{"id":"https://openalex.org/W4409019537","doi":"https://doi.org/10.1109/tcsvt.2025.3556422","title":"Temporal-Guided Mixture-of-Experts for Zero-Shot Video Question Answering","display_name":"Temporal-Guided Mixture-of-Experts for Zero-Shot Video Question Answering","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4409019537","doi":"https://doi.org/10.1109/tcsvt.2025.3556422"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3556422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3556422","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","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/A5112928277","display_name":"Yixin Qin","orcid":"https://orcid.org/0009-0004-1067-062X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixin Qin","raw_affiliation_strings":["Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0004-1067-062X","affiliations":[{"raw_affiliation_string":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101749819","display_name":"Lei Zhao","orcid":"https://orcid.org/0000-0002-8838-164X"},"institutions":[{"id":"https://openalex.org/I4210131342","display_name":"Yibin University","ror":"https://ror.org/03w8m2977","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210131342"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhao","raw_affiliation_strings":["Sichuan Artificial Intelligence Institute, Yibin, China","Sichuan Artificial Intelligence Research Institute, Yibin, China"],"raw_orcid":"https://orcid.org/0000-0002-8838-164X","affiliations":[{"raw_affiliation_string":"Sichuan Artificial Intelligence Institute, Yibin, China","institution_ids":["https://openalex.org/I4210131342"]},{"raw_affiliation_string":"Sichuan Artificial Intelligence Research Institute, Yibin, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2522-6394","affiliations":[{"raw_affiliation_string":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705309","display_name":"Haonan Zhang","orcid":"https://orcid.org/0000-0002-3871-6819"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haonan Zhang","raw_affiliation_strings":["Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087623065","display_name":"Pengpeng Zeng","orcid":"https://orcid.org/0000-0002-0672-3790"},"institutions":[{"id":"https://openalex.org/I4210131342","display_name":"Yibin University","ror":"https://ror.org/03w8m2977","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210131342"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengpeng Zeng","raw_affiliation_strings":["Sichuan Artificial Intelligence Institute, Yibin, China","Sichuan Artificial Intelligence Research Institute, Yibin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan Artificial Intelligence Institute, Yibin, China","institution_ids":["https://openalex.org/I4210131342"]},{"raw_affiliation_string":"Sichuan Artificial Intelligence Research Institute, Yibin, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"Center for Future Media and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9349,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72939806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"35","issue":"9","first_page":"9003","last_page":"9016"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.998199999332428,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996399998664856,"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/computer-science","display_name":"Computer science","score":0.6213075518608093},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5734946131706238},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5394642353057861},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4664202630519867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41260620951652527},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3715861439704895},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33573102951049805}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6213075518608093},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5734946131706238},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5394642353057861},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4664202630519867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41260620951652527},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3715861439704895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33573102951049805},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3556422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3556422","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2546663186","display_name":null,"funder_award_id":"62020106008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5045371132","display_name":null,"funder_award_id":"2023ZHYZ0004","funder_id":"https://openalex.org/F4320322922","funder_display_name":"Department of Science and Technology of Sichuan