{"id":"https://openalex.org/W7133189103","doi":"https://doi.org/10.52202/075280-1484","title":"Glance and Focus: Memory Prompting for Multi-Event Video Question Answering","display_name":"Glance and Focus: Memory Prompting for Multi-Event Video Question Answering","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W7133189103","doi":"https://doi.org/10.52202/075280-1484"},"language":"en","primary_location":{"id":"doi:10.52202/075280-1484","doi":"https://doi.org/10.52202/075280-1484","is_oa":false,"landing_page_url":"https://doi.org/10.52202/075280-1484","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 36","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2401.01529","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102798840","display_name":"Ziyi Bai","orcid":"https://orcid.org/0009-0004-5917-5400","observed_orcids":["https://orcid.org/0009-0004-5917-5400","https://orcid.org/0009-0001-5275-7238","https://orcid.org/0009-0006-5182-567X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyi Bai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127781535","display_name":"Ruiping Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruiping Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127818830","display_name":"Xilin Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xilin Chen","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":0.6156,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77399395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"34247","last_page":"34259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10812","display_name":"Human Pose and Action Recognition","score":9.999999747378752e-05,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0,"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/video-question-answering","display_name":"video question answering","score":0.8880000114440918},{"id":"https://openalex.org/keywords/bipartite-matching","display_name":"bipartite matching","score":0.8629999756813049},{"id":"https://openalex.org/keywords/cross-attention","display_name":"cross-attention","score":0.7910000085830688},{"id":"https://openalex.org/keywords/human-object-interaction","display_name":"human-object interaction","score":0.6399999856948853}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7131999731063843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5356000065803528},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3562999963760376},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3458999991416931},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33959999680519104},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3246000111103058},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3000999987125397},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2915000021457672},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28139999508857727}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/075280-1484","doi":"https://doi.org/10.52202/075280-1484","is_oa":false,"landing_page_url":"https://doi.org/10.52202/075280-1484","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 36","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2401.01529","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.01529","pdf_url":"https://arxiv.org/pdf/2401.01529","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2401.01529","doi":"https://doi.org/10.48550/arxiv.2401.01529","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.01529","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2401.01529","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.01529","pdf_url":"https://arxiv.org/pdf/2401.01529","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3848188706","display_name":null,"funder_award_id":"U19B2036","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4523261873","display_name":null,"funder_award_id":"U21B2025","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7133189103.pdf","grobid_xml":"https://content.openalex.org/works/W7133189103.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2965373594","https://openalex.org/W2968124245","https://openalex.org/W3123394884","https://openalex.org/W3217059257","https://openalex.org/W4318620664","https://openalex.org/W4386071468","https://openalex.org/W7133182950"],"related_works":["https://openalex.org/W4410357428","https://openalex.org/W4402915832","https://openalex.org/W7134198772","https://openalex.org/W2954199749","https://openalex.org/W7223018162","https://openalex.org/W7206213724","https://openalex.org/W4417432276","https://openalex.org/W4292829066","https://openalex.org/W2890904455","https://openalex.org/W6910621476"],"abstract_inverted_index":{"Video":[0],"Question":[1],"Answering":[2],"(VideoQA)":[3],"has":[4],"emerged":[5],"as":[6,59,96,170],"a":[7,54,92,103,124,171],"vital":[8],"tool":[9],"to":[10,14,61,84,90,109,111,122,140,153,173],"evaluate":[11],"agents'":[12],"ability":[13],"understand":[15],"human":[16],"daily":[17],"behaviors.":[18],"Despite":[19],"the":[20,77,131,142,163,175,178,190,192,197,205],"recent":[21],"success":[22],"of":[23,56,94,116,126,156],"large":[24,240],"vision":[25],"language":[26],"models":[27,241,250],"in":[28,242],"many":[29],"multi-modal":[30],"tasks,":[31],"complex":[32],"situation":[33],"reasoning":[34,73,210,245],"over":[35],"videos":[36],"involving":[37],"multiple":[38],"human-object":[39],"interaction":[40],"events":[41],"still":[42],"remains":[43],"challenging.":[44],"In":[45],"contrast,":[46],"humans":[47],"can":[48],"easily":[49],"tackle":[50],"it":[51],"by":[52],"using":[53,136],"series":[55],"episode":[57],"memories":[58,129,168],"anchors":[60],"quickly":[62],"locate":[63],"question-related":[64],"key":[65,97,199],"moments":[66],"for":[67,209],"reasoning.":[68],"To":[69],"mimic":[70],"this":[71],"effective":[72],"strategy,":[74],"we":[75,118,145],"propose":[76],"Glance-Focus":[78],"model.":[79],"One":[80],"simple":[81],"way":[82],"is":[83],"apply":[85],"an":[86,120,148],"action":[87],"detection":[88],"model":[89,193,234],"predict":[91],"set":[93,105,125],"actions":[95,101],"memories.":[98],"However,":[99],"these":[100,166],"within":[102],"closed":[104],"vocabulary":[106],"are":[107,251],"hard":[108],"generalize":[110],"various":[112,243],"video":[113,187],"domains.":[114],"Instead":[115],"that,":[117],"train":[119],"Encoder-Decoder":[121],"generate":[123],"dynamic":[127],"event":[128,143,159,167,182,200],"at":[130,162,253],"glancing":[132],"stage.":[133],"Apart":[134],"from":[135],"supervised":[137],"bipartite":[138],"matching":[139],"obtain":[141],"memories,":[144],"further":[146],"design":[147],"unsupervised":[149],"memory":[150],"generation":[151],"method":[152],"get":[154],"rid":[155],"dependence":[157],"on":[158,196,204,221],"annotations.":[160],"Next,":[161],"focusing":[164],"stage,":[165],"act":[169],"bridge":[172],"establish":[174],"correlation":[176],"between":[177],"questions":[179],"with":[180],"high-level":[181],"concepts":[183],"and":[184,230,249],"low-level":[185],"lengthy":[186],"content.":[188],"Given":[189],"question,":[191],"first":[194],"focuses":[195,203],"generated":[198],"memory,":[201],"then":[202],"most":[206],"relevant":[207],"moment":[208],"through":[211],"our":[212],"designed":[213],"multi-level":[214],"cross-attention":[215],"mechanism.":[216],"We":[217],"conduct":[218],"extensive":[219],"experiments":[220],"four":[222],"Multi-Event":[223],"VideoQA":[224],"benchmarks":[225],"including":[226],"STAR,":[227],"EgoTaskQA,":[228],"AGQA,":[229],"NExT-QA.":[231],"Our":[232],"proposed":[233],"achieves":[235],"state-of-the-art":[236],"results,":[237],"surpassing":[238],"current":[239],"challenging":[244],"tasks.":[246],"The":[247],"code":[248],"available":[252],"https://github.com/ByZ0e/Glance-Focus.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-03-03T00:00:00"}