{"id":"https://openalex.org/W4411975722","doi":"https://doi.org/10.1007/s11263-025-02510-7","title":"Guiding Audio-Visual Question Answering with Collective Question Reasoning","display_name":"Guiding Audio-Visual Question Answering with Collective Question Reasoning","publication_year":2025,"publication_date":"2025-07-03","ids":{"openalex":"https://openalex.org/W4411975722","doi":"https://doi.org/10.1007/s11263-025-02510-7"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-025-02510-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02510-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02510-7.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02510-7.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094173849","display_name":"Baoqi Pei","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Baoqi Pei","raw_affiliation_strings":["Zhejiang University, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018560644","display_name":"Yifei Huang","orcid":"https://orcid.org/0000-0001-8067-6227"},"institutions":[{"id":"https://openalex.org/I4210109338","display_name":"University of Tokyo Hospital","ror":"https://ror.org/022cvpj02","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210109338"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yifei Huang","raw_affiliation_strings":["The University of Tokyo, Tokyo Daigaku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo Daigaku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974","https://openalex.org/I4210109338"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445744","display_name":"Guo Chen","orcid":"https://orcid.org/0000-0003-2840-8879"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo Chen","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019996173","display_name":"Jilan Xu","orcid":"https://orcid.org/0000-0002-8208-2067"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jilan Xu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100335699","display_name":"Yali Wang","orcid":"https://orcid.org/0000-0001-9431-6812"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yali Wang","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695199","display_name":"Limin Wang","orcid":"https://orcid.org/0000-0002-8849-9621"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Limin Wang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061696740","display_name":"Tong L\u00fc","orcid":"https://orcid.org/0000-0002-7051-5347"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Lu","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068846388","display_name":"Yu Qiao","orcid":null},"institutions":[{"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":"Yu Qiao","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039792198","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0001-5498-4947"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["Zhejiang University, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5094173849"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":1.2892,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81619381,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"133","issue":"10","first_page":"6912","last_page":"6929"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T11439","display_name":"Video Analysis and Summarization","score":0.9994000196456909,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.8440256118774414},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6139609813690186},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5872980952262878},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5381293296813965},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.530337929725647},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3467041552066803},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.09029221534729004}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8440256118774414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6139609813690186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5872980952262878},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5381293296813965},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.530337929725647},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3467041552066803},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.09029221534729004}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-025-02510-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02510-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02510-7.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11263-025-02510-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02510-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02510-7.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1069223013","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G1817111062","display_name":null,"funder_award_id":"2022ZD0160102","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3198975195","display_name":"\u4e00\u4eba\u79f0\u8996\u70b9\u6559\u793a\u6620\u50cf\u306e\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u89e3\u6790\u306b\u3088\u308b\u4eba\u7269\u884c\u52d5\u306e\u5b66\u7fd2\u3068\u4e88\u6e2c","funder_award_id":"22KF0119","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4025074309","display_name":"\u539f\u5b50\u7089\u904b\u8ee2\u72b6\u6cc1\u53ca\u3073\u7167\u5c04\u8a2d\u5099\u306e\u30aa\u30f3\u30e9\u30a4\u30f3\u76e3\u8996\u30b7\u30b9\u30c6\u30e0\u306e\u958b\u767a\u306b\u95a2\u3059\u308b\u7814\u7a76","funder_award_id":"146150","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4636223006","display_name":null,"funder_award_id":"JSPS