{"id":"https://openalex.org/W4393206886","doi":"https://doi.org/10.1109/tnnls.2024.3377636","title":"Latent Attention Network With Position Perception for Visual Question Answering","display_name":"Latent Attention Network With Position Perception for Visual Question Answering","publication_year":2024,"publication_date":"2024-03-26","ids":{"openalex":"https://openalex.org/W4393206886","doi":"https://doi.org/10.1109/tnnls.2024.3377636","pmid":"https://pubmed.ncbi.nlm.nih.gov/38530725"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3377636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3377636","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100345320","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0001-6270-7771"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072723528","display_name":"Xiaoqiang Liu","orcid":"https://orcid.org/0000-0001-8342-5896"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqiang Liu","raw_affiliation_strings":["Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100621319","display_name":"Zhe Wang","orcid":"https://orcid.org/0000-0002-3759-2041"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100345320"],"corresponding_institution_ids":["https://openalex.org/I143593769"],"apc_list":null,"apc_paid":null,"fwci":1.0497,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76040849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"36","issue":"3","first_page":"5059","last_page":"5069"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.995199978351593,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9947999715805054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.7896350622177124},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7466020584106445},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6796169877052307},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6179004311561584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6068568825721741},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5887089967727661},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.5438334345817566},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.4946610629558563},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4239910840988159},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3814042806625366},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12795290350914001},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10812747478485107}],"concepts":[{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.7896350622177124},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7466020584106445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6796169877052307},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6179004311561584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6068568825721741},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5887089967727661},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.5438334345817566},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.4946610629558563},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4239910840988159},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3814042806625366},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12795290350914001},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10812747478485107},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3377636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3377636","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:38530725","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38530725","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6893319343","display_name":null,"funder_award_id":"22ZR1418400","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W2174492417","https://openalex.org/W2190656909","https://openalex.org/W2250539671","https://openalex.org/W2560730294","https://openalex.org/W2584723080","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2778748054","https://openalex.org/W2787119853","https://openalex.org/W2890531016","https://openalex.org/W2896902935","https://openalex.org/W2949197413","https://openalex.org/W2962994687","https://openalex.org/W2963150162","https://openalex.org/W2963176022","https://openalex.org/W2963383024","https://openalex.org/W2963521239","https://openalex.org/W2963656855","https://openalex.org/W2963717374","https://openalex.org/W2964067226","https://openalex.org/W2964072591","https://openalex.org/W2966683369","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W2976669726","https://openalex.org/W2996703886","https://openalex.org/W3004349648","https://openalex.org/W3006750887","https://openalex.org/W3034787499","https://openalex.org/W3035160838","https://openalex.org/W3035497460","https://openalex.org/W3080952252","https://openalex.org/W3087338569","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3107273227","https://openalex.org/W3121052081","https://openalex.org/W3131825083","https://openalex.org/W3134284227","https://openalex.org/W3135705837","https://openalex.org/W3152635550","https://openalex.org/W3173178959","https://openalex.org/W3173220247","https://openalex.org/W3174377922","https://openalex.org/W3177224328","https://openalex.org/W3184784418","https://openalex.org/W3185066916","https://openalex.org/W3195541832","https://openalex.org/W3211013634","https://openalex.org/W3212065237","https://openalex.org/W4205432963","https://openalex.org/W4206324769","https://openalex.org/W4210836196","https://openalex.org/W4221161347","https://openalex.org/W4285216227","https://openalex.org/W4289243726","https://openalex.org/W4309368547","https://openalex.org/W6631190155","https://openalex.org/W6681368121","https://openalex.org/W6685520387","https://openalex.org/W6687239747","https://openalex.org/W6719057275","https://openalex.org/W6728881024","https://openalex.org/W6747353509","https://openalex.org/W6748581942","https://openalex.org/W6752083267","https://openalex.org/W6756398402","https://openalex.org/W6767211374","https://openalex.org/W6787572754","https://openalex.org/W6810034224"],"related_works":["https://openalex.org/W4395694182","https://openalex.org/W2107329017","https://openalex.org/W2036134356","https://openalex.org/W2015353518","https://openalex.org/W3127825725","https://openalex.org/W2759653627","https://openalex.org/W2781516422","https://openalex.org/W2964305556","https://openalex.org/W4394909987","https://openalex.org/W2519822756"],"abstract_inverted_index":{"For":[0],"exploring":[1],"the":[2,14,68,76,80,86,96,99,102,118,122,138,146,168],"complex":[3,87],"relative":[4,50,88,113],"position":[5,11,33,51,77,89,114],"relationships":[6],"among":[7],"multiobject":[8,123],"with":[9,32,47],"multiple":[10,92],"prepositions":[12,78],"in":[13,29,79],"question,":[15],"we":[16,127],"propose":[17,129],"a":[18,38,130],"novel":[19,39,131],"latent":[20,110],"attention":[21,63,72,100],"(LA)":[22],"network":[23],"for":[24,143],"visual":[25,71],"question":[26],"answering":[27],"(VQA),":[28],"which":[30],"LA":[31,40,65,83],"perception":[34],"is":[35],"extracted":[36],"by":[37,53,66],"generation":[41],"module":[42,57,134],"(LAGM)":[43],"and":[44,49,94,112,163,174],"encoded":[45],"along":[46],"absolute":[48],"relations":[52,115],"our":[54,155],"proposed":[55,156],"position-aware":[56],"(PAM).":[58],"The":[59,82,107],"LAGM":[60],"reconstructs":[61],"original":[62],"into":[64],"capturing":[67],"tendency":[69],"of":[70,91,120,140,148],"shifting":[73],"according":[74],"to":[75,101,116,136],"question.":[81],"accurately":[84],"captures":[85],"features":[90],"objects":[93],"helps":[95],"model":[97],"locate":[98],"correct":[103],"object":[104],"or":[105],"region.":[106],"PAM":[108],"adopts":[109],"state":[111],"enhance":[117],"capability":[119],"comprehending":[121],"correlations.":[124],"In":[125],"addition,":[126],"also":[128],"gated":[132],"counting":[133,149],"(GCM)":[135],"strengthen":[137],"sensitivity":[139],"quantitative":[141],"knowledge":[142],"effectively":[144],"improving":[145],"performance":[147,160],"questions.":[150],"Extensive":[151],"experiments":[152],"demonstrate":[153],"that":[154],"method":[157],"achieves":[158],"excellent":[159],"on":[161,167],"VQA":[162,172,175],"outperforms":[164],"state-of-the-art":[165],"methods":[166],"widely":[169],"used":[170],"datasets":[171],"v2":[173],"v1.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}