{"id":"https://openalex.org/W2972113750","doi":"https://doi.org/10.1109/tip.2018.2859820","title":"A Better Way to Attend: Attention With Trees for Video Question Answering","display_name":"A Better Way to Attend: Attention With Trees for Video Question Answering","publication_year":2018,"publication_date":"2018-07-25","ids":{"openalex":"https://openalex.org/W2972113750","doi":"https://doi.org/10.1109/tip.2018.2859820","mag":"2972113750","pmid":"https://pubmed.ncbi.nlm.nih.gov/30047882"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2018.2859820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2018.2859820","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":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1909.02218","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hongyang Xue","orcid":"https://orcid.org/0000-0003-3161-3566"},"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":true,"raw_author_name":"Hongyang Xue","raw_affiliation_strings":["State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenqing Chu","orcid":"https://orcid.org/0000-0003-0816-7975"},"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":"Wenqing Chu","raw_affiliation_strings":["State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhou Zhao","orcid":null},"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":"Zhou Zhao","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":null,"display_name":"Deng Cai","orcid":null},"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":"Deng Cai","raw_affiliation_strings":["State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":1.9123,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.90213898,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"27","issue":"11","first_page":"5563","last_page":"5574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9840999841690063,"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":0.9840999841690063,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0019000000320374966,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0017000000225380063,"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":0.7996000051498413},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.7153000235557556},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6873000264167786},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.5705999732017517},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48249998688697815},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4244999885559082},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.39329999685287476},{"id":"https://openalex.org/keywords/parse-tree","display_name":"Parse tree","score":0.3846000134944916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8339999914169312},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7996000051498413},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7153000235557556},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6873000264167786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6567999720573425},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5978999733924866},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.5705999732017517},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48249998688697815},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.39329999685287476},{"id":"https://openalex.org/C2781466058","wikidata":"https://www.wikidata.org/wiki/Q627921","display_name":"Parse tree","level":3,"score":0.3846000134944916},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2904999852180481},{"id":"https://openalex.org/C188338183","wikidata":"https://www.wikidata.org/wiki/Q80735","display_name":"Stop words","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26570001244544983}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2018.2859820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2018.2859820","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:30047882","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30047882","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},{"id":"pmh:oai:arXiv.org:1909.02218","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.02218","pdf_url":"https://arxiv.org/pdf/1909.02218","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1909.02218","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.02218","pdf_url":"https://arxiv.org/pdf/1909.02218","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1022706131","display_name":null,"funder_award_id":"61602405","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6887114618","display_name":null,"funder_award_id":"61751307","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1586939924","https://openalex.org/W1816079941","https://openalex.org/W1895641373","https://openalex.org/W1933349210","https://openalex.org/W1974991592","https://openalex.org/W2097606805","https://openalex.org/W2130237711","https://openalex.org/W2136480620","https://openalex.org/W2139501017","https://openalex.org/W2154071538","https://openalex.org/W2202226326","https://openalex.org/W2250539671","https://openalex.org/W2302086703","https://openalex.org/W2527145521","https://openalex.org/W2527200148","https://openalex.org/W2962749469","https://openalex.org/W2963191264","https://openalex.org/W2963293463","https://openalex.org/W2963355447","https://openalex.org/W2963576560","https://openalex.org/W2963656855","https://openalex.org/W2963661253","https://openalex.org/W2963890755","https://openalex.org/W2963954913","https://openalex.org/W3037725825","https://openalex.org/W4235505822","https://openalex.org/W6630875275","https://openalex.org/W6632455782","https://openalex.org/W6638318767","https://openalex.org/W6682137061","https://openalex.org/W6719057275","https://openalex.org/W6729805386","https://openalex.org/W6730666313"],"related_works":[],"abstract_inverted_index":{"We":[0,200],"propose":[1,103],"a":[2,47,191],"new":[3],"attention":[4,15,30,41,142,193,220],"model":[5,83,216],"for":[6,84,110],"video":[7,85,111],"question":[8,45,86,97,112,126],"answering.":[9,113],"The":[10,29,128,171,207],"main":[11],"idea":[12],"of":[13,25,74,124,155,167,173,213],"the":[14,21,26,44,51,71,75,78,89,104,120,125,131,135,145,152,156,160,164,168,174,177,186,197,211,218],"models":[16,221],"is":[17,117],"to":[18,185,195],"locate":[19],"on":[20,95,163,204,223],"most":[22,38],"informative":[23],"parts":[24],"visual":[27,40,136],"data.":[28],"mechanisms":[31,42],"are":[32,138,179],"quite":[33],"popular":[34],"these":[35],"days.":[36],"However,":[37],"existing":[39],"regard":[43],"as":[46],"whole.":[48],"They":[49],"ignore":[50],"word-level":[52,90],"semantics":[53],"where":[54,134],"each":[55],"word":[56],"can":[57],"have":[58],"different":[59],"attentions":[60],"and":[61,144,176,181],"some":[62],"words":[63,132,137,175],"need":[64],"no":[65],"attention.":[66],"Neither":[67],"do":[68],"they":[69],"consider":[70],"semantic":[72,153],"structure":[73,154,166],"sentences.":[76,98,127],"Although":[77],"Extended":[79],"Soft":[80],"Attention":[81],"(E-SA)":[82],"answering":[87],"leverages":[88],"attention,":[91],"it":[92],"performs":[93],"poorly":[94],"long":[96],"In":[99],"this":[100],"paper,":[101],"we":[102,189],"heterogeneous":[105],"tree-structured":[106],"memory":[107],"network":[108],"(HTreeMN)":[109],"Our":[114],"proposed":[115],"approach":[116,203],"based":[118,162],"upon":[119],"syntax":[121],"parse":[122,169],"trees":[123],"HTreeMN":[129,215],"treats":[130],"differently":[133],"processed":[139],"with":[140],"an":[141],"module":[143],"verbal":[146],"ones":[147],"not.":[148],"It":[149],"also":[150],"utilizes":[151],"sentences":[157],"by":[158],"combining":[159],"neighbors":[161],"recursive":[165],"trees.":[170],"understandings":[172],"videos":[178],"propagated":[180],"merged":[182],"from":[183],"leaves":[184],"root.":[187],"Furthermore,":[188],"build":[190],"hierarchical":[192],"mechanism":[194],"distill":[196],"attended":[198],"features.":[199],"evaluate":[201],"our":[202,214],"two":[205],"datasets.":[206],"experimental":[208],"results":[209],"show":[210],"superiority":[212],"over":[217],"other":[219],"especially":[222],"complex":[224],"questions.":[225]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2019-09-12T00:00:00"}