{"id":"https://openalex.org/W2964057271","doi":"https://doi.org/10.1145/3320061","title":"Spatiotemporal-Textual Co-Attention Network for Video Question Answering","display_name":"Spatiotemporal-Textual Co-Attention Network for Video Question Answering","publication_year":2019,"publication_date":"2019-04-30","ids":{"openalex":"https://openalex.org/W2964057271","doi":"https://doi.org/10.1145/3320061","mag":"2964057271"},"language":"en","primary_location":{"id":"doi:10.1145/3320061","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3320061","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5003217535","display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zheng-Jun Zha","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-2510-8993","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320739","display_name":"Jiawei Liu","orcid":"https://orcid.org/0000-0001-9940-6366"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Liu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042851991","display_name":"Tianhao Yang","orcid":"https://orcid.org/0009-0004-8864-0420"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhao Yang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003217535"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":2.6549,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.92245728,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"15","issue":"2s","first_page":"1","last_page":"18"},"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":0.9937000274658203,"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":0.9896000027656555,"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/question-answering","display_name":"Question answering","score":0.9329515695571899},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8542899489402771},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6262494325637817},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.600078284740448},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.462191641330719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4050023555755615},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3775196075439453},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.363239586353302}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.9329515695571899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8542899489402771},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6262494325637817},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.600078284740448},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.462191641330719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4050023555755615},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3775196075439453},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.363239586353302},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3320061","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3320061","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4530701113","display_name":null,"funder_award_id":"WK2100100030","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5276383603","display_name":null,"funder_award_id":"61622211","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1488163396","https://openalex.org/W1522734439","https://openalex.org/W1686810756","https://openalex.org/W1933349210","https://openalex.org/W1950136256","https://openalex.org/W2110275531","https://openalex.org/W2189070436","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2293453011","https://openalex.org/W2402144811","https://openalex.org/W2412393473","https://openalex.org/W2425121537","https://openalex.org/W2463565445","https://openalex.org/W2526833393","https://openalex.org/W2565639579","https://openalex.org/W2575842049","https://openalex.org/W2606982687","https://openalex.org/W2620666060","https://openalex.org/W2678677036","https://openalex.org/W2732016772","https://openalex.org/W2735159761","https://openalex.org/W2741903908","https://openalex.org/W2745461083","https://openalex.org/W2746726611","https://openalex.org/W2751525844","https://openalex.org/W2751804245","https://openalex.org/W2752803734","https://openalex.org/W2763874937","https://openalex.org/W2765716052","https://openalex.org/W2766690867","https://openalex.org/W2769602762","https://openalex.org/W2771558241","https://openalex.org/W2791295466","https://openalex.org/W2798786641","https://openalex.org/W2798895485","https://openalex.org/W2803629456","https://openalex.org/W2808203533","https://openalex.org/W2887585070","https://openalex.org/W2889578543","https://openalex.org/W2912152775","https://openalex.org/W2950133940","https://openalex.org/W2953106684","https://openalex.org/W2962749469","https://openalex.org/W2962911528","https://openalex.org/W2962933067","https://openalex.org/W2962938145","https://openalex.org/W2962949233","https://openalex.org/W2963148311","https://openalex.org/W2963191264","https://openalex.org/W2963446712","https://openalex.org/W2963576560","https://openalex.org/W2963656855","https://openalex.org/W2963672682","https://openalex.org/W2963890755","https://openalex.org/W2963954913","https://openalex.org/W2963981422","https://openalex.org/W2964118342","https://openalex.org/W2964322347","https://openalex.org/W3105136412","https://openalex.org/W4234552385"],"related_works":["https://openalex.org/W3157284875","https://openalex.org/W2147241511","https://openalex.org/W2259406085","https://openalex.org/W2099715052","https://openalex.org/W4226247999","https://openalex.org/W3090872036","https://openalex.org/W3209772662","https://openalex.org/W4200629926","https://openalex.org/W4220955952","https://openalex.org/W4287868219"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"is":[4,101,134],"to":[5,91,103,136,147,164],"provide":[6],"a":[7,12,20,47,97,109,142],"natural":[8,21],"language":[9,22],"answer":[10,162],"for":[11,40,53,87],"pair":[13],"of":[14,119,124,150,173,185],"an":[15,161],"image":[16,34],"or":[17],"video":[18,41,54,106,154,174],"and":[19,37,62,84,155,179],"question.":[23,151],"Despite":[24],"recent":[25],"progress":[26],"on":[27,33,66,73,77,117,169],"VQA,":[28],"existing":[29],"works":[30],"primarily":[31],"focus":[32],"question":[35,42,55,139,156,175],"answering":[36,88],"are":[38,158],"suboptimal":[39],"answering.":[43,56],"This":[44],"article":[45],"presents":[46],"novel":[48],"Spatiotemporal-Textual":[49],"Co-Attention":[50],"Network":[51],"(STCA-Net)":[52],"The":[57,152],"STCA-Net":[58],"jointly":[59],"learns":[60],"spatially":[61],"temporally":[63],"visual":[64,83],"attention":[65,72,99,111,132,144],"videos":[67],"as":[68,70],"well":[69],"textual":[71,85,143],"questions.":[74],"It":[75,113],"concentrates":[76,114],"the":[78,115,122,127,183,186],"essential":[79],"cues":[80],"in":[81],"both":[82],"spaces":[86],"question,":[89],"leading":[90,146],"effective":[92],"question-video":[93],"representation.":[94],"In":[95],"particular,":[96],"question-guided":[98],"network":[100,116,133],"designed":[102],"learn":[104,137],"question-aware":[105],"representation":[107,140],"with":[108,141],"spatial-temporal":[110],"module.":[112],"regions":[118],"interest":[120,125],"within":[121],"frames":[123],"across":[126],"entire":[128],"video.":[129],"A":[130],"video-guided":[131],"proposed":[135,187],"video-aware":[138],"module,":[145],"fine-grained":[148],"understanding":[149],"learned":[153],"representations":[157],"used":[159],"by":[160],"predictor":[163],"generate":[165],"answers.":[166],"Extensive":[167],"experiments":[168],"two":[170],"challenging":[171],"datasets":[172],"answering,":[176],"i.e.,":[177],"MSVD-QA":[178],"MSRVTT-QA,":[180],"have":[181],"shown":[182],"effectiveness":[184],"approach.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}