{"id":"https://openalex.org/W2891525235","doi":"https://doi.org/10.1145/3230467.3230476","title":"Visual Question Answering Agent with Visual and Textual Attention","display_name":"Visual Question Answering Agent with Visual and Textual Attention","publication_year":2018,"publication_date":"2018-05-21","ids":{"openalex":"https://openalex.org/W2891525235","doi":"https://doi.org/10.1145/3230467.3230476","mag":"2891525235"},"language":"en","primary_location":{"id":"doi:10.1145/3230467.3230476","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3230467.3230476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 International Conference on E-business and Mobile Commerce","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/A5086171163","display_name":"Lorena Kodra","orcid":null},"institutions":[{"id":"https://openalex.org/I193184871","display_name":"Polytechnic University of Tirana","ror":"https://ror.org/05aec4025","country_code":"AL","type":"education","lineage":["https://openalex.org/I193184871"]}],"countries":["AL"],"is_corresponding":true,"raw_author_name":"Lorena Kodra","raw_affiliation_strings":["Polytechnic University of Tirana, Albania"],"affiliations":[{"raw_affiliation_string":"Polytechnic University of Tirana, Albania","institution_ids":["https://openalex.org/I193184871"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064898804","display_name":"Elinda Kajo Me\u00e7e","orcid":"https://orcid.org/0009-0002-7353-476X"},"institutions":[{"id":"https://openalex.org/I193184871","display_name":"Polytechnic University of Tirana","ror":"https://ror.org/05aec4025","country_code":"AL","type":"education","lineage":["https://openalex.org/I193184871"]}],"countries":["AL"],"is_corresponding":false,"raw_author_name":"Elinda Kajo Me\u00e7e","raw_affiliation_strings":["Polytechnic University of Tirana, Albania"],"affiliations":[{"raw_affiliation_string":"Polytechnic University of Tirana, Albania","institution_ids":["https://openalex.org/I193184871"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086171163"],"corresponding_institution_ids":["https://openalex.org/I193184871"],"apc_list":null,"apc_paid":null,"fwci":0.1045,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.44853344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"34","last_page":"38"},"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":0.9830999970436096,"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":0.9822999835014343,"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/computer-science","display_name":"Computer science","score":0.8508099317550659},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.8464905023574829},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7402743101119995},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.7066382169723511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.626209020614624},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6007674336433411},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5686041116714478},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.561539351940155},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49817490577697754},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48313137888908386},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4661131501197815},{"id":"https://openalex.org/keywords/intelligent-agent","display_name":"Intelligent agent","score":0.43402668833732605},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4014093577861786},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38054919242858887},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33489036560058594}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8508099317550659},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8464905023574829},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7402743101119995},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.7066382169723511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.626209020614624},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6007674336433411},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5686041116714478},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.561539351940155},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49817490577697754},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48313137888908386},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4661131501197815},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.43402668833732605},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4014093577861786},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38054919242858887},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33489036560058594},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3230467.3230476","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3230467.3230476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 International Conference on E-business and Mobile Commerce","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8500000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W753012316","https://openalex.org/W1533861849","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W2023615143","https://openalex.org/W2064675550","https://openalex.org/W2293453011","https://openalex.org/W2463565445","https://openalex.org/W2546696630","https://openalex.org/W2553418567","https://openalex.org/W2951690276","https://openalex.org/W2962749469","https://openalex.org/W2962835968","https://openalex.org/W2963383024","https://openalex.org/W2963656855","https://openalex.org/W2963672682","https://openalex.org/W2963954913"],"related_works":["https://openalex.org/W3157284875","https://openalex.org/W2259406085","https://openalex.org/W3009270862","https://openalex.org/W2099715052","https://openalex.org/W2147241511","https://openalex.org/W4226247999","https://openalex.org/W4213176082","https://openalex.org/W3090872036","https://openalex.org/W2187398150","https://openalex.org/W3209772662"],"abstract_inverted_index":{"Advancements":[0],"in":[1,13,24,110,144,182],"computer":[2],"vision,":[3],"natural":[4,63,81],"language":[5,64,82],"processing":[6],"and":[7,33,78,138,161,197,201],"deep":[8],"learning":[9],"techniques":[10,88],"have":[11,20],"resulted":[12],"the":[14,25,73,76,86,95,100,108,114,141,148,155,170,195,199],"creation":[15],"of":[16,85,107,140,169,194,203],"intelligent":[17,58],"systems":[18],"that":[19,42,128,163],"achieved":[21],"impressive":[22],"results":[23,196],"visually":[26],"grounded":[27],"tasks":[28],"such":[29],"as":[30],"image":[31,77,143],"captioning":[32],"visual":[34],"question":[35,65,74,136,177],"answering":[36],"(VQA).":[37],"VQA":[38],"is":[39,94],"a":[40,48,62,80,121,191],"task":[41,93],"can":[43],"be":[44],"used":[45],"to":[46,51,60,90,102,112,132,146,184],"evaluate":[47,151],"system's":[49],"capacity":[50],"understand":[52],"an":[53,57,67],"image.":[54,68],"It":[55,98],"requires":[56],"agent":[59,70,101],"answer":[61,113],"about":[66],"The":[69],"must":[71],"ground":[72],"into":[75],"return":[79],"answer.":[83,149],"One":[84],"latest":[87],"proposed":[89,157],"tackle":[91],"this":[92,117,180],"attention":[96,131],"mechanism.":[97],"allows":[99],"focus":[103,133],"on":[104,134,154],"specific":[105,135],"parts":[106,139],"input":[109,142],"order":[111,145,183],"question.":[115],"In":[116],"paper":[118],"we":[119,173],"propose":[120,174],"novel":[122],"long":[123],"short-term":[124],"memory":[125],"(LSTM)":[126],"architecture":[127],"uses":[129],"dual":[130],"words":[137],"generate":[147],"We":[150,188],"our":[152,204],"solution":[153],"recently":[156],"Visual":[158],"7W":[159],"dataset":[160,181],"show":[162,198],"it":[164],"performs":[165],"better":[166],"than":[167],"state":[168],"art.":[171],"Additionally,":[172],"two":[175],"new":[176],"types":[178],"for":[179],"improve":[185],"model":[186],"evaluation.":[187],"also":[189],"make":[190],"qualitative":[192],"analysis":[193],"strength":[200],"weakness":[202],"agent.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}