{"id":"https://openalex.org/W3206675006","doi":"https://doi.org/10.1145/3474085.3475193","title":"Progressive Graph Attention Network for Video Question Answering","display_name":"Progressive Graph Attention Network for Video Question Answering","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206675006","doi":"https://doi.org/10.1145/3474085.3475193","mag":"3206675006"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475193","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5063303076","display_name":"Liang Peng","orcid":"https://orcid.org/0000-0002-0576-1429"},"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":"Liang Peng","raw_affiliation_strings":["University of Electronic Science and Technology of China, chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083003270","display_name":"Shuangji Yang","orcid":null},"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":"Shuangji Yang","raw_affiliation_strings":["University of Electronic Science and Technology of China, chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024408423","display_name":"Yi Bin","orcid":"https://orcid.org/0000-0001-9714-8738"},"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":"Yi Bin","raw_affiliation_strings":["University of Electronic Science and Technology of China, chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100334018","display_name":"Guoqing Wang","orcid":"https://orcid.org/0000-0002-3938-5994"},"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":"Guoqing Wang","raw_affiliation_strings":["University of Electronic Science and Technology of China, chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2871","last_page":"2879"},"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/T10812","display_name":"Human Pose and Action Recognition","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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9909999966621399,"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":0.8464365601539612},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6628763675689697},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.6500629782676697},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5437551140785217},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5343742966651917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5239714980125427},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.521649181842804},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.4740709364414215},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4670146107673645},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4233565330505371},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4003962576389313},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33993247151374817},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2571914792060852}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8464365601539612},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6628763675689697},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.6500629782676697},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5437551140785217},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5343742966651917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5239714980125427},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.521649181842804},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.4740709364414215},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4670146107673645},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4233565330505371},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4003962576389313},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33993247151374817},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2571914792060852},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475193","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6299999952316284,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2464018058","display_name":null,"funder_award_id":"U20B2063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6438814647","display_name":null,"funder_award_id":"ZYGX2019Z015","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8993851716","display_name":null,"funder_award_id":"BX2021055 and 2021M690027","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2142192571","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2412400526","https://openalex.org/W2532034655","https://openalex.org/W2553418567","https://openalex.org/W2560730294","https://openalex.org/W2624614404","https://openalex.org/W2732016772","https://openalex.org/W2755385356","https://openalex.org/W2766237723","https://openalex.org/W2904323922","https://openalex.org/W2904452845","https://openalex.org/W2937305817","https://openalex.org/W2948358897","https://openalex.org/W2950178297","https://openalex.org/W2950761309","https://openalex.org/W2951024719","https://openalex.org/W2953106684","https://openalex.org/W2962934715","https://openalex.org/W2962949233","https://openalex.org/W2963150162","https://openalex.org/W2963717374","https://openalex.org/W2963954913","https://openalex.org/W2964345214","https://openalex.org/W2981578638","https://openalex.org/W2981582341","https://openalex.org/W2981985547","https://openalex.org/W2997344006","https://openalex.org/W2997805943","https://openalex.org/W2998166190","https://openalex.org/W3034730770","https://openalex.org/W3037773948","https://openalex.org/W3135856559","https://openalex.org/W3169472988"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2378211422","https://openalex.org/W2914694625","https://openalex.org/W4297783004","https://openalex.org/W4214591816","https://openalex.org/W4312650216","https://openalex.org/W4221155265","https://openalex.org/W3109142545","https://openalex.org/W3042849301","https://openalex.org/W2590022237"],"abstract_inverted_index":{"Video":[0],"question":[1,11],"answering~(Video-QA)":[2],"is":[3],"a":[4,8,17,48,147,174,181],"task":[5],"of":[6,16,80],"answering":[7],"natural":[9],"language":[10],"related":[12],"to":[13,34,120,150,157,187],"the":[14,23,37,61,72,86,94,97,101,105,115,122,127,131,152,162,189,195,203,207],"content":[15],"video.":[18],"Existing":[19],"methods":[20],"generally":[21],"explore":[22,60],"single":[24],"interactions":[25,116],"between":[26,29,91,104,117,136],"objects":[27,92],"or":[28],"frames,":[30],"which":[31,57],"are":[32,144,168,223],"insufficient":[33],"deal":[35],"with":[36,172],"sophisticated":[38],"scenes":[39],"in":[40,71,146],"videos.":[41],"To":[42],"tackle":[43],"this":[44],"problem,":[45],"we":[46,76,160],"propose":[47],"novel":[49],"model,":[50],"termed":[51],"Progressive":[52],"Graph":[53],"Attention":[54],"Network":[55],"(PGAT),":[56],"can":[58],"jointly":[59],"multiple":[62],"visual":[63,153],"relations":[64,90,103,135,154],"on":[65,185,198],"object-level,":[66],"frame-level":[67,112],"and":[68,88,133,179,202,206,221],"clip-level.":[69],"Specifically,":[70],"object-level":[73],"relation":[74],"encoding,":[75],"design":[77],"two":[78],"kinds":[79],"complementary":[81],"graphs,":[82],"one":[83],"for":[84,99,161],"learning":[85],"spatial":[87],"semantic":[89,134],"from":[93,108,139,155],"same":[95,106],"frame,":[96],"other":[98,216],"modeling":[100],"temporal":[102,132],"object":[107],"different":[109],"frames.":[110],"The":[111],"graph":[113,129],"explores":[114],"diverse":[118],"frames":[119],"record":[121],"fine-grained":[123],"appearance":[124],"change,":[125],"while":[126],"clip-level":[128],"models":[130],"various":[137],"actions":[138],"clips.":[140],"These":[141],"different-level":[142],"graphs":[143],"concatenated":[145],"progressive":[148],"manner":[149],"learn":[151],"low-level":[156],"high-level.":[158],"Furthermore,":[159],"first":[163],"time":[164],"identified":[165],"that":[166,211],"there":[167],"serious":[169],"answer":[170],"biases":[171],"TGIF-QA,":[173],"very":[175],"large":[176],"Video-QA":[177],"dataset,":[178],"reconstructed":[180],"new":[182,204],"dataset":[183,222],"based":[184],"it":[186],"overcome":[188],"biases,":[190],"called":[191],"TGIF-QA-R.":[192],"We":[193],"evaluate":[194],"proposed":[196],"model":[197,213],"three":[199],"benchmark":[200],"datasets":[201],"TGIF-QA-R,":[205],"experimental":[208],"results":[209],"demonstrate":[210],"our":[212],"significantly":[214],"outperforms":[215],"state-of-the-art":[217],"models.":[218],"Our":[219],"codes":[220],"available":[224],"at":[225],"https://github.com/PengLiang-cn/PGAT.":[226]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}