{"id":"https://openalex.org/W4391408891","doi":"https://doi.org/10.1145/3627631.3627670","title":"S-VQA: Sentence-Based Visual Question Answering","display_name":"S-VQA: Sentence-Based Visual Question Answering","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391408891","doi":"https://doi.org/10.1145/3627631.3627670"},"language":"en","primary_location":{"id":"doi:10.1145/3627631.3627670","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627631.3627670","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/A5048648865","display_name":"Sanchit Pathak","orcid":"https://orcid.org/0009-0005-7273-709X"},"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":"Sanchit Pathak","raw_affiliation_strings":["Data Science (Interdisciplinary), Indian Institute of Technology Guwahati, IN"],"affiliations":[{"raw_affiliation_string":"Data Science (Interdisciplinary), Indian Institute of Technology Guwahati, IN","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101832712","display_name":"Garima Singh","orcid":"https://orcid.org/0009-0004-0862-9978"},"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":"Garima Singh","raw_affiliation_strings":["Data Science (Interdisciplinary), Indian Institute of Technology Guwahati, IN"],"affiliations":[{"raw_affiliation_string":"Data Science (Interdisciplinary), Indian Institute of Technology Guwahati, IN","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":["Department of Computer Science and Engineering, Indian Institute of Technology Guwahati, IN"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, 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":[{"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":"Prithwijit Guha","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, IIT Guwahati, IN"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, IIT Guwahati, IN","institution_ids":["https://openalex.org/I1317621060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048648865"],"corresponding_institution_ids":["https://openalex.org/I1317621060"],"apc_list":null,"apc_paid":null,"fwci":0.1204,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46173763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9934999942779541,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.989799976348877,"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":0.9378324747085571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6427108645439148},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6061838865280151},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6057022213935852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5226999521255493},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4220186471939087}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.9378324747085571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6427108645439148},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6061838865280151},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6057022213935852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5226999521255493},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4220186471939087}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627631.3627670","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627631.3627670","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2343954916","https://openalex.org/W2560730294","https://openalex.org/W2597425697","https://openalex.org/W3037773948","https://openalex.org/W4301045096"],"related_works":["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","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"system":[4],"responds":[5,69],"to":[6,70,111,159,164],"a":[7,23,41,45,57,64,87],"natural":[8,100],"language":[9,101],"question":[10],"in":[11],"context":[12],"of":[13,33,40,55,80,86,121],"an":[14],"image.":[15],"This":[16,106,128],"problem":[17,25],"has":[18],"been":[19],"primarily":[20],"formulated":[21],"as":[22,29,75,112],"classification":[24],"with":[26,72,145],"the":[27,30,36,52,84,90,118,125,165],"answers":[28],"finite":[31],"number":[32],"classes.":[34],"Thus,":[35],"generated":[37],"response":[38],"consists":[39],"single":[42],"word":[43],"or":[44],"short":[46],"phrase.":[47],"However,":[48],"this":[49,61,81],"also":[50],"limits":[51],"linguistic":[53],"capabilities":[54],"such":[56],"system.":[58],"In":[59],"contrast,":[60],"work":[62,82],"presents":[63],"Sentence-based":[65],"VQA":[66,97,141],"(S-VQA)":[67],"which":[68],"questions":[71],"complete":[73],"sentences":[74],"answers.":[76],"The":[77,114,136,154],"first":[78],"contribution":[79,116],"is":[83,109,129,143],"development":[85],"dataset":[88,98,108],"from":[89],"Task":[91],"Directed":[92],"Image":[93],"Understanding":[94],"Challenge":[95],"(TDIUC)":[96],"using":[99,132],"rules":[102],"and":[103,148],"pretrained":[104],"para-phrasers.":[105],"new":[107],"referred":[110],"TDIUC-SVQA.":[113],"second":[115],"involves":[117],"performance":[119],"evaluation":[120],"multiple":[122],"models":[123,156],"on":[124],"TDIUC-SVQA":[126],"dataset.":[127],"performed":[130],"by":[131],"two":[133],"multi-modal":[134],"models.":[135],"Bottom-Up":[137],"Top-Down":[138],"Attention":[139],"based":[140],"model":[142],"combined":[144],"LSTM":[146],"decoder":[147],"Attention-on-Attention":[149],"Network":[150],"for":[151],"answer":[152],"generation.":[153],"proposed":[155],"are":[157],"observed":[158],"provide":[160],"improved":[161],"results":[162],"compared":[163],"baseline":[166],"model.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}