{"id":"https://openalex.org/W4295036294","doi":"https://doi.org/10.1109/tip.2022.3205212","title":"Video Question Answering With Prior Knowledge and Object-Sensitive Learning","display_name":"Video Question Answering With Prior Knowledge and Object-Sensitive Learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4295036294","doi":"https://doi.org/10.1109/tip.2022.3205212","pmid":"https://pubmed.ncbi.nlm.nih.gov/36083958"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2022.3205212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3205212","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5087623065","display_name":"Pengpeng Zeng","orcid":"https://orcid.org/0000-0002-0672-3790"},"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":"Pengpeng Zeng","raw_affiliation_strings":["Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-0672-3790","affiliations":[{"raw_affiliation_string":"Future Media Center 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/A5084439574","display_name":"Haonan Zhang","orcid":"https://orcid.org/0000-0003-1015-7338"},"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":["Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-1015-7338","affiliations":[{"raw_affiliation_string":"Future Media Center 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/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2522-6394","affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"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"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2549-8322","affiliations":[{"raw_affiliation_string":"Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"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"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"Future Media Center and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3279,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.93707835,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"5936","last_page":"5948"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9975000023841858,"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":0.9970999956130981,"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/computer-science","display_name":"Computer science","score":0.8409304618835449},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6816860437393188},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5994580984115601},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5694164037704468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5620591044425964},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5583265423774719},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5539742708206177},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5397264957427979},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5177304148674011},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5103723406791687},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49328678846359253},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4350389838218689},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08593869209289551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8409304618835449},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6816860437393188},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5994580984115601},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5694164037704468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5620591044425964},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5583265423774719},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5539742708206177},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5397264957427979},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5177304148674011},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5103723406791687},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49328678846359253},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4350389838218689},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08593869209289551},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2022.3205212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3205212","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:36083958","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36083958","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"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/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/G7314976618","display_name":"\u878d\u5408\u81ea\u7136\u8bed\u8a00\u5904\u7406\u7684\u6df1\u5ea6\u89c6\u89c9\u7406\u89e3\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61872064","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8027008232","display_name":"\u534f\u540c\u6df1\u5ea6\u89c6\u9891\u7406\u89e3\u3001\u63cf\u8ff0\u548c\u89c6\u89c9\u95ee\u7b54\u7684\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61772116","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2425121537","https://openalex.org/W2549139847","https://openalex.org/W2606982687","https://openalex.org/W2745461083","https://openalex.org/W2765716052","https://openalex.org/W2793546384","https://openalex.org/W2798786641","https://openalex.org/W2808124938","https://openalex.org/W2808399042","https://openalex.org/W2904291752","https://openalex.org/W2904452845","https://openalex.org/W2952620298","https://openalex.org/W2954199749","https://openalex.org/W2956018683","https://openalex.org/W2962716332","https://openalex.org/W2962934715","https://openalex.org/W2962949233","https://openalex.org/W2963037989","https://openalex.org/W2963176022","https://openalex.org/W2963541336","https://openalex.org/W2963705779","https://openalex.org/W2963954913","https://openalex.org/W2972113750","https://openalex.org/W2981582341","https://openalex.org/W2997344006","https://openalex.org/W2997805943","https://openalex.org/W2998166190","https://openalex.org/W3003991937","https://openalex.org/W3010593057","https://openalex.org/W3034730770","https://openalex.org/W3096935578","https://openalex.org/W3099849198","https://openalex.org/W3167092180","https://openalex.org/W3172845486","https://openalex.org/W3173367591","https://openalex.org/W3174873881","https://openalex.org/W3176689360","https://openalex.org/W3181758331","https://openalex.org/W3189890868","https://openalex.org/W3201184431","https://openalex.org/W3209229003","https://openalex.org/W4307129979","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6752083267","https://openalex.org/W6766978945","https://openalex.org/W6768853884","https://openalex.org/W6801820131","https://openalex.org/W6803673840","https://openalex.org/W6843731463"],"related_works":["https://openalex.org/W2051167396","https://openalex.org/W207304934","https://openalex.org/W219090214","https://openalex.org/W2970044932","https://openalex.org/W837932596","https://openalex.org/W4377703168","https://openalex.org/W2153799799","https://openalex.org/W2728071886","https://openalex.org/W4281760909","https://openalex.org/W15319282"],"abstract_inverted_index":{"Video":[0],"Question":[1],"Answering":[2],"(VideoQA),":[3],"which":[4,62],"explores":[5],"spatial-temporal":[6],"visual":[7,31,85],"information":[8,86,154],"of":[9,23,77,90,115],"videos":[10],"given":[11],"a":[12,104,131,146],"linguistic":[13,33],"query,":[14],"has":[15],"received":[16],"unprecedented":[17],"attention":[18],"over":[19],"recent":[20],"years.":[21],"One":[22],"the":[24,43,64,74,91,98,113,124,166],"main":[25],"challenges":[26],"lies":[27],"in":[28,63,72],"locating":[29],"relevant":[30],"and":[32,35,107,118,141,189,205,207],"information,":[34],"therefore":[36],"various":[37],"attention-based":[38],"approaches":[39],"are":[40,48],"proposed.":[41],"Despite":[42],"impressive":[44],"progress,":[45],"two":[46,100],"aspects":[47],"not":[49,80],"fully":[50,81],"explored":[51],"by":[52,111,183],"current":[53],"methods":[54],"to":[55,122,139,158,179],"get":[56],"proper":[57],"attention.":[58],"Firstly,":[59],"prior":[60,116,143,163],"knowledge,":[61],"human":[65],"cognitive":[66],"process":[67,76],"plays":[68],"an":[69,153,173],"important":[70],"role":[71],"assisting":[73],"reasoning":[75],"VideoQA,":[78],"is":[79,94,156,214],"utilized.":[82],"Secondly,":[83],"structured":[84],"(e.g.,":[87],"object)":[88],"instead":[89],"raw":[92],"video":[93],"underestimated.":[95],"To":[96],"address":[97],"above":[99],"issues,":[101],"we":[102,128,171],"propose":[103,130,172],"Prior":[105,132],"Knowledge":[106,133],"Object-sensitive":[108,174],"Learning":[109,176],"(PKOL)":[110],"exploring":[112],"effect":[114],"knowledge":[117,144,164],"learning":[119],"object-sensitive":[120,181],"representations":[121],"boost":[123],"VideoQA":[125],"task.":[126],"Specifically,":[127],"first":[129],"Exploring":[134],"(PKE)":[135],"module":[136,178],"that":[137],"aims":[138],"acquire":[140],"integrate":[142],"into":[145],"question":[147],"feature":[148,150],"for":[149],"enriching,":[151],"where":[152],"retriever":[155],"constructed":[157],"retrieve":[159],"related":[160],"sentences":[161],"as":[162],"from":[165],"massive":[167],"corpus.":[168],"In":[169],"addition,":[170],"Representation":[175],"(ORL)":[177],"generate":[180],"features":[182,186],"interacting":[184],"object-level":[185],"with":[187],"frame":[188],"clip-level":[190],"features.":[191],"Our":[192],"proposed":[193],"PKOL":[194],"achieves":[195],"consistent":[196],"improvements":[197],"on":[198],"three":[199],"competitive":[200],"benchmarks":[201],"(i.e.,":[202],"MSVD-QA,":[203],"MSRVTT-QA,":[204],"TGIF-QA)":[206],"gains":[208],"state-of-the-art":[209],"performance.":[210],"The":[211],"source":[212],"code":[213],"available":[215],"at":[216],"https://github.com/zchoi/PKOL.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":18}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}