{"id":"https://openalex.org/W7082151118","doi":"https://doi.org/10.5281/zenodo.17139882","title":"SAVGBench Dataset","display_name":"SAVGBench Dataset","publication_year":2025,"publication_date":"2025-09-17","ids":{"openalex":"https://openalex.org/W7082151118","doi":"https://doi.org/10.5281/zenodo.17139882"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.17139882","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17139882","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17139882","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shimada, Kazuki","orcid":"https://orcid.org/0000-0001-5389-2346"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shimada, Kazuki","raw_affiliation_strings":["Sony AI"],"raw_orcid":"https://orcid.org/0000-0001-5389-2346","affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Simon, Christian","orcid":"https://orcid.org/0009-0000-3642-820X"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simon, Christian","raw_affiliation_strings":["Sony Group Corporation"],"raw_orcid":"https://orcid.org/0009-0000-3642-820X","affiliations":[{"raw_affiliation_string":"Sony Group Corporation","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shibuya, Takashi","orcid":"https://orcid.org/0000-0002-4277-0164"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shibuya, Takashi","raw_affiliation_strings":["Sony AI"],"raw_orcid":"https://orcid.org/0000-0002-4277-0164","affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Takahashi, Shusuke","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takahashi, Shusuke","raw_affiliation_strings":["Sony Group Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"last","author":{"id":null,"display_name":"Mitsufuji, Yuki","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mitsufuji, Yuki","raw_affiliation_strings":["Sony AI","Sony Group Corporation"],"raw_orcid":"https://orcid.org/0000-0002-6806-6140","affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]},{"raw_affiliation_string":"Sony Group Corporation","institution_ids":["https://openalex.org/I2800278093"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2800278093"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6747000217437744,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6747000217437744,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T13067","display_name":"Geological Modeling and Analysis","score":0.03099999949336052,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10271","display_name":"Seismic Imaging and Inversion Techniques","score":0.01810000091791153,"subfield":{"id":"https://openalex.org/subfields/1908","display_name":"Geophysics"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5386000275611877},{"id":"https://openalex.org/keywords/stereophonic-sound","display_name":"Stereophonic sound","score":0.48660001158714294},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.46219998598098755},{"id":"https://openalex.org/keywords/ambisonics","display_name":"Ambisonics","score":0.45080000162124634},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.43970000743865967},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.4066999852657318},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4020000100135803},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.3693999946117401},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.34040001034736633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.756600022315979},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5386000275611877},{"id":"https://openalex.org/C140631703","wikidata":"https://www.wikidata.org/wiki/Q34678","display_name":"Stereophonic sound","level":3,"score":0.48660001158714294},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C47726159","wikidata":"https://www.wikidata.org/wiki/Q457547","display_name":"Ambisonics","level":3,"score":0.45080000162124634},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.43970000743865967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4092000126838684},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36660000681877136},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34929999709129333},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3061000108718872},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3052999973297119},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.3003999888896942},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2565999925136566},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17139882","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17139882","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.17139882","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