{"id":"https://openalex.org/W4415539649","doi":"https://doi.org/10.1145/3746027.3758261","title":"Valor32k-AVQA v2.0: Open-Ended Audio-Visual Question Answering Dataset and Benchmark","display_name":"Valor32k-AVQA v2.0: Open-Ended Audio-Visual Question Answering Dataset and Benchmark","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539649","doi":"https://doi.org/10.1145/3746027.3758261"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3758261","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758261","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3758261","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114618478","display_name":"Ines Riahi","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ines Riahi","raw_affiliation_strings":["Aalto University, Espoo, Uusimaa, Finland"],"raw_orcid":"https://orcid.org/0009-0004-8480-5128","affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Uusimaa, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049343215","display_name":"Abduljalil Radman","orcid":"https://orcid.org/0000-0002-6317-9752"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Abduljalil Radman","raw_affiliation_strings":["Aalto University, Espoo, Uusimaa, Finland"],"raw_orcid":"https://orcid.org/0000-0002-6317-9752","affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Uusimaa, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079044890","display_name":"Zixin Guo","orcid":"https://orcid.org/0000-0002-7088-2331"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Zixin Guo","raw_affiliation_strings":["Aalto University, Espoo, Uusimaa, Finland"],"raw_orcid":"https://orcid.org/0000-0002-7088-2331","affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Uusimaa, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053495468","display_name":"Rachid Hedjam","orcid":"https://orcid.org/0000-0002-9065-9591"},"institutions":[{"id":"https://openalex.org/I113281461","display_name":"Bishop's University","ror":"https://ror.org/051prj435","country_code":"CA","type":"education","lineage":["https://openalex.org/I113281461"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rachid Hedjam","raw_affiliation_strings":["Bishop's University, Sherbrooke, QC, Canada"],"raw_orcid":"https://orcid.org/0000-0002-9065-9591","affiliations":[{"raw_affiliation_string":"Bishop's University, Sherbrooke, QC, Canada","institution_ids":["https://openalex.org/I113281461"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036133390","display_name":"Jorma Laaksonen","orcid":"https://orcid.org/0000-0001-7218-3131"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jorma Laaksonen","raw_affiliation_strings":["Aalto University, Espoo, Uusimaa, Finland"],"raw_orcid":"https://orcid.org/0000-0001-7218-3131","affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Uusimaa, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35096621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13097","last_page":"13103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7164999842643738},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4699000120162964},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.27000001072883606},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.23600000143051147}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7164999842643738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6504999995231628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49300000071525574},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4699000120162964},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3813999891281128},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35690000653266907},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3237999975681305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2985999882221222},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.23600000143051147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3758261","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758261","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/140657","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/0c69ca42-ddea-4e42-ad5f-2423d504f8f3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3758261","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758261","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2133512280","https://openalex.org/W2963541336","https://openalex.org/W2970641574","https://openalex.org/W4403511263"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"growing":[1],"interest":[2],"in":[3,148],"Audio-Visual":[4],"Question":[5],"Answering":[6],"(AVQA),":[7],"existing":[8],"datasets":[9],"often":[10],"suffer":[11],"from":[12],"limited":[13],"diversity,":[14],"rigid":[15],"formats,":[16],"and":[17,22,40,49,58,73,90,126,159,170],"insufficient":[18],"integration":[19],"of":[20],"audio":[21,130,146],"visual":[23,138],"modalities.":[24],"To":[25],"address":[26],"these":[27],"limitations,":[28],"we":[29],"introduce":[30],"Valor32k-AVQA":[31,162],"v2.0,":[32],"a":[33,94,106,114,165],"large-scale":[34],"dataset":[35,54,150],"containing":[36],"28,863":[37],"real-world":[38],"videos":[39],"over":[41],"225,000":[42],"QA":[43],"pairs,":[44],"designed":[45],"to":[46,109],"support":[47],"diverse":[48],"realistic":[50],"multimodal":[51],"understanding.":[52],"The":[53],"features":[55],"both":[56],"open-ended":[57],"multiple-choice":[59],"questions,":[60,88],"each":[61],"annotated":[62],"with":[63,101,118],"the":[64,123,145],"required":[65],"modality":[66],"(":[67,76],"visual,":[68],"audio,":[69],"or":[70,82],"audio-visual":[71,173],")":[72],"question":[74,174],"category":[75],"description,":[77],"action,":[78],"count,":[79],"temporal,":[80],"location,":[81],"relative":[83],"position":[84],").":[85],"All":[86],"annotations-including":[87],"answers,":[89],"metadata-are":[91],"generated":[92],"through":[93],"fully":[95],"automated":[96],"prompting":[97],"pipeline":[98],"using":[99],"GPT-4o,":[100],"human":[102],"validation":[103],"performed":[104],"on":[105,122],"representative":[107],"sample":[108],"ensure":[110],"quality.":[111],"We":[112],"benchmark":[113],"few":[115],"state-of-the-art":[116],"models,":[117],"additional":[119],"evaluations":[120],"available":[121],"project":[124],"page,":[125],"observe":[127],"that":[128,144],"incorporating":[129],"consistently":[131],"improves":[132],"performance":[133],"during":[134],"fine-tuning":[135],"without":[136],"compromising":[137],"reasoning":[139],"capabilities.":[140],"These":[141],"findings":[142],"highlight":[143],"signals":[147],"our":[149],"are":[151],"not":[152],"only":[153],"well":[154],"integrated,":[155],"but":[156],"also":[157],"informative":[158],"complementary,":[160],"establishing":[161],"v2.0":[163],"as":[164],"valuable":[166],"resource":[167],"for":[168],"developing":[169],"evaluating":[171],"robust":[172],"answering":[175],"systems.":[176]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-25T00:00:00"}