{"id":"https://openalex.org/W4391408901","doi":"https://doi.org/10.1145/3627631.3627659","title":"Aggregated Co-attention based Visual Question Answering","display_name":"Aggregated Co-attention based Visual Question Answering","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391408901","doi":"https://doi.org/10.1145/3627631.3627659"},"language":"en","primary_location":{"id":"doi:10.1145/3627631.3627659","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627631.3627659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-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/A5009532727","display_name":"Aakansha Mishra","orcid":"https://orcid.org/0000-0002-0792-3006"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Aakansha Mishra","raw_affiliation_strings":["IIT Guwahati, India"],"affiliations":[{"raw_affiliation_string":"IIT Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040626471","display_name":"Ashish Anand","orcid":"https://orcid.org/0000-0002-0024-3358"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashish Anand","raw_affiliation_strings":["Indian Institute of Technology Guwahati, IN"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Guwahati, IN","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041308578","display_name":"Prithwijit Guha","orcid":"https://orcid.org/0000-0003-2885-0026"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prithwijit Guha","raw_affiliation_strings":["IIT Guwahati, IN"],"affiliations":[{"raw_affiliation_string":"IIT Guwahati, IN","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009532727"],"corresponding_institution_ids":["https://openalex.org/I1317621060"],"apc_list":null,"apc_paid":null,"fwci":0.123,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46242859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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":0.9994999766349792,"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":0.9934999942779541,"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":0.918258786201477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6600238680839539},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.42229944467544556},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3786534070968628},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3696134686470032},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1301318109035492},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.06200748682022095}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.918258786201477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6600238680839539},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.42229944467544556},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3786534070968628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3696134686470032},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1301318109035492},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.06200748682022095},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627631.3627659","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627631.3627659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2560730294","https://openalex.org/W2597425697","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2892259963","https://openalex.org/W2916723116","https://openalex.org/W2962779575","https://openalex.org/W2962933067","https://openalex.org/W2963066927","https://openalex.org/W2963150162","https://openalex.org/W2963176022","https://openalex.org/W2963191264","https://openalex.org/W2963383024","https://openalex.org/W2963717374","https://openalex.org/W2963770662","https://openalex.org/W2963954913","https://openalex.org/W2964067226","https://openalex.org/W2964072591","https://openalex.org/W2981694290","https://openalex.org/W2982461533","https://openalex.org/W3019617850","https://openalex.org/W3035497460","https://openalex.org/W3090449556","https://openalex.org/W3135367836","https://openalex.org/W3163142861","https://openalex.org/W4225791300","https://openalex.org/W4301409532","https://openalex.org/W6754553780"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W4288102755","https://openalex.org/W297543570"],"abstract_inverted_index":{"Recent":[0],"developments":[1],"in":[2,14,18,62],"the":[3,89,115,128],"field":[4],"of":[5,83,114,130],"Visual":[6],"Question":[7],"Answering":[8],"(VQA)":[9],"have":[10,25],"witnessed":[11],"promising":[12],"improvements":[13],"performance":[15],"through":[16],"contributions":[17],"attention":[19,29,33,84,132],"based":[20],"networks.":[21],"Most":[22],"such":[23],"approaches":[24],"focused":[26],"on":[27,38,66],"unidirectional":[28],"that":[30],"leverage":[31],"over":[32],"from":[34,91,103],"textual":[35],"domain":[36],"(question)":[37],"visual":[39],"space.":[40],"This":[41],"work":[42],"proposes":[43],"a":[44],"multistage":[45],"co-attention":[46,49,58],"framework.":[47],"Here,":[48],"framework":[50],"performs":[51],"both":[52],"image":[53],"and":[54,73,122,133],"text":[55],"attention.":[56],"The":[57,94],"mechanism":[59],"is":[60,85,118],"repeated":[61],"multiple":[63,98],"stages.":[64,93],"Attention":[65],"different":[67,92,116],"stages":[68,117],"may":[69],"capture":[70],"some":[71],"significant":[72],"distinct":[74],"features":[75],"for":[76,126],"learning":[77],"better":[78],"contextual":[79],"information.":[80],"Thus,":[81],"aggregation":[82],"performed":[86,125],"to":[87],"preserve":[88],"information":[90],"proposed":[95],"architecture":[96],"with":[97],"stage":[99],"network":[100],"could":[101],"suffer":[102],"vanishing":[104],"or":[105],"exploding":[106],"gradients.":[107],"To":[108],"prevent":[109],"this,":[110],"loss":[111],"at":[112],"each":[113],"computed.":[119],"Extensive":[120],"experiments":[121],"analysis":[123],"are":[124],"validating":[127],"effects":[129],"aggregated":[131],"stage-wise":[134],"loss.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}