{"id":"https://openalex.org/W3159630763","doi":"https://doi.org/10.1109/tip.2021.3076556","title":"Adaptive Spatio-Temporal Graph Enhanced Vision-Language Representation for Video QA","display_name":"Adaptive Spatio-Temporal Graph Enhanced Vision-Language Representation for Video QA","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3159630763","doi":"https://doi.org/10.1109/tip.2021.3076556","mag":"3159630763","pmid":"https://pubmed.ncbi.nlm.nih.gov/33950840"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2021.3076556","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3076556","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/A5051494566","display_name":"Weike Jin","orcid":"https://orcid.org/0000-0002-3132-5567"},"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":"Weike Jin","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3132-5567","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"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":"Zhou Zhao","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China","State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6121-0384","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068837264","display_name":"Xiaochun Cao","orcid":"https://orcid.org/0000-0001-7141-708X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochun Cao","raw_affiliation_strings":["Peng Cheng Laboratory, Cyberspace Security Research Center, Shenzhen, China","School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7141-708X","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Cyberspace Security Research Center, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048669373","display_name":"Jieming Zhu","orcid":"https://orcid.org/0000-0002-5666-8320"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieming Zhu","raw_affiliation_strings":["Huawei Noah\u2019s Ark Laboratory, Shenzhen, China","Huawei Noah's Ark Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Noah's Ark Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083350101","display_name":"Xiuqiang He","orcid":"https://orcid.org/0000-0002-4115-8205"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuqiang He","raw_affiliation_strings":["Huawei Noah\u2019s Ark Laboratory, Shenzhen, China","Huawei Noah's Ark Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Noah's Ark Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008666077","display_name":"Yueting Zhuang","orcid":"https://orcid.org/0000-0001-9017-2508"},"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":"Yueting Zhuang","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.621,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.90855791,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"5477","last_page":"5489"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9948999881744385,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9854000210762024,"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":0.8538424968719482},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5834784507751465},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5076748132705688},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4653419256210327},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4313158690929413},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3914693295955658},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3251383304595947},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.3178657293319702}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8538424968719482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5834784507751465},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5076748132705688},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4653419256210327},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4313158690929413},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3914693295955658},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3251383304595947},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3178657293319702}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2021.3076556","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2021.3076556","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:33950840","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33950840","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":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G5526867466","display_name":null,"funder_award_id":"U1611461","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6473908178","display_name":null,"funder_award_id":"2020QNA5024","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6605900608","display_name":null,"funder_award_id":"61751209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7528510259","display_name":"\u57fa\u4e8e\u5927\u89c4\u6a21\u8de8\u5a92\u4f53\u77e5\u8bc6\u7f51\u7edc\u7684\u590d\u6742\u89c6\u9891\u95ee\u7b54\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61836002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8365256475","display_name":null,"funder_award_id":"LR19F020006","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G8990919479","display_name":null,"funder_award_id":"2018AAA0100603","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1933349210