{"id":"https://openalex.org/W3163761993","doi":"https://doi.org/10.1109/icpr48806.2021.9412231","title":"Dual Path Multi-Modal High-Order Features for Textual Content based Visual Question Answering","display_name":"Dual Path Multi-Modal High-Order Features for Textual Content based Visual Question Answering","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3163761993","doi":"https://doi.org/10.1109/icpr48806.2021.9412231","mag":"3163761993"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412231","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","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/A5115602129","display_name":"Yanan Li","orcid":"https://orcid.org/0000-0003-2886-1585"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanan Li","raw_affiliation_strings":["Artificial Intelligence Institute, Zhejiang Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Institute, Zhejiang Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044643813","display_name":"Yuetan Lin","orcid":null},"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":"Yuetan Lin","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100570034","display_name":"Honghui Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"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":"Honghui Zhao","raw_affiliation_strings":["Artificial Intelligence Institute, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Institute, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100367955","display_name":"Donghui Wang","orcid":"https://orcid.org/0000-0002-1198-0978"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"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":"Donghui Wang","raw_affiliation_strings":["Artificial Intelligence Institute, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Institute, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4324","last_page":"4331"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9975000023841858,"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":0.9890999794006348,"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":0.85317063331604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7774947881698608},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.672223687171936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6172738075256348},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6022233366966248},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5807263851165771},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.562420129776001},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5319713950157166},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.49490779638290405},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4681667983531952},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45147955417633057},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15174171328544617}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.85317063331604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7774947881698608},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.672223687171936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6172738075256348},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6022233366966248},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5807263851165771},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.562420129776001},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5319713950157166},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.49490779638290405},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4681667983531952},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45147955417633057},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15174171328544617},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412231","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1491389626","https://openalex.org/W1522301498","https://openalex.org/W1575833922","https://openalex.org/W1861492603","https://openalex.org/W1922126009","https://openalex.org/W1933349210","https://openalex.org/W2058556535","https://openalex.org/W2142192571","https://openalex.org/W2151498684","https://openalex.org/W2157331557","https://openalex.org/W2190656909","https://openalex.org/W2194187530","https://openalex.org/W2277195237","https://openalex.org/W2442626797","https://openalex.org/W2519818067","https://openalex.org/W2532034655","https://openalex.org/W2550687635","https://openalex.org/W2553418567","https://openalex.org/W2560730294","https://openalex.org/W2563399268","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2807935099","https://openalex.org/W2809273748","https://openalex.org/W2875814315","https://openalex.org/W2896457183","https://openalex.org/W2938082352","https://openalex.org/W2949197413","https://openalex.org/W2953106684","https://openalex.org/W2962773189","https://openalex.org/W2963150162","https://openalex.org/W2963191264","https://openalex.org/W2963223524","https://openalex.org/W2963224792","https://openalex.org/W2963341956","https://openalex.org/W2963383024","https://openalex.org/W2963398599","https://openalex.org/W2963477107","https://openalex.org/W2963517393","https://openalex.org/W2963622213","https://openalex.org/W2963907629","https://openalex.org/W2963954913","https://openalex.org/W2964018263","https://openalex.org/W2964118342","https://openalex.org/W2964121744","https://openalex.org/W2964138017","https://openalex.org/W2979382951","https://openalex.org/W3005436539","https://openalex.org/W4297749157","https://openalex.org/W4298392976","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6634232107","https://openalex.org/W6639102338","https://openalex.org/W6682086655","https://openalex.org/W6726857151","https://openalex.org/W6728881024","https://openalex.org/W6729791593","https://openalex.org/W6729948091","https://openalex.org/W6738893770","https://openalex.org/W6748270630","https://openalex.org/W6752731419","https://openalex.org/W6755207826","https://openalex.org/W6761069331","https://openalex.org/W7072257459"],"related_works":["https://openalex.org/W3157284875","https://openalex.org/W2259406085","https://openalex.org/W2099715052","https://openalex.org/W4226247999","https://openalex.org/W4213176082","https://openalex.org/W2187398150","https://openalex.org/W3209772662","https://openalex.org/W4200629926","https://openalex.org/W4220955952","https://openalex.org/W4226470070"],"abstract_inverted_index":{"As":[0],"a":[1,35,60,76,144],"typical":[2],"cross-modal":[3],"problem,":[4],"visual":[5,29,91],"question":[6,64,86,99],"answering":[7,87],"(VQA)":[8],"has":[9],"received":[10],"increasing":[11],"attention":[12,112],"from":[13],"the":[14,32,45,90,97,111,133,161,168],"communities":[15],"of":[16],"computer":[17],"vision":[18],"and":[19,24,28,37,92,100,110,117,140,148],"natural":[20,62],"language":[21,63],"processing.":[22],"Reading":[23],"reasoning":[25],"about":[26],"texts":[27,142],"contents":[30],"in":[31,41,143],"images":[33],"is":[34],"burgeoning":[36],"important":[38],"research":[39],"topic":[40],"VQA,":[42],"especially":[43],"for":[44],"visually":[46],"impaired":[47],"assistance":[48],"applications.":[49],"Given":[50],"an":[51,57],"image,":[52,98],"it":[53,104,136],"aims":[54],"to":[55,59,67,114,154],"predict":[56],"answer":[58,156],"provided":[61],"closely":[65],"related":[66],"its":[68],"textual":[69,79,93],"contents.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74],"propose":[75],"novel":[77],"end-to-end":[78],"content":[80],"based":[81,152],"VQA":[82],"model,":[83],"which":[84],"grounds":[85],"both":[88],"on":[89,160],"information.":[94],"After":[95],"encoding":[96],"recognized":[101,141],"text":[102],"words,":[103],"uses":[105],"multi-modal":[106],"factorized":[107],"high-order":[108],"modules":[109],"mechanism":[113],"fuse":[115],"question-image":[116],"question-text":[118],"features":[119,126],"respectively.":[120],"The":[121],"complex":[122],"correlations":[123],"among":[124],"different":[125],"can":[127,171],"be":[128],"captured":[129],"efficiently.":[130],"To":[131],"ensure":[132],"model's":[134],"extendibility,":[135],"embeds":[137],"candidate":[138],"answers":[139],"semantic":[145,150],"embedding":[146,151],"space":[147],"adopts":[149],"classifier":[153],"perform":[155],"prediction.":[157],"Extensive":[158],"experiments":[159],"newly":[162],"proposed":[163,169],"benchmark":[164],"TextVQA":[165],"demonstrate":[166],"that":[167],"model":[170],"achieve":[172],"promising":[173],"results.":[174]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}