238240","https://openalex.org/W2114859792","https://openalex.org/W2117178839","https://openalex.org/W2122594606","https://openalex.org/W2123024445","https://openalex.org/W2140623962","https://openalex.org/W2142900973","https://openalex.org/W2152790380","https://openalex.org/W2154318594","https://openalex.org/W2329557562","https://openalex.org/W2422305492","https://openalex.org/W2425121537","https://openalex.org/W2487442924","https://openalex.org/W2507009361","https://openalex.org/W2532670842","https://openalex.org/W2550462002","https://openalex.org/W2618799552","https://openalex.org/W2619947201","https://openalex.org/W2738077708","https://openalex.org/W2781922022","https://openalex.org/W2794988145","https://openalex.org/W2796207103","https://openalex.org/W2808399042","https://openalex.org/W2842511635","https://openalex.org/W2843098267","https://openalex.org/W2883047779","https://openalex.org/W2883429621","https://openalex.org/W2885775891","https://openalex.org/W2889185481","https://openalex.org/W2890566571","https://openalex.org/W2893492883","https://openalex.org/W2899274165","https://openalex.org/W2948242301","https://openalex.org/W2950577311","https://openalex.org/W2962927978","https://openalex.org/W2963017553","https://openalex.org/W2963223499","https://openalex.org/W2963426332","https://openalex.org/W2963499204","https://openalex.org/W2963508075","https://openalex.org/W2963524571","https://openalex.org/W2963541336","https://openalex.org/W2963631366","https://openalex.org/W2963863119","https://openalex.org/W2963890755","https://openalex.org/W2963916161","https://openalex.org/W2964037671","https://openalex.org/W2964241990","https://openalex.org/W2965458216","https://openalex.org/W2967219836","https://openalex.org/W2975357369","https://openalex.org/W2984008963","https://openalex.org/W2987468995","https://openalex.org/W2988785632","https://openalex.org/W3010874390","https://openalex.org/W3033386097","https://openalex.org/W3035635319","https://openalex.org/W3037927086","https://openalex.org/W3043840704","https://openalex.org/W3047740097","https://openalex.org/W3047826509","https://openalex.org/W3095481265","https://openalex.org/W3104862079","https://openalex.org/W3105232955","https://openalex.org/W3105479157","https://openalex.org/W3110306138","https://openalex.org/W3117484799","https://openalex.org/W3135367836","https://openalex.org/W3204588463","https://openalex.org/W4212774754","https://openalex.org/W4234552385"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4214877189","https://openalex.org/W2074502265","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2728912566"],"abstract_inverted_index":{"Among":[0],"numerous":[1],"videos":[2,23],"shared":[3],"on":[4],"the":[5,35,106,124],"web,":[6],"well-edited":[7,22],"ones":[8],"always":[9],"attract":[10],"more":[11],"attention.":[12],"However,":[13],"it":[14,25],"is":[15],"difficult":[16],"for":[17,37,93],"inexperienced":[18],"users":[19],"to":[20,51,74],"make":[21],"because":[24],"requires":[26],"professional":[27],"expertise":[28],"and":[29,69,78,100],"immense":[30],"manual":[31],"labor.":[32],"To":[33],"meet":[34],"demands":[36],"non-experts,":[38],"we":[39,63,87],"present":[40],"Transcript-to-Video":[41],"--":[42],"a":[43,65,70],"weakly-supervised":[44],"framework":[45,109,131],"that":[46,105,129],"uses":[47],"texts":[48],"as":[49],"input":[50],"automatically":[52],"create":[53],"video":[54,95,117],"sequences":[55,118],"from":[56],"an":[57,89],"extensive":[58],"collection":[59],"of":[60,121],"shots.":[61],"Specifically,":[62],"propose":[64],"Content":[66],"Retrieval":[67],"Module":[68,73],"Temporal":[71],"Coherent":[72],"learn":[75],"visual-language":[76],"representations":[77],"model":[79],"shot":[80],"sequencing":[81],"styles,":[82],"respectively.":[83],"For":[84],"fast":[85],"inference,":[86],"introduce":[88],"efficient":[90],"search":[91],"strategy":[92],"real-time":[94],"clip":[96],"sequencing.":[97],"Quantitative":[98],"results":[99],"user":[101],"studies":[102],"demonstrate":[103],"empirically":[104],"proposed":[107],"learning":[108],"can":[110,132],"retrieve":[111],"content-relevant":[112],"shots":[113],"while":[114],"creating":[115],"plausible":[116],"in":[119],"terms":[120],"style.":[122],"Besides,":[123],"run-time":[125],"performance":[126],"analysis":[127],"shows":[128],"our":[130],"support":[133],"real-world":[134],"applications.":[135],"Project":[136],"page:":[137],"http://www.xiongyu.me/projects/transcript2video/":[138]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}