","https://openalex.org/W2056935845","https://openalex.org/W2131494463","https://openalex.org/W2277195237","https://openalex.org/W2293453011","https://openalex.org/W2412393473","https://openalex.org/W2425121537","https://openalex.org/W2463565445","https://openalex.org/W2560730294","https://openalex.org/W2565656701","https://openalex.org/W2606982687","https://openalex.org/W2732016772","https://openalex.org/W2745461083","https://openalex.org/W2753311918","https://openalex.org/W2765716052","https://openalex.org/W2774267535","https://openalex.org/W2798786641","https://openalex.org/W2808399042","https://openalex.org/W2832876791","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2904291752","https://openalex.org/W2907820376","https://openalex.org/W2916723116","https://openalex.org/W2948358897","https://openalex.org/W2949178656","https://openalex.org/W2951008357","https://openalex.org/W2954199749","https://openalex.org/W2962781483","https://openalex.org/W2962949233","https://openalex.org/W2963115613","https://openalex.org/W2963383024","https://openalex.org/W2963541336","https://openalex.org/W2963656855","https://openalex.org/W2963781647","https://openalex.org/W2963800628","https://openalex.org/W2963890755","https://openalex.org/W2963954913","https://openalex.org/W2964015378","https://openalex.org/W2964067226","https://openalex.org/W2964760297","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W2975813532","https://openalex.org/W2981851019","https://openalex.org/W2981985547","https://openalex.org/W2984008963","https://openalex.org/W2997591391","https://openalex.org/W2997805943","https://openalex.org/W2998166190","https://openalex.org/W2998356391","https://openalex.org/W3023993913","https://openalex.org/W3025665229","https://openalex.org/W3034730770","https://openalex.org/W3035218869","https://openalex.org/W3035265375","https://openalex.org/W3035356601","https://openalex.org/W3035635319","https://openalex.org/W3093471110","https://openalex.org/W3102887392","https://openalex.org/W4249013746","https://openalex.org/W6620707391","https://openalex.org/W6638318767","https://openalex.org/W6679844565","https://openalex.org/W6697449767","https://openalex.org/W6715144786","https://openalex.org/W6719057275","https://openalex.org/W6720468700","https://openalex.org/W6726873649","https://openalex.org/W6730666313","https://openalex.org/W6747225742","https://openalex.org/W6755207826","https://openalex.org/W6763170755","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6767279747","https://openalex.org/W6768263079","https://openalex.org/W6772396866","https://openalex.org/W6782511416"],"related_works":["https://openalex.org/W4389850132","https://openalex.org/W1574724839","https://openalex.org/W2365286546","https://openalex.org/W2377190948","https://openalex.org/W4221117092","https://openalex.org/W4361855866","https://openalex.org/W2096476311","https://openalex.org/W169721953","https://openalex.org/W1965900363","https://openalex.org/W1623638113"],"abstract_inverted_index":{"Vision-language":[0],"research":[1],"has":[2],"become":[3],"very":[4],"popular,":[5],"which":[6],"focuses":[7],"on":[8,42,166],"understanding":[9],"of":[10,26,129,150,160],"visual":[11,158],"contents,":[12],"language":[13],"semantics":[14],"and":[15,39,79],"relationships":[16],"between":[17],"them.":[18],"Video":[19,59,170],"question":[20],"answering":[21],"(Video":[22],"QA)":[23],"is":[24,80],"one":[25],"the":[27,51,58,117,126,157,161,178],"typical":[28],"tasks.":[29,45],"Recently,":[30],"several":[31],"BERT":[32],"style":[33],"pre-training":[34,74,96],"methods":[35],"have":[36],"been":[37],"proposed":[38],"shown":[40],"effectiveness":[41],"various":[43],"vision-language":[44,53,118,162],"In":[46],"this":[47],"work,":[48],"we":[49,63,123,145],"leverage":[50,94],"successful":[52],"transformer":[54,163],"structure":[55],"to":[56,82,93,97,115,133],"solve":[57],"QA":[60,171],"problem.":[61],"However,":[62],"do":[64],"not":[65],"pre-train":[66],"it":[67],"with":[68,84,99],"any":[69],"video":[70,73,153],"data,":[71],"because":[72],"requires":[75],"massive":[76],"computing":[77],"resources":[78],"hard":[81],"perform":[83],"only":[85],"a":[86,104,139,148],"few":[87],"GPUs.":[88],"Instead,":[89],"our":[90,175],"work":[91],"aims":[92],"image-language":[95],"help":[98],"video-language":[100],"modeling,":[101],"by":[102],"sharing":[103],"common":[105],"module":[106],"design.":[107],"We":[108],"further":[109],"introduce":[110],"an":[111],"adaptive":[112],"spatio-temporal":[113,127,135],"graph":[114,141],"enhance":[116],"representation":[119],"learning.":[120],"That":[121],"is,":[122],"adaptively":[124],"refine":[125],"tubes":[128],"salient":[130],"objects":[131],"according":[132],"their":[134],"relations":[136],"learned":[137],"through":[138],"hierarchical":[140],"convolution":[142],"process.":[143],"Finally,":[144],"can":[146],"obtain":[147],"number":[149],"fine-grained":[151],"tube-level":[152],"object":[154],"representations,":[155],"as":[156],"inputs":[159],"module.":[164],"Experiments":[165],"three":[167],"widely":[168],"used":[169],"datasets":[172],"show":[173],"that":[174],"model":[176],"achieves":[177],"new":[179],"state-of-the-art":[180],"results.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}