{"id":"https://openalex.org/W3003396160","doi":"https://doi.org/10.1109/iros40897.2019.8967758","title":"Exploring logical consistency and viewport sensitivity in compositional VQA models","display_name":"Exploring logical consistency and viewport sensitivity in compositional VQA models","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3003396160","doi":"https://doi.org/10.1109/iros40897.2019.8967758","mag":"3003396160"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8967758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5070799483","display_name":"Gabriela \u0160ejnov\u00e1","orcid":"https://orcid.org/0000-0002-0045-6425"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Gabriela Sejnova","raw_affiliation_strings":["Czech Technical University,Department of Cybernetics","Department of Cybernetics, Czech Technical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Technical University,Department of Cybernetics","institution_ids":["https://openalex.org/I44504214"]},{"raw_affiliation_string":"Department of Cybernetics, Czech Technical University","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018900043","display_name":"Michal Vavre\u010dka","orcid":"https://orcid.org/0000-0002-0152-2682"},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Michal Vavrecka","raw_affiliation_strings":["Czech Institute of Informatics, Robotics, and Cybernetics of the Czech Technical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Institute of Informatics, Robotics, and Cybernetics of the Czech Technical University","institution_ids":["https://openalex.org/I4210152232"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076818483","display_name":"Michael Tesa\u0159","orcid":null},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Michael Tesar","raw_affiliation_strings":["Czech Technical University,Department of Cybernetics","Department of Cybernetics, Czech Technical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Technical University,Department of Cybernetics","institution_ids":["https://openalex.org/I44504214"]},{"raw_affiliation_string":"Department of Cybernetics, Czech Technical University","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072116111","display_name":"Radoslav \u0160koviera","orcid":"https://orcid.org/0000-0002-9764-4325"},"institutions":[{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Radoslav Skoviera","raw_affiliation_strings":["Czech Institute of Informatics, Robotics, and Cybernetics of the Czech Technical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Institute of Informatics, Robotics, and Cybernetics of the Czech Technical University","institution_ids":["https://openalex.org/I4210152232"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2108","last_page":"2113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/viewport","display_name":"Viewport","score":0.8160701990127563},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7421210408210754},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7244459390640259},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7040307521820068},{"id":"https://openalex.org/keywords/consistency-model","display_name":"Consistency model","score":0.6634881496429443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6055801510810852},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5517280101776123},{"id":"https://openalex.org/keywords/sequential-consistency","display_name":"Sequential consistency","score":0.4729868173599243},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.461581289768219},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43727031350135803},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4179176688194275},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4155412018299103},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.41306138038635254},{"id":"https://openalex.org/keywords/data-consistency","display_name":"Data consistency","score":0.2943902611732483},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.20963981747627258}],"concepts":[{"id":"https://openalex.org/C2778090530","wikidata":"https://www.wikidata.org/wiki/Q2523931","display_name":"Viewport","level":2,"score":0.8160701990127563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7421210408210754},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7244459390640259},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7040307521820068},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.6634881496429443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6055801510810852},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5517280101776123},{"id":"https://openalex.org/C82029504","wikidata":"https://www.wikidata.org/wiki/Q4373882","display_name":"Sequential consistency","level":4,"score":0.4729868173599243},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.461581289768219},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43727031350135803},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4179176688194275},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4155412018299103},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.41306138038635254},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.2943902611732483},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.20963981747627258},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros40897.2019.8967758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W142418853","https://openalex.org/W2108598243","https://openalex.org/W2124915094","https://openalex.org/W2194775991","https://openalex.org/W2561715562","https://openalex.org/W2563399268","https://openalex.org/W2618065827","https://openalex.org/W2760103357","https://openalex.org/W2773249164","https://openalex.org/W2785578203","https://openalex.org/W2793546384","https://openalex.org/W2793589656","https://openalex.org/W2904311512","https://openalex.org/W2962716332","https://openalex.org/W2963143606","https://openalex.org/W2963224792","https://openalex.org/W2963937837","https://openalex.org/W2964118342","https://openalex.org/W3099849198","https://openalex.org/W6687668866","https://openalex.org/W6747437934","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2123855908","https://openalex.org/W4290062159","https://openalex.org/W2971748376","https://openalex.org/W2497440208","https://openalex.org/W2275529935","https://openalex.org/W3010022189","https://openalex.org/W2374240972","https://openalex.org/W4301894417","https://openalex.org/W2150223718","https://openalex.org/W1555579555"],"abstract_inverted_index":{"The":[0,150],"most":[1,66],"recent":[2],"architectures":[3],"for":[4,64],"Visual":[5],"Question":[6],"Answering":[7],"(VQA),":[8],"such":[9],"as":[10],"TbD":[11],"or":[12],"DDRprog,":[13],"have":[14],"already":[15],"outperformed":[16],"human-level":[17],"accuracy":[18,130],"on":[19,33,137],"benchmark":[20],"datasets":[21],"(e.g.":[22,47],"CLEVR).":[23],"We":[24,112],"administered":[25],"an":[26],"advanced":[27],"analysis":[28],"of":[29,39,53,80,90,104,147,174],"their":[30],"performance":[31],"based":[32],"novel":[34],"metrics":[35],"called":[36],"consistency":[37,63,132],"(sum":[38],"all":[40],"object":[41],"feature":[42],"instances":[43],"in":[44,56,94,162,177],"the":[45,50,54,57,65,81,91,105,109,129,148,158,163,168,171,175,178],"scene":[46],"shapes)":[48],"equals":[49],"total":[51],"number":[52],"objects":[55],"scene)":[58],"and":[59,131,170],"revealed":[60],"only":[61],"56%":[62],"accurate":[67],"architecture":[68],"(TbD).":[69],"In":[70],"respect":[71],"to":[72,127,143,156],"this":[73],"finding,":[74],"we":[75,140],"propose":[76],"a":[77,99,115],"new":[78],"method":[79,152],"VQA":[82,92],"training,":[83],"which":[84],"reaches":[85],"98%":[86],"consistency.":[87],"Furthermore,":[88],"testing":[89],"model":[93],"real":[95,164],"world":[96],"brings":[97],"out":[98],"problem":[100],"with":[101,119,123],"precise":[102],"mimicking":[103],"camera":[106,125,160,176],"position":[107,146,173],"from":[108,133],"original":[110],"dataset.":[111],"therefore":[113],"created":[114],"virtual":[116],"environment":[117,165],"along":[118],"its":[120],"real-world":[121],"counterpart":[122],"variable":[124],"positions":[126],"test":[128],"different":[134],"viewports.":[135],"Based":[136],"these":[138],"errors,":[139],"were":[141],"able":[142],"estimate":[144],"optimal":[145,159],"camera.":[149],"proposed":[151],"thus":[153],"allows":[154],"us":[155],"find":[157],"viewport":[161],"without":[166],"knowing":[167],"geometry":[169],"exact":[172],"synthetic":[179],"training":[180],"environment.":[181]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}