{"id":"https://openalex.org/W4205492448","doi":"https://doi.org/10.1109/tip.2022.3142526","title":"Cross-Attentional Spatio-Temporal Semantic Graph Networks for Video Question Answering","display_name":"Cross-Attentional Spatio-Temporal Semantic Graph Networks for Video Question Answering","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4205492448","doi":"https://doi.org/10.1109/tip.2022.3142526","pmid":"https://pubmed.ncbi.nlm.nih.gov/35044914"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2022.3142526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3142526","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":null,"display_name":"Yun Liu","orcid":"https://orcid.org/0000-0002-3557-6179"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yun Liu","raw_affiliation_strings":["Moutai Institute, Renhuai, China"],"affiliations":[{"raw_affiliation_string":"Moutai Institute, Renhuai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoming Zhang","orcid":"https://orcid.org/0000-0002-6662-4102"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]},{"id":"https://openalex.org/I890469752","display_name":"Ministry of Industry and Information Technology","ror":"https://ror.org/0385nmy68","country_code":"CN","type":"government","lineage":["https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Zhang","raw_affiliation_strings":["Key Laboratory of Aerospace Network Security, Ministry of Industry and Information Technology, School of Cyberspace Science and Technology, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Aerospace Network Security, Ministry of Industry and Information Technology, School of Cyberspace Science and Technology, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I890469752","https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Feiran Huang","orcid":"https://orcid.org/0000-0003-4294-0212"},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiran Huang","raw_affiliation_strings":["College of Cyber Security/College of Information Science and Technology, Jinan University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Cyber Security/College of Information Science and Technology, Jinan University, Guangzhou, China","institution_ids":["https://openalex.org/I159948400"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bo Zhang","orcid":"https://orcid.org/0000-0002-3555-8202"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]},{"id":"https://openalex.org/I890469752","display_name":"Ministry of Industry and Information Technology","ror":"https://ror.org/0385nmy68","country_code":"CN","type":"government","lineage":["https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhang","raw_affiliation_strings":["Key Laboratory of Aerospace Network Security, Ministry of Industry and Information Technology, School of Cyberspace Science and Technology, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Aerospace Network Security, Ministry of Industry and Information Technology, School of Cyberspace Science and Technology, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I890469752","https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhoujun Li","orcid":"https://orcid.org/0000-0002-9603-9713"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhoujun Li","raw_affiliation_strings":["State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5729,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.94108082,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"1684","last_page":"1696"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9958999752998352,"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":0.9958999752998352,"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/T10028","display_name":"Topic Modeling","score":0.000699999975040555,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0005000000237487257,"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":0.7353000044822693},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6385999917984009},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6144999861717224},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.48159998655319214},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.46320000290870667},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4449000060558319},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.4323999881744385},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.36550000309944153},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3472000062465668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8015000224113464},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7353000044822693},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6385999917984009},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6144999861717224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6069999933242798},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.48159998655319214},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.46320000290870667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44850000739097595},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.4323999881744385},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39160001277923584},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38989999890327454},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3472000062465668},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.3057999908924103},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C234837","wikidata":"https://www.wikidata.org/wiki/Q1420493","display_name":"Conceptual