17139882","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Description":[0],"This":[1],"work":[2],"addresses":[3],"the":[4,34,59,68,125,136,144,159,181,224,229,276,301,316,322,341,354,358,365,371,392,402,406],"lack":[5],"of":[6,11,110,120,138,180,196,203,210,217,231,324,357],"multimodal":[7],"generative":[8,23],"models":[9,24],"capable":[10],"producing":[12],"high-quality":[13],"videos":[14],"with":[15,199,213,250,262,386],"spatially":[16,72],"aligned":[17,73],"audio.":[18],"While":[19],"recent":[20],"advancements":[21],"in":[22,28,57,169,286,289],"have":[25],"been":[26],"successful":[27],"video":[29,83,88,133,150,390],"generation,":[30],"they":[31],"often":[32],"overlook":[33],"spatial":[35],"alignment":[36],"between":[37,300],"audio":[38,80,86,130,148,388],"and":[39,81,87,117,131,142,149,166,174,191,226,304,306,335,347,389,409],"visuals,":[40],"which":[41],"is":[42,77,102,236,294,313],"essential":[43],"for":[44,158,315,391,401],"immersive":[45],"experiences.":[46],"To":[47],"tackle":[48],"this":[49],"problem,":[50],"we":[51,362],"establish":[52],"a":[53,71,78,200,214],"new":[54],"research":[55],"direction":[56],"benchmarking":[58],"Spatially":[60],"Aligned":[61],"Audio-Video":[62],"Generation":[63],"(SAVG)":[64],"task.":[65],"We":[66,123,146],"introduce":[67],"SAVGBench":[69,160,182],"dataset,":[70,84],"audio-visual":[74,106],"dataset.":[75,161],"It":[76,101,162],"stereo":[79,129,253,387],"perspective":[82,132],"whose":[85],"data":[89,127,151,192,385,400],"are":[90,97,338,350],"curated":[91],"based":[92],"on":[93,141,164],"whether":[94],"sound":[95,121,139,156],"events":[96,140,157],"onscreen":[98,155],"or":[99],"not.":[100],"derived":[103,339],"from":[104,340],"an":[105],"dataset":[107,183,317],"(STARSS23)":[108],"consisting":[109],"first-order":[111],"Ambisonics":[112],"(FOA)":[113],"audio,":[114],"360\u00b0":[115],"video,":[116],"spatiotemporal":[118],"annotations":[119],"events.":[122],"convert":[124],"STARSS23":[126,342],"into":[128],"data,":[134],"tracking":[135],"position":[137],"off":[143],"screen.":[145],"curate":[147],"that":[152,361],"contain":[153],"only":[154,297,364],"focuses":[163],"humans":[165],"musical":[167],"instruments":[168],"indoor":[170],"environments,":[171],"including":[172],"speeches":[173],"instrument":[175,234],"sounds.":[176],"Specifications":[177],"The":[178,272,291,310,330,344,380],"specifications":[179],"can":[184],"be":[185],"summarized":[186],"as":[187],"follows:":[188],"Volume,":[189],"duration,":[190,198,212],"split:":[193],"5,031":[194],"clips":[195,209],"5-sec":[197,211],"total":[201,215],"time":[202,216,288,349],"7.0":[204],"hours":[205],"(development":[206],"set).":[207,221],"547":[208],"0.8":[218],"hrs":[219],"(evaluation":[220],"In":[222],"both":[223],"development":[225,393],"evaluation":[227,307,403],"sets,":[228],"ratio":[230],"speech":[232],"to":[233,298,319,352,398,415],"sounds":[235],"maintained":[237],"at":[238,375],"about":[239],"2:1.":[240],"Audio:":[241],"Sampling":[242],"rate:":[243],"16kHz.":[244],"Stereo":[245],"format:":[246,257],"mid-side":[247],"(M/S)":[248],"technique":[249],"left-right":[251],"cardioid":[252],"patterns.":[254],"Video:":[255],"Video":[256,259,264],"perspective.":[258],"resolution:":[260],"256x256":[261],"padding.":[263],"frames":[265],"per":[266,283],"second":[267],"(fps):":[268],"4.":[269],"Naming":[270],"convention":[271],"MP4":[273,384,399],"files":[274,408],"follow":[275],"naming":[277],"convention:":[278],"fold[fold":[279],"number]_room[room":[280],"number]_mix[recording":[281],"number":[282,293,337],"room]_deg[viewing":[284],"angle":[285,346,368,374],"degree]_start[start":[287],"frame].mp4":[290],"fold":[292,331],"currently":[295],"used":[296],"distinguish":[299],"training":[302],"(fold3":[303],"fold4)":[305],"(fold5)":[308],"splits.":[309],"room":[311,333],"information":[312],"provided":[314,351],"user":[318],"help":[320],"understand":[321],"performance":[323],"their":[325],"method":[326],"concerning":[327],"different":[328],"conditions.":[329],"number,":[332,334],"recording":[336],"recordings.":[343],"viewing":[345,367,373],"start":[348],"indicate":[353],"conversion":[355],"configuration":[356],"clip.":[359],"Note":[360],"change":[363],"horizontal":[366],"while":[369],"keeping":[370],"vertical":[372],"0\u00b0":[376],"elevation.":[377],"Download":[378,405],"instruction":[379],"file":[381,395],"SAVGBench_Dataset_Development.zip":[382],"contains":[383],"set.The":[394],"SAVGBench_Dataset_Evaluation.zip":[396],"corresponds":[397],"set.":[404],"zip":[407],"use":[410],"your":[411],"preferred":[412],"compression":[413],"tool":[414],"unzip":[416],"them.":[417]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
