{"id":"https://openalex.org/W4403791730","doi":"https://doi.org/10.1145/3664647.3680612","title":"TAVGBench: Benchmarking Text to Audible-Video Generation","display_name":"TAVGBench: Benchmarking Text to Audible-Video Generation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791730","doi":"https://doi.org/10.1145/3664647.3680612"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680612","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680612","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/A5054666317","display_name":"Yuxin Mao","orcid":"https://orcid.org/0000-0002-9239-091X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuxin Mao","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101341266","display_name":"Xuyang Shen","orcid":"https://orcid.org/0000-0002-1968-7055"},"institutions":[{"id":"https://openalex.org/I4210111163","display_name":"Shanghai Open University","ror":"https://ror.org/027r7gj11","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111163"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuyang Shen","raw_affiliation_strings":["OpenNLPLab, Shanghai AI Lab, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"OpenNLPLab, Shanghai AI Lab, Shanghai, China","institution_ids":["https://openalex.org/I4210111163","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630815","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0002-8516-0913"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101640161","display_name":"Zhen Qin","orcid":"https://orcid.org/0009-0005-9856-0843"},"institutions":[{"id":"https://openalex.org/I4210153230","display_name":"Shanghai Academy of Spaceflight Technology","ror":"https://ror.org/050qhwt21","country_code":"CN","type":"government","lineage":["https://openalex.org/I2802615301","https://openalex.org/I4210153230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Qin","raw_affiliation_strings":["Tap Tap, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Tap Tap, Shanghai, China","institution_ids":["https://openalex.org/I4210153230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047303316","display_name":"Jinxing Zhou","orcid":"https://orcid.org/0000-0001-6402-7593"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxing Zhou","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032741887","display_name":"Mochu Xiang","orcid":"https://orcid.org/0009-0006-7332-8324"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mochu Xiang","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066621365","display_name":"Yiran Zhong","orcid":"https://orcid.org/0000-0003-1404-3610"},"institutions":[{"id":"https://openalex.org/I4210111163","display_name":"Shanghai Open University","ror":"https://ror.org/027r7gj11","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111163"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiran Zhong","raw_affiliation_strings":["OpenNLPLab, Shanghai AI Lab, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"OpenNLPLab, Shanghai AI Lab, Shanghai, China","institution_ids":["https://openalex.org/I4210111163","https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036202579","display_name":"Yuchao Dai","orcid":"https://orcid.org/0000-0002-4432-7406"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchao Dai","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5054666317"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":2.4928,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.90788444,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6607","last_page":"6616"},"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/T12290","display_name":"Human Motion and Animation","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7783570885658264},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7774125933647156},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4481469988822937},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.35741135478019714}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7783570885658264},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7774125933647156},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4481469988822937},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.35741135478019714},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3680612","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680612","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"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/733751710","is_oa":false,"landing_page_url":"https://hdl.handle.net/1885/733751710","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W1901129140","https://openalex.org/W2425121537","https://openalex.org/W2593116425","https://openalex.org/W2963524571","https://openalex.org/W2965813579","https://openalex.org/W2981852735","https://openalex.org/W3035524453","https://openalex.org/W3193083951","https://openalex.org/W3204588463","https://openalex.org/W4288089799","https://openalex.org/W4294541506","https://openalex.org/W4309660795","https://openalex.org/W4312933868","https://openalex.org/W4313123347","https://openalex.org/W4319443927","https://openalex.org/W4367359628","https://openalex.org/W4372266552","https://openalex.org/W4386065882","https://openalex.org/W4386071707","https://openalex.org/W4386071828","https://openalex.org/W4386071957","https://openalex.org/W4386075767","https://openalex.org/W4386076280","https://openalex.org/W4386076291","https://openalex.org/W4387968628","https://openalex.org/W4388979610","https://openalex.org/W4390872297","https://openalex.org/W4390872556","https://openalex.org/W4390872864","https://openalex.org/W4390873135","https://openalex.org/W4393159092","https://openalex.org/W4399474077","https://openalex.org/W4403386295"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699"],"abstract_inverted_index":{"The":[0,169],"Text":[1,39],"to":[2,40,65,88,120],"Audible-Video":[3,41],"Generation":[4,42],"(TAVG)":[5],"task":[6],"involves":[7],"generating":[8],"videos":[9],"with":[10,51],"accompanying":[11],"audio":[12,24,76,99,137],"based":[13],"on":[14,151,176,181],"text":[15],"descriptions.":[16],"Achieving":[17],"this":[18,32,130,177],"requires":[19],"skillful":[20],"alignment":[21,95,135],"of":[22,55,93,136,157],"both":[23,74,162],"and":[25,77,100,138,143,149,165,171,180],"video":[26,69,78,101,139],"elements.":[27],"To":[28],"support":[29],"research":[30,128],"in":[31,129],"field,":[33],"we":[34,104,153],"have":[35],"developed":[36],"a":[37,52,90,106,115,122],"comprehensive":[38],"Benchmark":[43],"(TAVGBench),":[44],"which":[45,113],"contains":[46],"over":[47],"1.7":[48],"million":[49],"clips":[50],"total":[53],"duration":[54],"11.8":[56],"thousand":[57],"hours.":[58],"We":[59,80,132],"propose":[60],"an":[61],"automatic":[62],"annotation":[63],"pipeline":[64],"ensure":[66],"each":[67],"audible":[68],"has":[70],"detailed":[71],"descriptions":[72],"for":[73,109,126],"its":[75],"contents.":[79],"also":[81],"introduce":[82],"the":[83,94,97,134,155],"Audio-Visual":[84],"Harmoni":[85],"score":[86],"(AVHScore)":[87],"provide":[89,121],"quantitative":[91],"measure":[92],"between":[96],"generated":[98],"modalities.":[102],"Additionally,":[103],"present":[105],"baseline":[107],"model":[108,119,160],"TAVG":[110],"called":[111],"TAVDiffusion,":[112],"uses":[114],"two-stream":[116],"latent":[117],"diffusion":[118],"fundamental":[123],"starting":[124],"point":[125],"further":[127],"area.":[131],"achieve":[133],"by":[140],"employing":[141],"cross-attention":[142],"contrastive":[144],"learning.":[145],"Through":[146],"extensive":[147],"experiments":[148],"evaluations":[150],"TAVGBench,":[152],"demonstrate":[154],"effectiveness":[156],"our":[158,166],"proposed":[159,167],"under":[161],"conventional":[163],"metrics":[164],"metrics.":[168],"dataset":[170],"code":[172],"can":[173],"be":[174],"found":[175],"page":[178],"https://npucvr.github.io/TAVGBench/":[179],"github":[182],"https://github.com/OpenNLPLab/TAVGBench.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
