{"id":"https://openalex.org/W4403791860","doi":"https://doi.org/10.1145/3664647.3680724","title":"Edit As You Wish: Video Caption Editing with Multi-grained User Control","display_name":"Edit As You Wish: Video Caption Editing with Multi-grained User Control","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791860","doi":"https://doi.org/10.1145/3664647.3680724"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680724","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680724","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/A5100599428","display_name":"Linli Yao","orcid":"https://orcid.org/0000-0002-9809-8864"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linli Yao","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102338865","display_name":"Yuanmeng Zhang","orcid":"https://orcid.org/0009-0002-7523-9457"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanmeng Zhang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107031530","display_name":"Zichong Wang","orcid":null},"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":"Ziheng Wang","raw_affiliation_strings":["School of Information, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077117114","display_name":"x. hou","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinglin Hou","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027308029","display_name":"Tiezheng Ge","orcid":"https://orcid.org/0000-0003-1381-2692"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiezheng Ge","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102883869","display_name":"Yuning Jiang","orcid":"https://orcid.org/0000-0003-1665-3025"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuning Jiang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101441137","display_name":"Xu Sun","orcid":"https://orcid.org/0000-0001-8241-9320"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Sun","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"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":"Qin Jin","raw_affiliation_strings":["School of Information, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100599428"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.7479,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73068643,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1924","last_page":"1933"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.9994000196456909,"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":0.992900013923645,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8370012044906616},{"id":"https://openalex.org/keywords/wish","display_name":"Wish","score":0.573516309261322},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3580487370491028},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34013962745666504},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3342105746269226},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.06233668327331543}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8370012044906616},{"id":"https://openalex.org/C2781298115","wikidata":"https://www.wikidata.org/wiki/Q241625","display_name":"Wish","level":2,"score":0.573516309261322},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3580487370491028},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34013962745666504},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3342105746269226},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.06233668327331543},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680724","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680724","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1895577753","https://openalex.org/W2058373514","https://openalex.org/W2139501017","https://openalex.org/W2507365558","https://openalex.org/W2523993696","https://openalex.org/W2525981529","https://openalex.org/W2526273376","https://openalex.org/W2534253848","https://openalex.org/W2565656701","https://openalex.org/W2887585070","https://openalex.org/W2913822893","https://openalex.org/W2951390634","https://openalex.org/W2979826702","https://openalex.org/W2981411942","https://openalex.org/W2989322838","https://openalex.org/W3034316193","https://openalex.org/W3034999214","https://openalex.org/W3035392611","https://openalex.org/W3093026747","https://openalex.org/W3105136412","https://openalex.org/W3205021045","https://openalex.org/W3214192224","https://openalex.org/W4225739172","https://openalex.org/W4285142661","https://openalex.org/W4285389151","https://openalex.org/W4287077836","https://openalex.org/W4367046808","https://openalex.org/W4387968685"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2009944257","https://openalex.org/W1960554414","https://openalex.org/W2358785095","https://openalex.org/W4238084319","https://openalex.org/W2415636950","https://openalex.org/W4254898000","https://openalex.org/W2043738496"],"abstract_inverted_index":{"Automatically":[0],"narrating":[1],"videos":[2,20],"in":[3,50],"natural":[4],"language":[5],"complying":[6],"with":[7,21,146],"user":[8,42,86,96,108],"requests,":[9],"i.e.":[10],"Controllable":[11],"Video":[12,71],"Captioning":[13],"task,":[14,118],"can":[15,38,55],"help":[16],"people":[17],"manage":[18],"massive":[19],"desired":[22],"intentions.":[23],"However,":[24],"existing":[25,80],"works":[26],"suffer":[27],"from":[28,110],"two":[29,147],"shortcomings:":[30],"1)":[31],"the":[32,45,95,116,158,177],"control":[33],"signal":[34],"is":[35,48],"single-grained":[36],"which":[37,54],"not":[39,56],"satisfy":[40],"diverse":[41,107],"intentions;":[43],"2)":[44],"video":[46,81],"description":[47,82],"generated":[49],"a":[51,69,99,139],"single":[52],"round":[53],"be":[57],"further":[58,137],"edited":[59],"to":[60,76,105,112,152],"meet":[61],"dynamic":[62],"needs.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,93,119,163],"propose":[68,138],"novel":[70,159],"Caption":[72],"Editing":[73],"(VCE)":[74],"task":[75,178],"automatically":[77,120],"revise":[78],"an":[79,122,131,154],"guided":[83],"by":[84,89],"multi-grained":[85],"requests.":[87],"Inspired":[88],"human":[90],"writing-revision":[91],"habits,":[92],"design":[94],"command":[97],"as":[98],"pivotal":[100],"triplet":[101],"{operation,":[102],"position,":[103],"attribute}":[104],"cover":[106],"needs":[109],"coarse-grained":[111],"fine-grained.":[113],"To":[114],"facilitate":[115],"VCE":[117],"construct":[121],"open-domain":[123],"benchmark":[124],"dataset":[125,133],"named":[126],"VATEX-EDIT":[127],"and":[128,172,185,190],"manually":[129],"collect":[130],"e-commerce":[132],"called":[134],"EMMAD-EDIT.":[135],"We":[136],"specialized":[140],"small-scale":[141],"model":[142],"(i.e.,":[143],"OPA)":[144],"compared":[145],"generalist":[148],"Large":[149],"Multi-modal":[150],"Models":[151],"perform":[153],"exhaustive":[155],"analysis":[156],"of":[157,180],"task.":[160],"For":[161],"evaluation,":[162],"adopt":[164],"comprehensive":[165],"metrics":[166],"considering":[167],"caption":[168],"fluency,":[169],"command-caption":[170],"consistency,":[171],"video-caption":[173],"alignment.":[174],"Experiments":[175],"reveal":[176],"challenges":[179],"fine-grained":[181],"multi-modal":[182],"semantics":[183],"understanding":[184],"processing.":[186],"Our":[187],"datasets,":[188],"codes,":[189],"evaluation":[191],"tools":[192],"are":[193],"available":[194],"at":[195],"https://github.com/yaolinli/VCE.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