KAK","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6367331636","display_name":null,"funder_award_id":"JP22KF0119","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320322832","display_name":"University of Tokyo","ror":"https://ror.org/057zh3y96"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411975722.pdf","grobid_xml":"https://content.openalex.org/works/W4411975722.grobid-xml"},"referenced_works_count":71,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2593116425","https://openalex.org/W2765716052","https://openalex.org/W2795307598","https://openalex.org/W2885156408","https://openalex.org/W2890052321","https://openalex.org/W2904452845","https://openalex.org/W2954199749","https://openalex.org/W2962865004","https://openalex.org/W2963717374","https://openalex.org/W2964109005","https://openalex.org/W2964220823","https://openalex.org/W2990113535","https://openalex.org/W2990138404","https://openalex.org/W2990408345","https://openalex.org/W2990467045","https://openalex.org/W2997909293","https://openalex.org/W2998476971","https://openalex.org/W3017343282","https://openalex.org/W3034730770","https://openalex.org/W3034802267","https://openalex.org/W3044495139","https://openalex.org/W3096780661","https://openalex.org/W3108367559","https://openalex.org/W3118120400","https://openalex.org/W3118366136","https://openalex.org/W3135367836","https://openalex.org/W3138516171","https://openalex.org/W3167565399","https://openalex.org/W3168154341","https://openalex.org/W3169318522","https://openalex.org/W3170088426","https://openalex.org/W3175961224","https://openalex.org/W3182657421","https://openalex.org/W3186187670","https://openalex.org/W3195486004","https://openalex.org/W3196974791","https://openalex.org/W3197457832","https://openalex.org/W3214328324","https://openalex.org/W4214604251","https://openalex.org/W4286242385","https://openalex.org/W4296151206","https://openalex.org/W4304098310","https://openalex.org/W4312356258","https://openalex.org/W4312370427","https://openalex.org/W4312380001","https://openalex.org/W4312583638","https://openalex.org/W4312746376","https://openalex.org/W4312864739","https://openalex.org/W4313123347","https://openalex.org/W4313186260","https://openalex.org/W4362597616","https://openalex.org/W4382202615","https://openalex.org/W4386072368","https://openalex.org/W4386076626","https://openalex.org/W4386076661","https://openalex.org/W4386083089","https://openalex.org/W4386113246","https://openalex.org/W4387247768","https://openalex.org/W4388192054","https://openalex.org/W4389524317","https://openalex.org/W4390872366","https://openalex.org/W4393154284","https://openalex.org/W4394592978","https://openalex.org/W4394625659","https://openalex.org/W4394625876","https://openalex.org/W4396219542","https://openalex.org/W4402727916","https://openalex.org/W4404724811","https://openalex.org/W6739901393","https://openalex.org/W6743837088"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Abstract":[0],"Audio-Visual":[1],"Question":[2,74],"Answering":[3],"(AVQA)":[4],"requires":[5],"the":[6,31,57,64,72,109,160,174,213],"model":[7,65,161],"to":[8,62,83,107,145],"answer":[9],"questions":[10,61,114,172],"with":[11],"complex":[12],"dynamic":[13],"audio-visual":[14,156],"information.":[15],"Prior":[16],"works":[17],"on":[18,187,204],"this":[19,38],"task":[20],"mainly":[21],"consider":[22],"only":[23,129],"using":[24],"single":[25],"question-answer":[26,51,90],"pairs":[27,52,91,169],"during":[28,97,115],"training,":[29],"overlooking":[30],"rich":[32],"semantic":[33],"associations":[34],"between":[35],"questions.":[36],"In":[37],"work,":[39],"we":[40,158],"propose":[41],"a":[42,102,163],"novel":[43],"Collective":[44],"Question-Guided":[45],"Network":[46],"(CoQo),":[47],"which":[48,78],"accepts":[49],"multiple":[50,89,113],"as":[53,134],"input":[54],"and":[55,142,150,224],"leverages":[56],"reasoning":[58,82,125,220],"over":[59],"these":[60,120],"assist":[63],"training":[66,193],"process.":[67],"The":[68],"core":[69],"module":[70],"is":[71,132],"proposed":[73,217],"Guided":[75],"Transformer":[76],"(QGT),":[77],"uses":[79,101],"collective":[80,110,218],"question":[81,131,219],"perform":[84],"question-guided":[85],"feature":[86,168],"extraction.":[87],"Since":[88],"are":[92],"not":[93],"always":[94],"available,":[95],"especially":[96],"inference,":[98],"our":[99,181,202,216],"QGT":[100,138],"set":[103],"of":[104,170,201,215],"learnable":[105,121],"tokens":[106,122],"learn":[108],"information":[111,126],"from":[112],"training.":[116],"At":[117],"inference":[118],"time,":[119],"bring":[123],"additional":[124],"even":[127],"when":[128],"one":[130],"used":[133],"input.":[135],"We":[136,196],"employ":[137],"in":[139,162],"both":[140,222],"spatial":[141],"temporal":[143],"dimensions":[144],"extract":[146],"question-related":[147],"features":[148],"effectively":[149],"efficiently.":[151],"To":[152],"better":[153],"capture":[154],"detailed":[155],"associations,":[157],"train":[159],"finer":[164],"level":[165],"by":[166],"distinguishing":[167],"different":[171],"within":[173],"same":[175],"video.":[176],"Extensive":[177],"experiments":[178],"demonstrate":[179],"that":[180],"method":[182,203],"can":[183],"achieve":[184],"state-of-the-art":[185],"performance":[186],"three":[188,205],"AVQA":[189],"datasets":[190],"while":[191],"reducing":[192],"time":[194],"significantly.":[195],"also":[197],"observe":[198],"strong":[199],"performances":[200],"VQA":[206],"benchmarks.":[207],"Detailed":[208],"ablation":[209],"studies":[210],"further":[211],"confirm":[212],"effectiveness":[214],"scheme,":[221],"quantitatively":[223],"qualitatively.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}