{"id":"https://openalex.org/W7154245525","doi":"https://doi.org/10.48550/arxiv.2604.10695","title":"Retrieving to Recover: Towards Incomplete Audio-Visual Question Answering via Semantic-consistent Purification","display_name":"Retrieving to Recover: Towards Incomplete Audio-Visual Question Answering via Semantic-consistent Purification","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7154245525","doi":"https://doi.org/10.48550/arxiv.2604.10695"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.10695","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10695","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.10695","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133573019","display_name":"Jiayu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiayu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069824702","display_name":"Shuo Ye","orcid":"https://orcid.org/0000-0001-7756-8233"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Shuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125707546","display_name":"Qilang Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Qilang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133596026","display_name":"Zihan Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Zihan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079560261","display_name":"Jiajian Huang","orcid":"https://orcid.org/0009-0005-9298-7950"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jiajian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133577945","display_name":"Zitong Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Zitong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.958899974822998,"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":0.958899974822998,"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/T10860","display_name":"Speech and Audio Processing","score":0.00930000003427267,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.004800000227987766,"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/missing-data","display_name":"Missing data","score":0.8515999913215637},{"id":"https://openalex.org/keywords/imputation","display_name":"Imputation (statistics)","score":0.7064999938011169},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6227999925613403},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5859000086784363},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.578499972820282},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5703999996185303},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5224999785423279}],"concepts":[{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.8515999913215637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7416999936103821},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.7064999938011169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6414999961853027},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6227999925613403},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5859000086784363},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.578499972820282},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5703999996185303},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5224999785423279},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49470001459121704},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44369998574256897},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38040000200271606},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28209999203681946},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27489998936653137},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2624000012874603}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.10695","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10695","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.10695","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10695","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"Audio-Visual":[1],"Question":[2],"Answering":[3],"(AVQA)":[4],"methods":[5,12,33,51],"have":[6],"advanced":[7],"significantly.":[8],"However,":[9],"most":[10],"AVQA":[11,159],"lack":[13],"effective":[14],"mechanisms":[15],"for":[16,34],"handling":[17,35,92],"missing":[18,36,45,66,90,111],"modalities,":[19],"suffering":[20],"from":[21,93,149],"severe":[22],"performance":[23],"degradation":[24],"in":[25,163],"real-world":[26],"scenarios":[27],"with":[28],"data":[29],"interruptions.":[30],"Furthermore,":[31],"prevailing":[32],"modalities":[37],"predominantly":[38],"rely":[39],"on":[40],"generative":[41,95],"imputation":[42,96],"to":[43,53,59,69,97,109,141],"synthesize":[44],"features.":[46],"While":[47],"partially":[48],"effective,":[49],"these":[50,77],"tend":[52],"capture":[54],"inter-modal":[55],"commonalities":[56],"but":[57],"struggle":[58],"acquire":[60,110],"unique,":[61],"modality-specific":[62],"knowledge":[63,148],"within":[64,130],"the":[65,87,131,144],"data,":[67],"leading":[68],"hallucinations":[70],"and":[71,160],"compromised":[72],"reasoning":[73],"accuracy.":[74],"To":[75,114],"tackle":[76],"challenges,":[78],"we":[79,101,118,135],"propose":[80],"R$^{2}$ScP,":[81],"a":[82,120,137],"novel":[83],"framework":[84],"that":[85,125,155],"shifts":[86],"paradigm":[88],"of":[89],"modality":[91],"traditional":[94],"retrieval-based":[98],"recovery.":[99],"Specifically,":[100],"leverage":[102],"cross-modal":[103],"retrieval":[104],"via":[105],"unified":[106],"semantic":[107,116,128,145],"embeddings":[108],"domain-specific":[112],"knowledge.":[113],"maximize":[115],"restoration,":[117],"introduce":[119],"context-aware":[121],"adaptive":[122],"purification":[123],"mechanism":[124],"eliminates":[126],"latent":[127],"noise":[129],"retrieved":[132],"data.":[133],"Additionally,":[134],"employ":[136],"two-stage":[138],"training":[139],"strategy":[140],"explicitly":[142],"model":[143],"relationships":[146],"between":[147],"different":[150],"sources.":[151],"Extensive":[152],"experiments":[153],"demonstrate":[154],"R$^{2}$ScP":[156],"significantly":[157],"improves":[158],"enhances":[161],"robustness":[162],"modal-incomplete":[164],"scenarios.":[165]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-15T00:00:00"}