graph","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2022.3142526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3142526","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:35044914","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35044914","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":[],"awards":[{"id":"https://openalex.org/G2323930268","display_name":null,"funder_award_id":"U1636211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3470454067","display_name":null,"funder_award_id":"61906075","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5152102630","display_name":null,"funder_award_id":"U1636210","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5545615564","display_name":null,"funder_award_id":"4182037","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G576546066","display_name":null,"funder_award_id":"61932010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7975877154","display_name":null,"funder_award_id":"2019A1515011920","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2425121537","https://openalex.org/W2430055109","https://openalex.org/W2565656701","https://openalex.org/W2606982687","https://openalex.org/W2737435850","https://openalex.org/W2741903908","https://openalex.org/W2751525844","https://openalex.org/W2765440071","https://openalex.org/W2765716052","https://openalex.org/W2766690867","https://openalex.org/W2807174321","https://openalex.org/W2808181286","https://openalex.org/W2890904455","https://openalex.org/W2896294941","https://openalex.org/W2897857500","https://openalex.org/W2904291752","https://openalex.org/W2904452845","https://openalex.org/W2950733407","https://openalex.org/W2954199749","https://openalex.org/W2962949233","https://openalex.org/W2963150162","https://openalex.org/W2963890755","https://openalex.org/W2963954913","https://openalex.org/W2964220823","https://openalex.org/W2966238183","https://openalex.org/W2969897437","https://openalex.org/W2972113750","https://openalex.org/W2974161034","https://openalex.org/W2981582341","https://openalex.org/W2981985547","https://openalex.org/W2982139784","https://openalex.org/W2996763163","https://openalex.org/W2997344006","https://openalex.org/W2997805943","https://openalex.org/W2998159097","https://openalex.org/W2998166190","https://openalex.org/W3023993913","https://openalex.org/W3027790991","https://openalex.org/W3034730770","https://openalex.org/W3152635550","https://openalex.org/W3167092180","https://openalex.org/W3168640669","https://openalex.org/W4256350387","https://openalex.org/W6631190155","https://openalex.org/W6638318767","https://openalex.org/W6684090549","https://openalex.org/W6719057275","https://openalex.org/W6739901393","https://openalex.org/W6762207533","https://openalex.org/W6768853884","https://openalex.org/W6792405717","https://openalex.org/W6798359198","https://openalex.org/W6801791115"],"related_works":[],"abstract_inverted_index":{"Due":[0],"to":[1,34,53,99,133,150,170],"the":[2,116,126,141,152,163,172,182],"rich":[3],"spatio-temporal":[4,128,159],"visual":[5,28],"content":[6,40],"and":[7,20,41,58,94,121,137,143,162,184],"complex":[8],"multimodal":[9],"relations,":[10],"Video":[11],"Question":[12],"Answering":[13],"(VideoQA)":[14],"has":[15],"become":[16],"a":[17,66,75,87,107],"challenging":[18],"task":[19],"attracted":[21],"increasing":[22],"attention.":[23],"Current":[24],"methods":[25,46],"usually":[26],"leverage":[27],"attention,":[29,31],"linguistic":[30],"or":[32],"self-attention":[33],"uncover":[35],"latent":[36],"correlations":[37,60],"between":[38,50,103],"video":[39,118],"question":[42,122],"semantics.":[43],"Although":[44],"these":[45],"exploit":[47],"interactive":[48],"information":[49,145],"different":[51,104],"modalities":[52,105],"improve":[54],"comprehension":[55],"ability,":[56],"inter-":[57,136],"intra-modality":[59,138],"cannot":[61],"be":[62],"effectively":[63],"integrated":[64],"in":[65,106,124],"uniform":[67],"model.":[68],"To":[69],"address":[70],"this":[71],"problem,":[72],"we":[73],"propose":[74],"novel":[76],"VideoQA":[77,179],"model":[78,188],"called":[79],"Cross-Attentional":[80],"Spatio-Temporal":[81],"Semantic":[82],"Graph":[83],"Networks":[84],"(CASSG).":[85],"Specifically,":[86],"multi-head":[88],"multi-hop":[89],"attention":[90],"module":[91],"with":[92,190],"diversity":[93],"progressivity":[95],"is":[96,148],"first":[97],"proposed":[98,149],"explore":[100],"fine-grained":[101],"interactions":[102],"crossing":[108],"manner.":[109],"Then,":[110],"heterogeneous":[111],"graphs":[112,130,161],"are":[113,131],"constructed":[114],"from":[115,157,167],"cross-attended":[117],"frames,":[119],"clips,":[120],"words,":[123],"which":[125],"multi-stream":[127,158],"semantic":[129,160],"designed":[132],"synchronously":[134],"reasoning":[135,154],"correlations.":[139],"Last,":[140],"global":[142,164],"local":[144,153],"fusion":[146],"method":[147],"coalesce":[151],"vector":[155,165],"learned":[156,166],"another":[168],"branch":[169],"infer":[171],"answer.":[173],"Experimental":[174],"results":[175],"on":[176],"three":[177],"public":[178],"datasets":[180],"confirm":[181],"effectiveness":[183],"superiority":[185],"of":[186],"our":[187],"compared":[189],"state-of-the-art":[191],"methods.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2022-01-26T00:00:00"}