{"id":"https://openalex.org/W4415194981","doi":"https://doi.org/10.1109/iccv51701.2025.00103","title":"VGGSounder: Audio-Visual Evaluations for Foundation Models","display_name":"VGGSounder: Audio-Visual Evaluations for Foundation Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415194981","doi":"https://doi.org/10.1109/iccv51701.2025.00103"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.08237","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120003873","display_name":"Daniil Zverev","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Daniil Zverev","raw_affiliation_strings":["Technical University of Munich, MCML"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich, MCML","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054652375","display_name":"Thadd\u00e4us Wiedemer","orcid":"https://orcid.org/0009-0003-6280-0804"},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Th\u00e4ddaus Wiedemer","raw_affiliation_strings":["University of T&#x00FC;bingen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T&#x00FC;bingen","institution_ids":["https://openalex.org/I143910747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114202924","display_name":"Ameya Prabhu","orcid":null},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ameya Prabhu","raw_affiliation_strings":["University of T&#x00FC;bingen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T&#x00FC;bingen","institution_ids":["https://openalex.org/I143910747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061457780","display_name":"Matthias Bethge","orcid":"https://orcid.org/0000-0002-6417-7812"},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Bethge","raw_affiliation_strings":["University of T&#x00FC;bingen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T&#x00FC;bingen","institution_ids":["https://openalex.org/I143910747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086801305","display_name":"Wieland Brendel","orcid":null},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wieland Brendel","raw_affiliation_strings":["University of T&#x00FC;bingen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T&#x00FC;bingen","institution_ids":["https://openalex.org/I143910747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001366802","display_name":"A. Sophia Koepke","orcid":"https://orcid.org/0000-0002-5807-0576"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"A. Sophia Koepke","raw_affiliation_strings":["Technical University of Munich, MCML"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich, MCML","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5120003873"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3315827,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1027","last_page":"1037"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9114999771118164,"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":0.9114999771118164,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.7172999978065491},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6165000200271606},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6097000241279602},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.5892000198364258},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4968000054359436},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.3409999907016754}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.7172999978065491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6366999745368958},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6165000200271606},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6097000241279602},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.5892000198364258},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4320000112056732},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3312000036239624},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25450000166893005}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.08237","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.08237","pdf_url":"https://arxiv.org/pdf/2508.08237","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},{"id":"doi:10.48550/arxiv.2508.08237","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.08237","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.08237","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.08237","pdf_url":"https://arxiv.org/pdf/2508.08237","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G53513784","display_name":null,"funder_award_id":"276693517","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8115580220","display_name":null,"funder_award_id":"01IS24060,01I524085B,01IS18039A","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,15],"emergence":[1],"of":[2,9,34,50,88],"audio-visual":[3,26,77],"foundation":[4,78],"models":[5],"underscores":[6],"the":[7],"importance":[8],"reliably":[10],"assessing":[11],"their":[12],"multi-modal":[13],"understanding.":[14],"VGGSound":[16,70],"dataset":[17],"is":[18,72],"commonly":[19],"used":[20],"as":[21],"a":[22,62],"benchmark":[23],"for":[24],"evaluation":[25],"classification.":[27],"However,":[28],"our":[29,106],"analysis":[30],"identifies":[31],"several":[32],"limitations":[33,95],"VGGSound,":[35],"including":[36],"incomplete":[37],"labelling,":[38],"partially":[39],"overlapping":[40],"classes,":[41],"and":[42,52,71],"misaligned":[43],"modalities.":[44],"These":[45],"lead":[46],"to":[47,75],"distorted":[48],"evaluations":[49],"auditory":[51],"visual":[53],"capabilities.":[54],"To":[55],"address":[56],"these":[57],"limitations,":[58],"we":[59,92],"introduce":[60],"VGGSounder,":[61],"comprehensively":[63],"re-annotated,":[64],"multi-label":[65],"test":[66],"set":[67],"that":[68],"extends":[69],"specifically":[73],"designed":[74],"evaluate":[76],"models.":[79],"VGGSounder":[80],"features":[81],"detailed":[82],"modality":[83,104,108],"annotations,":[84],"enabling":[85],"precise":[86],"analyses":[87],"modality-specific":[89],"performance.":[90],"Furthermore,":[91],"reveal":[93],"model":[94],"by":[96],"analysing":[97],"performance":[98],"degradation":[99],"when":[100],"adding":[101],"another":[102],"input":[103],"with":[105],"new":[107],"confusion":[109],"metric.":[110]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-15T00:00:00"}
