{"id":"https://openalex.org/W4408353045","doi":"https://doi.org/10.1109/icassp49660.2025.10890400","title":"Multi-Prototype Grouping for Continual Learning in Visual Question Answering","display_name":"Multi-Prototype Grouping for Continual Learning in Visual Question Answering","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353045","doi":"https://doi.org/10.1109/icassp49660.2025.10890400"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100612751","display_name":"Licheng Zhang","orcid":"https://orcid.org/0000-0001-8090-4883"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Licheng Zhang","raw_affiliation_strings":["University of Science and Technology of China,School of Information Science and Technology,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Information Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023341829","display_name":"Zhendong Mao","orcid":"https://orcid.org/0000-0001-5739-8126"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhendong Mao","raw_affiliation_strings":["University of Science and Technology of China,School of Information Science and Technology,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Information Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053065618","display_name":"Yixing Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixing Peng","raw_affiliation_strings":["University of Science and Technology of China,School of Information Science and Technology,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Information Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057108350","display_name":"Zheren Fu","orcid":"https://orcid.org/0000-0001-8389-8642"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheren Fu","raw_affiliation_strings":["University of Science and Technology of China,School of Information Science and Technology,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Information Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["University of Science and Technology of China,School of Information Science and Technology,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Information Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9972000122070312,"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":0.9972000122070312,"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":0.9940000176429749,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9829999804496765,"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":0.868346095085144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7720523476600647},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4702269732952118},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37657076120376587},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.351291298866272},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3302275538444519}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.868346095085144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7720523476600647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4702269732952118},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37657076120376587},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.351291298866272},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3302275538444519}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W1987971958","https://openalex.org/W2560647685","https://openalex.org/W2560730294","https://openalex.org/W2786446225","https://openalex.org/W2951796662","https://openalex.org/W2962934715","https://openalex.org/W2963224792","https://openalex.org/W2963305465","https://openalex.org/W2963588172","https://openalex.org/W2966683369","https://openalex.org/W3175961224","https://openalex.org/W4205488143","https://openalex.org/W4282032253","https://openalex.org/W4382450654","https://openalex.org/W4386071757","https://openalex.org/W4386075840","https://openalex.org/W4392904190","https://openalex.org/W4402715976","https://openalex.org/W6757384668","https://openalex.org/W6761283764","https://openalex.org/W6771829773","https://openalex.org/W6776188292","https://openalex.org/W6789909235"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"aims":[4],"to":[5,46,86,100,111,142],"answer":[6],"questions":[7],"utilizing":[8],"information":[9],"from":[10,62,75,165],"both":[11],"textual":[12],"and":[13,19,54,146,180],"visual":[14],"modalities.":[15],"New":[16],"data":[17],"categories":[18],"novel":[20],"combinations":[21],"of":[22,51,109],"the":[23,58,76,92,116,160],"two":[24,63],"modalities":[25,64],"will":[26],"continuously":[27],"emerge":[28],"in":[29],"practical":[30],"applications,":[31],"necessitating":[32],"continual":[33,130],"learning.":[34,89],"For":[35],"this":[36,122],"unique":[37],"compositional":[38],"generalization":[39],"challenge,":[40,95],"existing":[41,96],"work":[42],"adopts":[43],"prototype":[44,61,83,163],"learning":[45,131],"separately":[47],"capture":[48],"sample-invariant":[49,148],"features":[50],"question":[52],"types":[53],"image":[55],"objects,":[56],"retrieving":[57],"most":[59],"similar":[60],"as":[65],"generalizable":[66],"representations.":[67],"However,":[68],"for":[69,91,133],"semantic":[70],"fuzzy":[71],"samples":[72,103,110],"that":[73],"deviate":[74],"corresponding":[77],"prototype,":[78],"relying":[79],"on":[80,139,159],"a":[81,127,153],"single":[82],"may":[84],"lead":[85],"error-prone":[87],"representation":[88],"Additionally,":[90],"catastrophic":[93],"forgetting":[94],"methods":[97,175],"employ":[98],"memory":[99,117,154],"store":[101],"past":[102],"but":[104],"lack":[105],"an":[106],"effective":[107],"selection":[108,156],"be":[112],"stored,":[113],"merely":[114],"updating":[115],"through":[118],"random":[119],"sampling.":[120],"In":[121],"paper,":[123],"we":[124],"propose":[125],"ProtoGroup,":[126],"multi-prototype":[128],"grouping":[129],"framework":[132,172],"VQA,":[134],"which":[135],"groups":[136,164],"prototypes":[137],"based":[138,158],"their":[140],"similarity":[141],"obtain":[143],"more":[144],"accurate":[145],"stable":[147],"features.":[149],"We":[150],"also":[151],"devise":[152],"sample":[155],"method":[157],"correlation":[161],"with":[162],"old":[166],"tasks.":[167],"Experimental":[168],"results":[169],"demonstrate":[170],"our":[171],"outperforms":[173],"previous":[174],"significantly":[176],"across":[177],"multiple":[178],"datasets":[179],"settings.":[181]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}