{"id":"https://openalex.org/W2904452845","doi":"https://doi.org/10.1609/aaai.v33i01.33018658","title":"Beyond RNNs: Positional Self-Attention with Co-Attention for Video Question Answering","display_name":"Beyond RNNs: Positional Self-Attention with Co-Attention for Video Question Answering","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2904452845","doi":"https://doi.org/10.1609/aaai.v33i01.33018658","mag":"2904452845"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33018658","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018658","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4887/4760","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4887/4760","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101598763","display_name":"Xiangpeng Li","orcid":"https://orcid.org/0000-0001-5350-5780"},"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":"Xiangpeng Li","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of 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":[{"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":"Lianli Gao","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024067284","display_name":"Xianglong Liu","orcid":"https://orcid.org/0000-0001-8425-4195"},"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":"Xianglong Liu","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032642601","display_name":"Wenbing Huang","orcid":"https://orcid.org/0000-0002-2566-4159"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbing Huang","raw_affiliation_strings":["Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038668215","display_name":"Xiangnan He","orcid":"https://orcid.org/0000-0001-8472-7992"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiangnan He","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040877128","display_name":"Chuang Gan","orcid":"https://orcid.org/0000-0003-4031-5886"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuang Gan","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":268,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"8658","last_page":"8665"},"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":0.9941999912261963,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9934999942779541,"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":0.836276650428772},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7947717905044556},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7869559526443481},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7495794296264648},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6980432868003845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.535485565662384},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44531917572021484},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.43173742294311523},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34314805269241333},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.23562294244766235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.836276650428772},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7947717905044556},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7869559526443481},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7495794296264648},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6980432868003845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.535485565662384},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44531917572021484},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.43173742294311523},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34314805269241333},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.23562294244766235},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33018658","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018658","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4887/4760","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4887","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33018658","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33018658","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4887/4760","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3623292902","display_name":null,"funder_award_id":"61632007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6598207522","display_name":null,"funder_award_id":"ZYGX2014J063","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7095600686","display_name":null,"funder_award_id":"61602049","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"},{"id":"https://openalex.org/G8167822162","display_name":null,"funder_award_id":"ZYGX2016J085","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2904452845.pdf","grobid_xml":"https://content.openalex.org/works/W2904452845.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W2171810632","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2293453011","https://openalex.org/W2531409750","https://openalex.org/W2546696630","https://openalex.org/W2551396370","https://openalex.org/W2559818034","https://openalex.org/W2565656701","https://openalex.org/W2606982687","https://openalex.org/W2613904329","https://openalex.org/W2621571501","https://openalex.org/W2737766105","https://openalex.org/W2739107216","https://openalex.org/W2745132836","https://openalex.org/W2766749819","https://openalex.org/W2788533147","https://openalex.org/W2794578224","https://openalex.org/W2798858969","https://openalex.org/W2804078698","https://openalex.org/W2807941860","https://openalex.org/W2952467640","https://openalex.org/W2962938145","https://openalex.org/W2963351113","https://openalex.org/W2963521239","https://openalex.org/W2963954913","https://openalex.org/W2964345214","https://openalex.org/W3023993913","https://openalex.org/W4295253143","https://openalex.org/W4385245566","https://openalex.org/W6666761814","https://openalex.org/W6687483927","https://openalex.org/W6691431627","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6752083267","https://openalex.org/W6752378368","https://openalex.org/W6780493881"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2378211422","https://openalex.org/W2387743295","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W2086519370","https://openalex.org/W2028665553","https://openalex.org/W4225394202","https://openalex.org/W3031223029"],"abstract_inverted_index":{"Most":[0],"of":[1,39,65,96,106,118,161,169,177,183,230,233],"the":[2,19,36,63,78,89,103,112,116,132,137,145,159,166,175,187,196,206,221,228],"recent":[3],"progresses":[4],"on":[5,11,186,198,205],"visual":[6,178],"question":[7,58,107,119,179],"answering":[8],"are":[9,23],"based":[10],"recurrent":[12],"neural":[13],"networks":[14],"(RNNs)":[15],"with":[16,48,172,220],"attention.":[17],"Despite":[18],"success,":[20],"these":[21],"models":[22],"often":[24],"timeconsuming":[25],"and":[26,92,108,114,120,201,215],"having":[27],"difficulties":[28],"in":[29,67,111,124,127],"modeling":[30,150],"long":[31],"range":[32],"dependencies":[33,105],"due":[34],"to":[35,76,85,129,131,136,153],"sequential":[37],"nature":[38],"RNNs.":[40],"We":[41],"propose":[42,72],"a":[43,73],"new":[44],"architecture,":[45],"Positional":[46,74],"Self-Attention":[47,75],"Coattention":[49],"(PSAC),":[50],"which":[51],"does":[52],"not":[53],"require":[54],"RNNs":[55,171],"for":[56,174],"video":[57,121,133,141],"answering.":[59,180],"Specifically,":[60],"inspired":[61],"by":[62,83,148],"success":[64],"self-attention":[66],"machine":[68],"translation":[69],"task,":[70],"we":[71,143],"calculate":[77],"response":[79],"at":[80],"each":[81,231],"position":[82],"attending":[84,130],"all":[86],"positions":[87],"within":[88],"same":[90],"sequence,":[91],"then":[93],"add":[94],"representations":[95],"absolute":[97],"positions.":[98],"Therefore,":[99],"PSAC":[100],"can":[101],"exploit":[102],"global":[104],"temporal":[109],"information":[110],"video,":[113],"make":[115],"process":[117],"encoding":[122],"executed":[123],"parallel.":[125],"Furthermore,":[126],"addition":[128],"features":[134],"relevant":[135],"given":[138],"questions":[139],"(i.e.,":[140],"attention),":[142],"utilize":[144],"co-attention":[146],"mechanism":[147],"simultaneously":[149],"\u201cwhat":[151],"words":[152],"listen":[154],"to\u201d":[155],"(question":[156],"attention).":[157],"To":[158],"best":[160],"our":[162,192,234],"knowledge,":[163],"this":[164],"is":[165],"first":[167],"work":[168],"replacing":[170],"selfattention":[173],"task":[176],"Experimental":[181],"results":[182],"four":[184],"tasks":[185,200],"benchmark":[188],"dataset":[189],"show":[190],"that":[191],"model":[193,210],"significantly":[194],"outperforms":[195],"state-of-the-art":[197],"three":[199],"attains":[202],"comparable":[203],"result":[204],"Count":[207],"task.":[208],"Our":[209],"requires":[211],"less":[212],"computation":[213],"time":[214],"achieves":[216],"better":[217],"performance":[218],"compared":[219],"RNNs-based":[222],"methods.":[223],"Additional":[224],"ablation":[225],"study":[226],"demonstrates":[227],"effect":[229],"component":[232],"proposed":[235],"model.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":56},{"year":2022,"cited_by_count":43},{"year":2021,"cited_by_count":61},{"year":2020,"cited_by_count":51},{"year":2019,"cited_by_count":11}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}