{"id":"https://openalex.org/W2791103749","doi":"https://doi.org/10.1109/icip.2017.8296600","title":"A cascaded long short-term memory (LSTM) driven generic visual question answering (VQA)","display_name":"A cascaded long short-term memory (LSTM) driven generic visual question answering (VQA)","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2791103749","doi":"https://doi.org/10.1109/icip.2017.8296600","mag":"2791103749"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2017.8296600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2017.8296600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Image Processing (ICIP)","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/A5040174394","display_name":"Iqbal Chowdhury","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Iqbal Chowdhury","raw_affiliation_strings":["Queensland University of Technology"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038839161","display_name":"Kien Nguyen","orcid":"https://orcid.org/0000-0002-3466-9218"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kien Nguyen","raw_affiliation_strings":["Queensland University of Technology"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034095159","display_name":"Clinton Fookes","orcid":"https://orcid.org/0000-0002-8515-6324"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Clinton Fookes","raw_affiliation_strings":["Queensland University of Technology"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055128383","display_name":"Sridha Sridharan","orcid":"https://orcid.org/0000-0003-4316-9001"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sridha Sridharan","raw_affiliation_strings":["Queensland University of Technology"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040174394"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":0.5461,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.76962672,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"abs 1511 5960","issue":null,"first_page":"1842","last_page":"1846"},"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":0.9993000030517578,"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":0.9980000257492065,"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":0.9370414018630981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8266746401786804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.739537239074707},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5721999406814575},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5323781371116638},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5192075371742249},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.49433279037475586},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4530789256095886},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4461895227432251},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4317372143268585},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.42956024408340454},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3944004774093628},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38444554805755615}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.9370414018630981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8266746401786804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.739537239074707},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5721999406814575},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5323781371116638},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5192075371742249},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.49433279037475586},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4530789256095886},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4461895227432251},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4317372143268585},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.42956024408340454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3944004774093628},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38444554805755615},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icip.2017.8296600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2017.8296600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:116207","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP)","raw_type":"Chapter in Book, Report or Conference volume"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1581407678","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1983927101","https://openalex.org/W2064675550","https://openalex.org/W2117539524","https://openalex.org/W2131571251","https://openalex.org/W2142192571","https://openalex.org/W2151498684","https://openalex.org/W2155541015","https://openalex.org/W2174492417","https://openalex.org/W2293453011","https://openalex.org/W2295744208","https://openalex.org/W2442626797","https://openalex.org/W2496096353","https://openalex.org/W2962835968","https://openalex.org/W2963398599","https://openalex.org/W2963572611","https://openalex.org/W2963579811","https://openalex.org/W2963672682","https://openalex.org/W2963954913","https://openalex.org/W2964018924","https://openalex.org/W2964136408","https://openalex.org/W2964138017","https://openalex.org/W2964138343","https://openalex.org/W3099514962","https://openalex.org/W4250857377","https://openalex.org/W4294375521","https://openalex.org/W4298392976","https://openalex.org/W6610616021","https://openalex.org/W6634906388","https://openalex.org/W6636501129","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6679713772","https://openalex.org/W6682086655","https://openalex.org/W6685271692","https://openalex.org/W6685337303","https://openalex.org/W6685520387","https://openalex.org/W6685574838","https://openalex.org/W6697306443","https://openalex.org/W6697449767"],"related_works":["https://openalex.org/W128392744","https://openalex.org/W3107474891","https://openalex.org/W1602056621","https://openalex.org/W105002793","https://openalex.org/W207304934","https://openalex.org/W2128901302","https://openalex.org/W1527340856","https://openalex.org/W2366644548","https://openalex.org/W2138279922","https://openalex.org/W1518289136"],"abstract_inverted_index":{"A":[0],"cascaded":[1],"long":[2],"short-term":[3],"memory":[4],"(LSTM)":[5],"architecture":[6,26],"with":[7],"discriminant":[8],"feature":[9],"learning":[10,106],"is":[11,48,78,99,107],"proposed":[12,24,61],"for":[13,71,122],"the":[14,60,66,83,96],"task":[15],"of":[16,33,37,44,69,75,92,104,126],"question":[17,38,62,70,114],"answering":[18,63,115],"on":[19],"real":[20],"world":[21],"images.":[22],"The":[23],"LSTM":[25],"jointly":[27],"learns":[28],"visual":[29,46,113],"features":[30,47],"and":[31],"parts":[32],"speech":[34],"(POS)":[35],"tags":[36],"words":[39],"or":[40],"tokens.":[41],"Also,":[42],"dimensionality":[43],"deep":[45],"reduced":[49],"by":[50],"applying":[51],"Principal":[52],"Component":[53],"Analysis":[54],"(PCA)":[55],"technique.":[56],"In":[57],"this":[58,90,102],"manner,":[59],"model":[64],"captures":[65],"generic":[67,105],"pattern":[68],"a":[72,108,111],"given":[73],"context":[74],"image":[76],"which":[77,118],"just":[79],"not":[80],"constricted":[81],"within":[82],"training":[84],"dataset.":[85],"Empirical":[86],"outcome":[87],"shows":[88],"that":[89,101],"kind":[91,103],"approach":[93],"significantly":[94],"improves":[95],"accuracy.":[97],"It":[98],"believed":[100],"step":[109],"towards":[110],"real-world":[112],"(VQA)":[116],"system":[117],"will":[119],"perform":[120],"well":[121],"all":[123],"possible":[124],"forms":[125],"open-ended":[127],"natural":[128],"language":[129],"queries.":[130]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}