Province"},{"id":"https://openalex.org/G680623718","display_name":null,"funder_award_id":"U22A2097","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6864684409","display_name":null,"funder_award_id":"62122018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7805001638","display_name":null,"funder_award_id":"U23A2031","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8418174427","display_name":null,"funder_award_id":"82441006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G975111477","display_name":null,"funder_award_id":"62425208","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"},{"id":"https://openalex.org/F4320322922","display_name":"Department of Science and Technology of Sichuan Province","ror":"https://ror.org/04323m874"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2124785086","https://openalex.org/W2606982687","https://openalex.org/W2765716052","https://openalex.org/W2896457183","https://openalex.org/W2904291752","https://openalex.org/W2904452845","https://openalex.org/W2963541336","https://openalex.org/W2965373594","https://openalex.org/W2990503944","https://openalex.org/W3027790991","https://openalex.org/W3034730770","https://openalex.org/W3092535672","https://openalex.org/W3111766820","https://openalex.org/W3168640669","https://openalex.org/W3175961224","https://openalex.org/W3197457832","https://openalex.org/W3199693760","https://openalex.org/W3204588463","https://openalex.org/W3205964985","https://openalex.org/W3209229003","https://openalex.org/W4214773477","https://openalex.org/W4250820669","https://openalex.org/W4285787895","https://openalex.org/W4312246181","https://openalex.org/W4312480274","https://openalex.org/W4312864639","https://openalex.org/W4313163028","https://openalex.org/W4319299894","https://openalex.org/W4377235294","https://openalex.org/W4383112678","https://openalex.org/W4385245566","https://openalex.org/W4385574156","https://openalex.org/W4385800837","https://openalex.org/W4386071468","https://openalex.org/W4386075505","https://openalex.org/W4386076140","https://openalex.org/W4386076176","https://openalex.org/W4386076661","https://openalex.org/W4404724811"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2384605597","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2387743295","https://openalex.org/W2366718574","https://openalex.org/W2359774528"],"abstract_inverted_index":{"Video":[0],"Question":[1],"Answering":[2],"(VideoQA)":[3],"is":[4,114,141],"a":[5,103,122,137],"challenging":[6],"task":[7],"in":[8,68,72,95,116,150,192,202],"the":[9,14,21,32,42,64,75,81,130,146,155,160,193],"vision-language":[10],"field.":[11],"Due":[12],"to":[13,41,51,57,125,132,143,157],"time-consuming":[15],"and":[16,47,74,182,199],"labor-intensive":[17],"labeling":[18],"process":[19],"of":[20,44,66,77,100,162],"question-answer":[22],"pairs,":[23],"fully":[24,194],"supervised":[25,195],"methods":[26,191],"are":[27],"no":[28],"longer":[29],"suitable":[30],"for":[31,36,109],"current":[33],"increasing":[34],"demand":[35],"data.":[37],"This":[38],"has":[39],"led":[40],"rise":[43],"zero-shot":[45,59,96,110,172],"VideoQA,":[46],"some":[48],"works":[49],"propose":[50],"adapt":[52],"large":[53],"language":[54,127],"models":[55,128,200],"(LLMs)":[56],"assist":[58],"learning.":[60],"Despite":[61],"recent":[62],"progress,":[63],"inadequacy":[65],"LLMs":[67],"comprehending":[69],"temporal":[70,78,123,134,147],"information":[71],"videos":[73],"neglect":[76],"differences,":[79],"e.g.,":[80],"different":[82,151],"dynamic":[83],"changes":[84],"between":[85],"scenes":[86],"or":[87],"objects,":[88],"remain":[89],"insufficiently":[90],"addressed":[91],"by":[92,178],"existing":[93],"attempts":[94],"VideoQA.":[97],"In":[98],"light":[99],"these":[101],"challenges,":[102],"novel":[104],"Temporal-guided":[105],"Mixture-of-Experts":[106],"Network":[107],"(T-MoENet)":[108],"video":[111],"question":[112],"answering":[113],"proposed":[115,142,165],"this":[117,203],"paper.":[118],"Specifically,":[119],"we":[120],"apply":[121],"module":[124,140],"imbue":[126],"with":[129,189],"capacity":[131,161],"perceive":[133],"information.":[135],"Then":[136],"temporal-guided":[138],"mixture-of-experts":[139],"further":[144],"learn":[145],"differences":[148],"presented":[149],"videos.":[152],"It":[153],"enables":[154],"model":[156],"effectively":[158],"improve":[159],"generalization.":[163],"Our":[164],"method":[166],"achieves":[167],"state-of-the-art":[168],"performance":[169],"on":[170,180,184],"multiple":[171],"VideoQA":[173],"benchmarks,":[174],"notably":[175],"improving":[176],"accuracy":[177],"5.6%":[179],"TGIF-FrameQA":[181],"2.3%":[183],"MSRVTT-QA":[185],"while":[186],"remaining":[187],"competitive":[188],"other":[190],"setting.":[196],"The":[197],"codes":[198],"developed":[201],"study":[204],"will":[205],"be":[206],"made":[207],"publicly":[208],"available":[209],"at":[210],"<uri":[211],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[212],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/qyx1121/T-MoENet</uri>.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
